hoàn thành cơ bản các chức năng

update attribute table

.gitattributes

@@ -0,0 +1,4 @@
+*.tif filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.nc filter=lfs diff=lfs merge=lfs -text
+*.ipynb filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,7 @@
+ThuanHoa/ThuanHoa_VH.tif
+ThuanHoa/ThuanHoa_VV.tif
+model_train/model.joblib
+model_train/model_new.joblib
+backup_model_train/model.joblib
+backup_model_train/model_new.joblib
+dataset_cache/sentinel2_timeseries_40scenes.nc

.vscode/settings.json

@@ -1,5 +0,0 @@
-{
-    "python-envs.defaultEnvManager": "ms-python.python:conda",
-    "python-envs.defaultPackageManager": "ms-python.python:conda",
-    "python-envs.pythonProjects": []
-}

01.train_ODC.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3fecbef4c80ff1bd20922e6b2250d94ac05e55c3a2efbff4da20fcea3d739f
+size 39812

01.train_ODC_XGBoost.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350b680a5454d4d080d8d943d723ea01668c9c19219cb8feb396c54462ee89c3
+size 857629

01.train_ODC_local_with_Mic_supplyer.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c347e98288e77ddb7579d4cfa2b49924a993f7173a2d12155ef7a1893082b1
+size 163627

02.predict_ODC.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54efd837e5dcbfbd4bd8c2cfc44ff1b5eecbf03de302d41fab0ed47257bfa62c
+size 4828615

03.compare_ODC.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d0f97e1e623ab49fe749054c8b2c3901ff0807b52667289108bbd0b8220e2a
+size 2240648

KetQuaPhanLoaiDat.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff33ab950e3524342a99e70a02598ccb1ca57e60627c887c10b34466eabf3e87
+size 3536032

ThuanHoa/.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a62b68a633d79c53a6fd8893e8ea42dcf2b9a8a3e907b1b9861661f04f21517
+size 72

ThuanHoa/KetQua/NN.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520c3480efaafdf844c3bba3dd165a8e44f3318ab21209539c78201f18fd6312
+size 3066028

ThuanHoa/KetQua/PNN.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3bff20682fc510a9c41b5aa2b42e3ebef8098ed81e27b4436f9ae86f47b9a6
+size 3066028

ThuanHoa/KetQua/TQ.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322f48d2d54ee921facfc3c0c44b320a86a90694e1779b683824264f9affa3fc
+size 3066028

ThuanHoa/ThuanHoa_VH.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2948384b4c43483675d366b75b7bcdceb63fe5a8ad7d9b7a84ee4a1018cfc826
+size 55333632

ThuanHoa/ThuanHoa_VV.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d5a53bba7a6db30b7f80bc4250d09edacfd244e97d7993382927a9bde85c6f7
+size 55738194

api_server.py

@@ -0,0 +1,788 @@
+"""
+API Server for Land Classification Model Training
+Cho phép chọn dữ liệu và cấu hình training qua giao diện web
+"""
+
+from fastapi import FastAPI, BackgroundTasks, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.staticfiles import StaticFiles
+from fastapi.responses import HTMLResponse, FileResponse
+from pydantic import BaseModel
+from typing import Optional, List
+import uvicorn
+import joblib
+import json
+from datetime import datetime
+from pathlib import Path
+import sys
+
+app = FastAPI(title="Land Classification Training API", version="1.0.0")
+
+# Enable CORS
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Global training status
+training_status = {
+    "is_training": False,
+    "progress": "",
+    "error": None,
+    "result": None,
+    "start_time": None,
+    "end_time": None,
+    "cancel_requested": False
+}
+
+# Global prediction status
+prediction_status = {
+    "is_predicting": False,
+    "progress": "",
+    "error": None,
+    "result": None,
+    "output_file": None,
+    "start_time": None,
+    "end_time": None
+}
+
+
+class TrainingConfig(BaseModel):
+    """Cấu hình training"""
+    # Khu vực (bbox)
+    min_lon: float = 105.6
+    min_lat: float = 9.3
+    max_lon: float = 106.2
+    max_lat: float = 9.8
+    
+    # Thời gian
+    start_date: str = "2023-03-01"
+    end_date: str = "2023-05-31"
+    
+    # Dữ liệu
+    max_scenes: int = 12
+    cloud_cover: int = 30
+    resolution: int = 20  # 10m hoặc 20m
+    
+    # Model parameters
+    model_type: str = "xgboost"  # xgboost, random_forest, decision_tree, svm, cnn
+    n_estimators: int = 100
+    max_depth: int = 20
+    learning_rate: float = 0.1
+    use_gpu: bool = True
+    
+    # Cache
+    use_cache: bool = True  # Cache dataset để test nhanh hơn
+    
+    # Training data
+    training_shapefile: str = "train/ST_training data_updated_1130points_new.shp"
+
+
+class PredictionConfig(BaseModel):
+    """Cấu hình dự đoán"""
+    # Model to use
+    model_filename: str
+    
+    # Khu vực (bbox)
+    min_lon: float = 105.6
+    min_lat: float = 9.3
+    max_lon: float = 106.2
+    max_lat: float = 9.8
+    
+    # Thời gian
+    start_date: str = "2023-03-01"
+    end_date: str = "2023-05-31"
+    
+    # Dữ liệu
+    max_scenes: int = 12
+    cloud_cover: int = 30
+    resolution: int = 20
+
+
+class TrainingStatus(BaseModel):
+    """Trạng thái training"""
+    is_training: bool
+    progress: str
+    error: Optional[str]
+    result: Optional[dict]
+    start_time: Optional[str]
+    end_time: Optional[str]
+
+
+@app.get("/", response_class=HTMLResponse)
+async def root():
+    """Serve giao diện web"""
+    html_file = Path(__file__).parent / "training_interface.html"
+    if html_file.exists():
+        return FileResponse(html_file)
+    else:
+        return HTMLResponse("""
+        <html>
+            <head><title>Training Interface</title></head>
+            <body>
+                <h1>Land Classification Training API</h1>
+                <p>API Documentation: <a href="/docs">/docs</a></p>
+                <p>Training Interface: Tạo file training_interface.html</p>
+            </body>
+        </html>
+        """)
+
+
+@app.get("/api/config/presets")
+async def get_presets():
+    """Lấy các preset cấu hình sẵn"""
+    return {
+        "presets": [
+            {
+                "name": "PC - Nhỏ (3 tháng, 20m, 12 scenes)",
+                "config": {
+                    "min_lon": 105.6, "min_lat": 9.3, "max_lon": 106.2, "max_lat": 9.8,
+                    "start_date": "2023-03-01", "end_date": "2023-05-31",
+                    "max_scenes": 12, "cloud_cover": 30, "resolution": 20
+                }
+            },
+            {
+                "name": "Server - Trung bình (6 tháng, 10m, 30 scenes)",
+                "config": {
+                    "min_lon": 105.5, "min_lat": 9.2, "max_lon": 106.4, "max_lat": 10.0,
+                    "start_date": "2023-01-01", "end_date": "2023-06-30",
+                    "max_scenes": 30, "cloud_cover": 30, "resolution": 10
+                }
+            },
+            {
+                "name": "Full - Lớn (1 năm, 10m, 60 scenes)",
+                "config": {
+                    "min_lon": 105.5, "min_lat": 9.2, "max_lon": 106.4, "max_lat": 10.0,
+                    "start_date": "2022-09-01", "end_date": "2023-10-01",
+                    "max_scenes": 60, "cloud_cover": 50, "resolution": 10
+                }
+            }
+        ]
+    }
+
+
+@app.get("/api/training/status", response_model=TrainingStatus)
+async def get_training_status():
+    """Kiểm tra trạng thái training"""
+    return training_status
+
+
+@app.post("/api/training/start")
+async def start_training(config: TrainingConfig, background_tasks: BackgroundTasks):
+    """Bắt đầu training với config đã chọn"""
+    global training_status
+    
+    if training_status["is_training"]:
+        raise HTTPException(status_code=400, detail="Training đang chạy, vui lòng đợi")
+    
+    # Reset status
+    training_status = {
+        "is_training": True,
+        "progress": "Đang khởi tạo...",
+        "error": None,
+        "result": None,
+        "start_time": datetime.now().isoformat(),
+        "end_time": None
+    }
+    
+    # Run training in background
+    background_tasks.add_task(run_training, config)
+    
+    return {"message": "Training đã bắt đầu", "status": training_status}
+
+
+@app.post("/api/training/stop")
+async def stop_training():
+    """Dừng training (nếu đang chạy)"""
+    global training_status
+    
+    if not training_status["is_training"]:
+        return {"message": "Không có training nào đang chạy"}
+    
+    # Set cancel flag - the training will check this and stop
+    training_status["cancel_requested"] = True
+    training_status["progress"] = "Đang hủy training..."
+    
+    return {"message": "Đang dừng training..."}
+
+
+@app.post("/api/cache/clear")
+async def clear_cache():
+    """Xóa cache dataset"""
+    import shutil
+    cache_dir = Path("dataset_cache")
+    
+    if not cache_dir.exists():
+        return {"message": "Không có cache để xóa", "deleted": 0}
+    
+    # Count files
+    cache_files = list(cache_dir.glob("*.joblib"))
+    count = len(cache_files)
+    
+    # Delete all cache files
+    for cache_file in cache_files:
+        try:
+            cache_file.unlink()
+        except:
+            pass
+    
+    return {"message": f"Đã xóa {count} file cache", "deleted": count}
+
+
+@app.get("/api/cache/info")
+async def get_cache_info():
+    """Lấy thông tin về cache với metadata đầy đủ"""
+    cache_dir = Path("dataset_cache")
+    
+    if not cache_dir.exists():
+        return {"exists": False, "files": [], "total_size_mb": 0}
+    
+    cache_files = []
+    total_size = 0
+    
+    for cache_file in cache_dir.glob("*.joblib"):
+        size = cache_file.stat().st_size
+        total_size += size
+        
+        # Try to load metadata from cache
+        metadata = {}
+        try:
+            cached_data = joblib.load(cache_file)
+            if isinstance(cached_data, dict):
+                metadata = {
+                    "bbox": cached_data.get("bbox", []),
+                    "time_range": cached_data.get("time_range", ""),
+                    "resolution": cached_data.get("resolution", 20),
+                    "n_samples": len(cached_data.get("features", [])),
+                    "created": cached_data.get("timestamp", "")
+                }
+                # Parse time_range to get start/end dates
+                if metadata["time_range"]:
+                    time_parts = metadata["time_range"].split("/")
+                    if len(time_parts) == 2:
+                        metadata["start_date"] = time_parts[0]
+                        metadata["end_date"] = time_parts[1]
+                # Parse bbox to get min/max lon/lat
+                if metadata["bbox"] and len(metadata["bbox"]) == 4:
+                    metadata["min_lon"] = metadata["bbox"][0]
+                    metadata["min_lat"] = metadata["bbox"][1]
+                    metadata["max_lon"] = metadata["bbox"][2]
+                    metadata["max_lat"] = metadata["bbox"][3]
+        except Exception as e:
+            print(f"Error loading cache metadata: {e}")
+        
+        cache_files.append({
+            "filename": cache_file.name,
+            "size_mb": round(size / 1024 / 1024, 2),
+            "modified": datetime.fromtimestamp(cache_file.stat().st_mtime).isoformat(),
+            "metadata": metadata
+        })
+    
+    # Sort by modified time (newest first)
+    cache_files.sort(key=lambda x: x["modified"], reverse=True)
+    
+    return {
+        "exists": True,
+        "files": cache_files,
+        "count": len(cache_files),
+        "total_size_mb": round(total_size / 1024 / 1024, 2)
+    }
+
+
+
+@app.get("/api/models/list")
+async def list_models():
+    """Liệt kê các model đã train"""
+    model_dir = Path("model_train")
+    if not model_dir.exists():
+        return {"models": []}
+    
+    models = []
+    for model_file in model_dir.glob("*.joblib"):
+        info_file = model_file.with_suffix('.json')
+        info = {}
+        if info_file.exists():
+            with open(info_file) as f:
+                info = json.load(f)
+        
+        models.append({
+            "filename": model_file.name,
+            "created": datetime.fromtimestamp(model_file.stat().st_mtime).isoformat(),
+            "size_mb": round(model_file.stat().st_size / 1024 / 1024, 2),
+            "info": info
+        })
+    
+    # Sort by creation time (newest first)
+    models.sort(key=lambda x: x["created"], reverse=True)
+    return {"models": models}
+
+
+@app.post("/api/prediction/start")
+async def start_prediction(config: PredictionConfig, background_tasks: BackgroundTasks):
+    """Bắt đầu dự đoán"""
+    global prediction_status
+    
+    if prediction_status["is_predicting"]:
+        raise HTTPException(status_code=400, detail="Đang có dự đoán khác đang chạy")
+    
+    # Reset status
+    prediction_status = {
+        "is_predicting": True,
+        "progress": "Đang khởi động...",
+        "error": None,
+        "result": None,
+        "output_file": None,
+        "start_time": datetime.now().isoformat(),
+        "end_time": None
+    }
+    
+    # Run prediction in background
+    background_tasks.add_task(run_prediction, config)
+    
+    return {"message": "Đã bắt đầu dự đoán", "status": prediction_status}
+
+
+@app.get("/api/prediction/status")
+async def get_prediction_status():
+    """Kiểm tra trạng thái dự đoán"""
+    return prediction_status
+
+
+async def run_training(config: TrainingConfig):
+    """Chạy training process"""
+    global training_status
+    
+    try:
+        training_status["cancel_requested"] = False
+        training_status["progress"] = "Đang import thư viện..."
+        
+        # Import training module
+        from train_module import train_model
+        
+        training_status["progress"] = "Đang load dữ liệu Sentinel-2..."
+        
+        # Function to check if training should be cancelled
+        def should_cancel():
+            return training_status.get("cancel_requested", False)
+        
+        # Run training
+        result = train_model(
+            bbox=[config.min_lon, config.min_lat, config.max_lon, config.max_lat],
+            time_range=f"{config.start_date}/{config.end_date}",
+            max_scenes=config.max_scenes,
+            cloud_cover=config.cloud_cover,
+            resolution=config.resolution,
+            training_shapefile=config.training_shapefile,
+            model_type=config.model_type,
+            n_estimators=config.n_estimators,
+            max_depth=config.max_depth,
+            learning_rate=config.learning_rate,
+            use_gpu=config.use_gpu,
+            use_cache=config.use_cache,
+            status_callback=lambda msg: update_progress(msg),
+            cancel_check=should_cancel
+        )
+        
+        if training_status.get("cancel_requested", False):
+            training_status["is_training"] = False
+            training_status["progress"] = "Đã hủy training"
+            training_status["error"] = "Training cancelled by user"
+        else:
+            training_status["is_training"] = False
+            training_status["progress"] = "Hoàn thành!"
+            training_status["result"] = result
+        training_status["end_time"] = datetime.now().isoformat()
+        
+    except Exception as e:
+        training_status["is_training"] = False
+        training_status["error"] = str(e)
+        training_status["progress"] = f"Lỗi: {str(e)}"
+        training_status["end_time"] = datetime.now().isoformat()
+        import traceback
+        print(traceback.format_exc())
+
+
+def update_progress(message: str):
+    """Cập nhật progress message"""
+    global training_status
+    training_status["progress"] = message
+    print(f"[PROGRESS] {message}")
+
+
+def update_prediction_progress(message: str):
+    """Cập nhật prediction progress message"""
+    global prediction_status
+    prediction_status["progress"] = message
+    print(f"[PREDICTION PROGRESS] {message}")
+
+
+async def run_prediction(config: PredictionConfig):
+    """Chạy prediction process - Áp dụng phương pháp từ 02.predict_ODC.ipynb"""
+    global prediction_status
+    
+    try:
+        prediction_status["progress"] = "Đang import thư viện..."
+        
+        # Import required libraries
+        import xarray as xr
+        import numpy as np
+        from datetime import datetime as dt
+        import rioxarray
+        import dask.array as da
+        
+        prediction_status["progress"] = "Đang load model..."
+        
+        # Load model
+        model_path = Path("model_train") / config.model_filename
+        if not model_path.exists():
+            raise FileNotFoundError(f"Model không tồn tại: {config.model_filename}")
+        
+        model_data = joblib.load(model_path)
+        
+        # Extract model from dict (models are saved as {'model': xgb_model, 'label_encoder': encoder})
+        if isinstance(model_data, dict):
+            model = model_data.get('model')
+            label_encoder = model_data.get('label_encoder')
+        else:
+            model = model_data
+            label_encoder = None
+        
+        # Check if it's a CNN model (PyTorch)
+        is_cnn_model = hasattr(model, '__class__') and 'CNN' in model.__class__.__name__
+        if is_cnn_model:
+            prediction_status["progress"] = "Phát hiện PyTorch CNN model..."
+            # Import PyTorch if needed
+            try:
+                import torch
+            except ImportError:
+                raise ImportError("PyTorch is required for CNN prediction. Install: pip install torch")
+        
+        prediction_status["progress"] = "Đang kết nối Microsoft Planetary Computer..."
+        
+        # Import and use Microsoft Planetary Computer STAC API
+        import pystac_client
+        import planetary_computer
+        from odc.stac import load
+        
+        catalog = pystac_client.Client.open(
+            "https://planetarycomputer.microsoft.com/api/stac/v1",
+            modifier=planetary_computer.sign_inplace,
+        )
+        
+        bbox = [config.min_lon, config.min_lat, config.max_lon, config.max_lat]
+        time_range = f"{config.start_date}/{config.end_date}"
+        
+        # ============ BƯỚC 1: TẢI DỮ LIỆU SENTINEL-2 ============
+        prediction_status["progress"] = "Đang tải dữ liệu Sentinel-2..."
+        
+        # Search Sentinel-2 data
+        s2_search = catalog.search(
+            collections=["sentinel-2-l2a"],
+            bbox=bbox,
+            datetime=time_range,
+            query={"eo:cloud_cover": {"lt": config.cloud_cover}}
+        )
+        
+        s2_items = list(s2_search.items())
+        if not s2_items:
+            raise ValueError("Không tìm thấy dữ liệu Sentinel-2 cho khu vực và thời gian này")
+        
+        s2_items = s2_items[:config.max_scenes]
+        prediction_status["progress"] = f"Đang xử lý {len(s2_items)} scenes Sentinel-2..."
+        
+        # Load Sentinel-2 data
+        s2_data = load(
+            s2_items,
+            bbox=bbox,
+            chunks={"time": 1, "x": 2048, "y": 2048},
+            groupby="solar_day",
+            resolution=config.resolution
+        )
+        
+        # ============ BƯỚC 2: TÍNH NDVI VÀ XỬ LÝ MÂY ============
+        prediction_status["progress"] = "Đang tính toán NDVI và xử lý mây..."
+        
+        # Calculate NDVI using Sentinel-2 band names (B08 = NIR, B04 = Red)
+        nir = s2_data["B08"].astype('float32')
+        red = s2_data["B04"].astype('float32')
+        ndvi = (nir - red) / (nir + red + 1e-8)
+        
+        # Mask clouds using SCL band if available
+        if "SCL" in s2_data:
+            scl = s2_data["SCL"]
+            # SCL values: 4=vegetation, 5=bare soil, 6=water - these are clear
+            # 3=cloud shadow, 8=cloud medium, 9=cloud high, 10=cirrus - mask these
+            cloud_mask = (scl == 3) | (scl == 8) | (scl == 9) | (scl == 10)
+            ndvi = ndvi.where(~cloud_mask)
+        
+        # ============ BƯỚC 3: ĐIỀN GIÁ TRỊ NAN (FILL NAN) ============
+        prediction_status["progress"] = "Đang điền giá trị bị che mây..."
+        
+        # Fill NaN using forward fill and backward fill
+        ndvi_filled = ndvi.ffill(dim='time').bfill(dim='time')
+        
+        # Resample to monthly average
+        prediction_status["progress"] = "Đang tính trung bình NDVI theo tháng..."
+        ndvi_monthly = ndvi_filled.resample(time="1ME").mean()
+        
+        # Compute NDVI (convert from dask to numpy)
+        ndvi_monthly = ndvi_monthly.compute()
+        
+        # ============ BƯỚC 4: TẢI DỮ LIỆU SENTINEL-1 (VH, VV) ============
+        prediction_status["progress"] = "Đang tải dữ liệu Sentinel-1 (Radar)..."
+        
+        # Search Sentinel-1 data
+        s1_search = catalog.search(
+            collections=["sentinel-1-rtc"],
+            bbox=bbox,
+            datetime=time_range,
+        )
+        
+        s1_items = list(s1_search.items())
+        
+        if s1_items:
+            s1_items = s1_items[:config.max_scenes]
+            prediction_status["progress"] = f"Đang xử lý {len(s1_items)} scenes Sentinel-1..."
+            
+            # Load Sentinel-1 data (without like= to avoid conflict with bbox/resolution)
+            s1_data = load(
+                s1_items,
+                bbox=bbox,
+                chunks={"time": 1, "x": 2048, "y": 2048},
+                groupby="sat:absolute_orbit",
+                resolution=config.resolution
+            )
+            
+            # Extract VH and VV bands
+            if "vh" in s1_data and "vv" in s1_data:
+                vh = s1_data["vh"].astype('float32')
+                vv = s1_data["vv"].astype('float32')
+                
+                # Resample to monthly average
+                prediction_status["progress"] = "Đang tính trung bình VH/VV theo tháng..."
+                vh_monthly = vh.resample(time="1ME").mean().compute()
+                vv_monthly = vv.resample(time="1ME").mean().compute()
+                
+                use_radar = True
+            else:
+                prediction_status["progress"] = "Không tìm thấy bands VH/VV, tiếp tục với NDVI..."
+                use_radar = False
+        else:
+            prediction_status["progress"] = "Không có dữ liệu Sentinel-1, tiếp tục với NDVI..."
+            use_radar = False
+        
+        # ============ BƯỚC 5: CHUẨN BỊ FEATURES CHO DỰ ĐOÁN ============
+        prediction_status["progress"] = "Đang chuẩn bị features cho dự đoán..."
+        
+        # Get shape information
+        n_times_ndvi = len(ndvi_monthly.time)
+        y_size = len(ndvi_monthly.y)
+        x_size = len(ndvi_monthly.x)
+        n_pixels = y_size * x_size
+        
+        # Prepare NDVI features (flatten each time step)
+        ndvi_features = []
+        for t in range(n_times_ndvi):
+            ndvi_t = ndvi_monthly.isel(time=t).values.flatten()
+            ndvi_features.append(ndvi_t)
+        
+        # Stack NDVI features
+        features = np.column_stack(ndvi_features)
+        
+        # Add radar features if available
+        if use_radar:
+            n_times_vh = len(vh_monthly.time)
+            n_times_vv = len(vv_monthly.time)
+            
+            # Add VH features
+            for t in range(min(n_times_vh, n_times_ndvi)):
+                vh_t = vh_monthly.isel(time=t).values.flatten()
+                # Resize if needed
+                if len(vh_t) != n_pixels:
+                    vh_t = np.resize(vh_t, n_pixels)
+                features = np.column_stack([features, vh_t])
+            
+            # Add VV features
+            for t in range(min(n_times_vv, n_times_ndvi)):
+                vv_t = vv_monthly.isel(time=t).values.flatten()
+                # Resize if needed
+                if len(vv_t) != n_pixels:
+                    vv_t = np.resize(vv_t, n_pixels)
+                features = np.column_stack([features, vv_t])
+        
+        # Handle NaN values in features✓ CNN PyTorch: Mạnh nhất với ảnh vệ tinh, tự học features, tương thích GPU tốt, cần pip install torch
+        features = np.nan_to_num(features, nan=0.0)
+        
+        # ============ BƯỚC 6: DỰ ĐOÁN ============
+        # Check model's expected feature count and adjust
+        try:
+            # Get expected number of features from model
+            if is_cnn_model:
+                # For PyTorch CNN, get n_features from model
+                expected_features = model.n_features
+            elif hasattr(model, 'n_features_in_'):
+                expected_features = model.n_features_in_
+            elif hasattr(model, 'feature_names_in_'):
+                expected_features = len(model.feature_names_in_)
+            else:
+                # Try to get from booster for XGBoost
+                try:
+                    expected_features = model.get_booster().num_features()
+                except:
+                    expected_features = features.shape[1]
+            
+            prediction_status["progress"] = f"Model cần {expected_features} features, đang có {features.shape[1]} features..."
+            
+            # Adjust features to match model
+            if features.shape[1] > expected_features:
+                # Trim to expected number (use only first N features - NDVI only)
+                prediction_status["progress"] = f"Cắt bớt features từ {features.shape[1]} xuống {expected_features}..."
+                features = features[:, :expected_features]
+            elif features.shape[1] < expected_features:
+                # Pad with zeros or repeat last features
+                prediction_status["progress"] = f"Thêm features từ {features.shape[1]} lên {expected_features}..."
+                n_missing = expected_features - features.shape[1]
+                # Repeat last feature column to fill
+                padding = np.tile(features[:, -1:], (1, n_missing))
+                features = np.column_stack([features, padding])
+        except Exception as e:
+            prediction_status["progress"] = f"Không thể xác định số features của model, tiếp tục với {features.shape[1]} features..."
+        
+        prediction_status["progress"] = f"Đang dự đoán với {features.shape[1]} features..."
+        
+        # Make prediction
+        if is_cnn_model:
+            # PyTorch CNN prediction
+            predictions = model.predict(features)
+        else:
+            predictions = model.predict(features)
+        
+        # Decode labels if label_encoder exists
+        if label_encoder is not None:
+            try:
+                predictions = label_encoder.inverse_transform(predictions)
+            except:
+                pass  # Keep numeric predictions if inverse_transform fails
+        
+        # Reshape to original shape
+        pred_shape = (y_size, x_size)
+        predictions_2d = predictions.reshape(pred_shape)
+        
+        # ============ BƯỚC 7: TẠO OUTPUT VÀ LƯU KẾT QUẢ ============
+        prediction_status["progress"] = "Đang tạo bản đồ phân loại..."
+        
+        # Create output xarray
+        prediction_da = xr.DataArray(
+            predictions_2d,
+            coords={
+                "y": ndvi_monthly.y,
+                "x": ndvi_monthly.x
+            },
+            dims=["y", "x"],
+            name="classification"
+        )
+        
+        # Save output
+        output_dir = Path("predictions")
+        output_dir.mkdir(exist_ok=True)
+        
+        timestamp = dt.now().strftime("%Y%m%d_%H%M%S")
+        output_file = output_dir / f"prediction_{timestamp}.tif"
+        
+        prediction_status["progress"] = "Đang lưu kết quả GeoTIFF..."
+        
+        # Set CRS and save as GeoTIFF
+        if hasattr(s2_data, 'rio') and s2_data.rio.crs is not None:
+            prediction_da.rio.write_crs(s2_data.rio.crs, inplace=True)
+        else:
+            prediction_da.rio.write_crs("EPSG:4326", inplace=True)
+        
+        prediction_da.rio.to_raster(str(output_file), driver="GTiff")
+        
+        # Get unique classes for result
+        unique_classes = np.unique(predictions_2d)
+        unique_classes = unique_classes[~np.isnan(unique_classes)].tolist()
+        
+        prediction_status["is_predicting"] = False
+        prediction_status["progress"] = "Hoàn thành!"
+        prediction_status["output_file"] = str(output_file)
+        prediction_status["result"] = {
+            "output_file": str(output_file),
+            "shape": list(pred_shape),
+            "unique_classes": unique_classes,
+            "bbox": bbox,
+            "time_range": time_range,
+            "n_features": features.shape[1],
+            "n_times_ndvi": n_times_ndvi,
+            "used_radar": use_radar,
+            "model_used": config.model_filename
+        }
+        prediction_status["end_time"] = dt.now().isoformat()
+        
+    except Exception as e:
+        prediction_status["is_predicting"] = False
+        prediction_status["error"] = str(e)
+        prediction_status["progress"] = f"Lỗi: {str(e)}"
+        prediction_status["end_time"] = dt.now().isoformat()
+        import traceback
+        print(traceback.format_exc())
+
+
+@app.get("/api/predictions/list")
+async def list_predictions():
+    """Lấy danh sách các file prediction đã tạo"""
+    predictions_dir = Path("predictions")
+    predictions_dir.mkdir(exist_ok=True)
+    
+    predictions = []
+    for pred_file in predictions_dir.glob("*.tif"):
+        predictions.append({
+            "filename": pred_file.name,
+            "created": datetime.fromtimestamp(pred_file.stat().st_mtime).isoformat(),
+            "size_mb": round(pred_file.stat().st_size / 1024 / 1024, 2),
+            "download_url": f"/api/predictions/download/{pred_file.name}"
+        })
+    
+    # Sort by creation time (newest first)
+    predictions.sort(key=lambda x: x["created"], reverse=True)
+    return {"predictions": predictions}
+
+
+@app.get("/api/predictions/download/{filename}")
+async def download_prediction(filename: str):
+    """Download file prediction GeoTIFF"""
+    predictions_dir = Path("predictions")
+    file_path = predictions_dir / filename
+    
+    # Security check: ensure filename doesn't contain path traversal
+    if ".." in filename or "/" in filename or "\\" in filename:
+        raise HTTPException(status_code=400, detail="Invalid filename")
+    
+    if not file_path.exists():
+        raise HTTPException(status_code=404, detail=f"File không tồn tại: {filename}")
+    
+    return FileResponse(
+        path=str(file_path),
+        filename=filename,
+        media_type="image/tiff",
+        headers={
+            "Content-Disposition": f"attachment; filename={filename}"
+        }
+    )
+
+
+if __name__ == "__main__":
+    print("=" * 70)
+    print("🚀 LAND CLASSIFICATION TRAINING API SERVER")
+    print("=" * 70)
+    print("\n📍 Endpoints:")
+    print("   - Web Interface: http://localhost:8000")
+    print("   - API Docs: http://localhost:8000/docs")
+    print("   - Start Training: POST http://localhost:8000/api/training/start")
+    print("   - Check Status: GET http://localhost:8000/api/training/status")
+    print("\n" + "=" * 70)
+    
+    uvicorn.run(app, host="0.0.0.0", port=8000, log_level="info")

backup_S3_download_Amazon/01.train_S3.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37686f6bbdd4590ce2dc5474eef8268f680498c2b78881a486625e264d2a1015
+size 841901

backup_S3_download_Amazon/02.predict-Test.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d28d677d39cc67e607bb418948b9e3e921351762d63b4737036fc02d1d361a
+size 3375913

backup_S3_download_Amazon/02.predict_S3.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:892cabc8da5cfcc0f9295ddb3ad32fda077027efa53e7b48e2f81965ad6ca202
+size 3361173

backup_S3_download_Amazon/03.compare-test.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbab8f823ca6965dcbe43d9ce914f8912e3976833de1b205032eec48bfa83970
+size 1670930

backup_S3_download_Amazon/03.compare_S3.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c33115ec7d6896758abf1eb8d07eba94ae15444c63f318e8adbd5d032df9a4f
+size 1671094

backup_ketquaphanloai/KetQuaPhanLoaiDatODC.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71c696efbcb9e766eb1a666cc85b4f604992a65efc7258a46a46c7f81c596db
+size 3536032

backup_ketquaphanloai/NN.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520c3480efaafdf844c3bba3dd165a8e44f3318ab21209539c78201f18fd6312
+size 3066028

backup_ketquaphanloai/PNN.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3bff20682fc510a9c41b5aa2b42e3ebef8098ed81e27b4436f9ae86f47b9a6
+size 3066028

backup_ketquaphanloai/TQ.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322f48d2d54ee921facfc3c0c44b320a86a90694e1779b683824264f9affa3fc
+size 3066028

backup_model_train/model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a446d333bf7f6d0cb7df014f12b0da3f7298f85bdfb4de06893173e90fbd5ccb
+size 14112695

backup_model_train/model_new.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eec576dffe1cc1393fdb584fb99d28db62abdd0977d41030aee5c4fa5377180
+size 11474743

backup_model_train/model_odc.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc125de4c172c98d9e50123bfcc2f8dd856e4ccd6bb04edd639badf090af2eef
+size 5077735

cloud_new/draw/draw_graph.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8004f197bab9800b257d62064bf1220b908f2b17eadce826b87f0284241a1842
+size 1420071

cloud_new/draw/draw_lines.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e989c28641beb9af91d2b12a9a0b957b2b8c6510f437a68b69271ea136cce65
+size 1604860

cloud_new/draw/draw_time_series.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7115a28f7fb41599b59f9337d7457ed4578ba989878a4ccd907c60e69be2311a
+size 973302

cloud_new/draw/test_result.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da63ad454fd0e6de316e17df9345abe1b193998d1eb97c545b6a87a66058e884
+size 766972

cloud_new/train_cloud_mask.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb8412f0ee12abb7f1bb067522b3b800102ffdfa18b84027603c5d1870c968e
+size 518845

dataset_cache/training_data_59838d7be931abe93b5dd38e7cd89ad7.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7318566231680cb0c97883b7a5e4177aa1bfeec462a0f52ed34aa103ddec210b
+size 20903

dataset_cache/training_data_73f65eba2eb052d78cdbf76250e1e68a.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cabf5e0241dcc3a73133ac8ae11171f34042c491f895b268c016407619bdfe1
+size 20903

document/giai_thich_quy_trinh_phan_loai_dat.md

@@ -0,0 +1,164 @@
+# 🌾 Giải Thích Quy Trình Phân Loại Đất Trồng Cây
+
+File notebook `02.predict_ODC.ipynb` sử dụng **Machine Learning** kết hợp với **dữ liệu vệ tinh** để phân loại các loại đất/cây trồng. Dưới đây là quy trình chi tiết:
+
+---
+
+## **Bước 1: Thu thập dữ liệu vệ tinh** (Cell 3-4)
+
+```python
+date_range = ('2022-09-01', '2023-10-01')
+longtitude_range = (105.86575, 105.94120)
+latitude_range = (9.65070, 9.69850)
+data = load_data(dc, date_range, longtitude_range, latitude_range)
+```
+
+- Lấy ảnh **Sentinel-2** (ảnh quang học) từ kho dữ liệu trong khoảng thời gian và vị trí cụ thể
+
+---
+
+## **Bước 2: Xử lý mây** (Cell 5)
+
+```python
+result = mask_clean(data)
+```
+
+- Loại bỏ các pixel bị mây che phủ để đảm bảo dữ liệu chính xác
+
+---
+
+## **Bước 3: Tính chỉ số NDVI** (Cell 6-10)
+
+```python
+ndvi = calculate_indices(result, index='NDVI', satellite_mission='s2')
+fill_nan_ndvi = fill_nan(ndvi, time_split)
+average_ndvi = fill_nan_ndvi.resample(time='1M').mean()
+```
+
+- **NDVI** (Normalized Difference Vegetation Index) = (NIR - Red) / (NIR + Red)
+- Giá trị từ **-1 đến 1**: cao = thực vật xanh tốt, thấp = đất trống/nước
+- Điền giá trị nan (mây) và tính trung bình theo tháng
+
+---
+
+## **Bước 4: Lấy dữ liệu Radar Sentinel-1** (Cell 11)
+
+```python
+dsvh, dsvv = load_data_sen1(dc, date_range, coordinates)
+average_vv = calculate_average(dsvv, time_pattern='1M')
+average_vh = calculate_average(dsvh, time_pattern='1M')
+```
+
+- **VH, VV**: Dữ liệu radar (xuyên mây), cho biết cấu trúc bề mặt
+- Giúp phân biệt lúa ngập nước, cây trồng cạn, mặt nước...
+
+---
+
+## **Bước 5: Dự đoán bằng Model ML** (Cell 12) ⭐ **QUAN TRỌNG NHẤT**
+
+```python
+loaded_model = joblib.load("model_train/model_odc.joblib")
+data_array = predict(loaded_model, data.rio.crs, average_ndvi, average_vh, average_vv)
+```
+
+**Model đã được train trước** với dữ liệu mẫu (training data) gồm:
+- **Đầu vào (Features)**: NDVI theo tháng + VH + VV (chuỗi thời gian)
+- **Đầu ra (Labels)**: Loại đất đã được gắn nhãn thủ công
+
+### Cách model phân loại:
+
+| Đặc điểm | Loại đất |
+|----------|----------|
+| NDVI cao đều, VV thấp | Rừng |
+| NDVI biến đổi theo mùa vụ, VH cao (nước) | Lúa |
+| NDVI thấp, VV rất thấp | Sông/nước |
+| NDVI trung bình ổn định | Cây lâu năm (CLN) |
+
+---
+
+## **Bước 6: Hiển thị kết quả** (Cell 13-15)
+
+```python
+colors = ["#abcee9", "#ffef44", "#c4ff9e", "#ffd6a8", "#93ddda", "#1aeef7", "#ffa7f2", "#33ee33"]
+labels = ["Lúa tôm", "Lúa", "CHN", "CLN", "TS", "Sông", "Đất xây dựng", "Rừng"]
+```
+
+### 8 lớp phân loại:
+
+| Mã | Tên | Màu | Ý nghĩa |
+|----|-----|-----|---------|
+| 0 | Lúa tôm | 🔵 Xanh nhạt | Luân canh lúa-tôm |
+| 1 | Lúa | 🟡 Vàng | Đất trồng lúa |
+| 2 | CHN | 🟢 Xanh lá nhạt | Cây hàng năm |
+| 3 | CLN | 🟠 Cam nhạt | Cây lâu năm (cây ăn trái) |
+| 4 | TS | 🩵 Xanh ngọc | Thủy sản |
+| 5 | Sông | 🔷 Cyan | Mặt nước sông |
+| 6 | Đất XD | 💗 Hồng | Đất xây dựng |
+| 7 | Rừng | 💚 Xanh đậm | Rừng |
+
+---
+
+## **Bước 7: Lưu kết quả** (Cell 16)
+
+```python
+region_result.rio.to_raster("KetQuaPhanLoaiDatODC.tif")
+```
+
+- Xuất file GeoTIFF chứa mã phân loại (0-7) cho từng pixel
+
+---
+
+## 📊 **Tóm tắt quy trình:**
+
+```
+Ảnh vệ tinh (Sentinel-1 + Sentinel-2)
+        ↓
+Xử lý (loại mây, tính NDVI, VH, VV)
+        ↓
+Kết hợp features theo thời gian (13 tháng)
+        ↓
+Model ML (Random Forest/XGBoost) dự đoán
+        ↓
+Bản đồ phân loại 8 lớp đất
+        ↓
+File .tif (mỗi pixel = 1 mã loại đất)
+```
+
+---
+
+## 📁 Cấu trúc dữ liệu đầu vào cho Model
+
+### Features (Đặc trưng):
+- **NDVI theo 13 tháng**: 13 bands
+- **VH (radar) theo 13 tháng**: 13 bands  
+- **VV (radar) theo 13 tháng**: 13 bands
+- **Tổng cộng**: ~39 features cho mỗi pixel
+
+### Labels (Nhãn):
+- Được lấy từ shapefile training: `train/ST_training data_updated_1130points_new.shp`
+- 1130 điểm mẫu đã được gắn nhãn thủ công bởi chuyên gia
+
+---
+
+## 🔧 Các thư viện sử dụng
+
+| Thư viện | Mục đích |
+|----------|----------|
+| `datacube` | Truy vấn dữ liệu vệ tinh |
+| `xarray` | Xử lý dữ liệu đa chiều |
+| `rioxarray` | Đọc/ghi GeoTIFF |
+| `joblib` | Load/save model ML |
+| `sklearn` / `xgboost` | Training model |
+| `matplotlib` / `hvplot` | Trực quan hóa |
+
+---
+
+## 📝 Ghi chú
+
+- **Độ phân giải**: 10-20m (tùy cấu hình)
+- **Thời gian xử lý**: Phụ thuộc vào kích thước vùng và số scenes
+- **Yêu cầu**: Cần kết nối internet để tải dữ liệu vệ tinh từ Planetary Computer hoặc ODC
+
+---
+
+*Tài liệu được tạo ngày 14/12/2025*

easi_tools/__init__.py

@@ -1,9 +0,0 @@
-#!python 3
-
-from .deployments import EasiDefaults
-from .notebook_utils import \
-    heading, \
-    initialize_dask, \
-    mostcommon_crs, \
-    unset_cachingproxy, \
-    xarray_object_size

easi_tools/deployments.py

@@ -1,335 +0,0 @@
-#!python3
-
-import sys
-import os
-import logging
-import collections
-
-# A class that provides notebook variables for each of the EASI deployments
-
-# Map an internal deployment name to deployment variables and search parameters.
-# Update to ensure that the product/space/time parameters are available in the respective databases
-deployment_map = {
-    'adias': {
-        'domain': 'adias.aquawatchaus.space',
-        'db_database': 'adias_prod_db',
-        'training_shapefile': '',
-        'scratch': 'adias-prod-user-scratch',
-        'productmap': {'landsat': 'landsat8_c2l2_sr', 'sentinel-2': 's2_l2a', 'sar': 'asf_s1_grd_gamma0', 'dem': 'copernicus_dem_30'},
-        'location': 'Lake Tahoe, California',
-        'latitude': (39.0, 39.3),
-        'longitude': (-120.2, -119.9),
-        'time': ('2022-02-01', '2022-05-01'),
-        'target': {
-            'landsat': {'crs': 'epsg:26911', 'resolution': (-30,30)},
-            'sentinel-2': {'crs': 'epsg:26911', 'resolution': (-10,10)}
-        },
-        'aliases': {
-            'landsat': {'qa_band': 'qa_pixel', 'nir': 'nir08', 'swir1': 'swir16', 'swir2': 'swir22'}
-        },
-        'qa_mask': {
-            'landsat': {'nodata': False, 'water': 'land_or_cloud',
-                        'cloud': 'not_high_confidence', 'cloud_shadow': 'not_high_confidence'}
-        }
-    },
-    'asia': {
-        'domain': 'asia.easi-eo.solutions',
-        'db_database': 'easi_asia_db',
-        'training_shapefile': '',
-        'scratch': 'easi-asia-user-scratch',
-        'productmap': {'landsat': 'landsat8_c2l2_sr', 'sentinel-2': 'sentinel_2_c1_l2a', 'sentinel-1': 'sentinel1_grd_gamma0_20m', 'dem': 'copernicus_dem_30'},
-        'location': 'Lake Tempe, Indonesia',
-        'latitude': (-4.2, -3.9),
-        'longitude': (119.8, 120.1),
-        'time': ('2020-02-01', '2020-04-01'),
-        'proxy': True,
-        'target': {
-            'landsat': {'crs': 'epsg:32650', 'resolution': (-30,30)},
-            'sentinel-2': {'crs': 'epsg:32650', 'resolution': (-10,10)}
-        },
-        'aliases': {
-            'landsat': {'qa_band': 'qa_pixel', 'nir': 'nir08', 'swir1': 'swir16', 'swir2': 'swir22'}
-        },
-        'qa_mask': {
-            'landsat': {'nodata': False, 'water': 'land_or_cloud',
-                        'cloud': 'not_high_confidence', 'cloud_shadow': 'not_high_confidence'}
-        }
-    },
-    'chile': {
-        'domain': 'datacubechile.cl',
-        'db_database': 'easido_prod_db',
-        'training_shapefile': '',
-        'scratch': 'easido-prod-user-scratch',
-        'productmap': {'landsat': 'landsat8_c2l2_sr', 'sentinel-2': 'sentinel_2_c1_l2a', 'sar': 'asf_s1_grd_gamma0', 'dem': 'copernicus_dem_30'},
-        'location': 'La Serena, Chile',
-        'latitude': (-29.95, -29.85),
-        'longitude': (-71.3, -71.2),
-        'latitude_big': (-29.95, -27.95),
-        'longitude_big': (-71.3, -69.3),
-        'time': ('2022-02-01', '2022-05-01'),
-        'target': {
-            'landsat': {'crs': 'epsg:32718', 'resolution': (-30,30)},
-            'sentinel-2': {'crs': 'epsg:32718', 'resolution': (-10,10)}
-        },
-        'aliases': {
-            'landsat': {'qa_band': 'qa_pixel', 'nir': 'nir08', 'swir1': 'swir16', 'swir2': 'swir22'}
-        },
-        'qa_mask': {
-            'landsat': {'nodata': False, 'water': 'land_or_cloud',
-                        'cloud': 'not_high_confidence', 'cloud_shadow': 'not_high_confidence'}
-        }
-    },
-    'cal': {
-        'domain': 'cal.ceos.org',
-        'db_database': 'ceoseail_eail_db',
-        'training_shapefile': './ancillary_data/VA_Counties_Newport_News.shp',
-        'scratch': 'ceoseail-eail-user-scratch',
-        'ows': False,
-        'map': False,
-        'productmap': {'landsat': 'landsat8_c2l2_sr', 'sentinel-2': 's2_l2a', 'sentinel-1': 's1_rtc', 'dem': 'copernicus_dem_30'},
-        'location': 'Newport News, Virginia',
-        'latitude': (37.02, 37.12),
-        'longitude': (-76.55, -76.45),
-        'time': ('2022-01-01', '2022-04-01'),
-        'target': {
-            'landsat': {'crs': 'epsg:32618', 'resolution': (-30,30)},
-            'sentinel-2': {'crs': 'epsg:32618', 'resolution': (-10,10)}
-        },
-        'aliases': {
-            'landsat': {'qa_band': 'qa_pixel', 'nir': 'nir08', 'swir1': 'swir16', 'swir2': 'swir22'}
-        },
-        'qa_mask': {
-            'landsat': {'nodata': False, 'water': 'land_or_cloud',
-                        'cloud': 'not_high_confidence', 'cloud_shadow': 'not_high_confidence'}
-        }
-    },
-    'csiro': {
-        'domain': 'csiro.easi-eo.solutions',
-        'db_database': 'easihub_csiro_db',
-        'training_shapefile': '',
-        'scratch': 'easihub-csiro-user-scratch',
-        'productmap': {'landsat': 'ga_ls8c_ard_3', 'sentinel-2': 'ga_s2am_ard_3', 'sentinel-1': 'sentinel1_grd_gamma0_20m', 'dem': 'copernicus_dem_30'},
-        'location': 'Lake Hume, Australia',
-        'latitude': (-36.3, -35.8),
-        'longitude': (146.8, 147.3),
-        'time': ('2020-02-01', '2020-04-01'),
-        'aliases': {
-            'landsat': {'red': 'nbart_red', 'green': 'nbart_green', 'blue': 'nbart_blue',
-                        'nir': 'nbart_nir', 'swir1': 'nbart_swir_1', 'swir2': 'nbart_swir_2',
-                        'qa_band': 'oa_fmask'}
-        },
-        'qa_mask': {
-            'landsat': {'fmask':'valid'}
-        }
-    },
-    'sub-apse2': {
-        'domain': 'sub-apse2.easi-eo.solutions',
-        'db_database': '',
-        'training_shapefile': '',
-        'scratch': '',
-        'ows': False,
-        'map': False,
-        'productmap': {'landsat': 'ga_ls8c_ard_3', 'sentinel-2': 'ga_s2am_ard_3', 'dem': 'copernicus_dem_30'},
-        'location': 'Lake Hume, Australia',
-        'latitude': (-36.3, -35.8),
-        'longitude': (146.8, 147.3),
-        'time': ('2020-02-01', '2020-04-01'),
-        'aliases': {
-            'landsat': {'red': 'nbart_red', 'green': 'nbart_green', 'blue': 'nbart_blue',
-                        'nir': 'nbart_nir', 'swir1': 'nbart_swir_1', 'swir2': 'nbart_swir_2',
-                        'qa_band': 'oa_fmask'}
-        },
-        'qa_mask': {
-            'landsat': {'fmask':'valid'}
-        }
-    },
-}
-
-
-class EasiDefaults():
-    """Provide deployment-specific default variables for EASI notebooks"""
-
-    def __init__(self, deployment=None):
-        """Initialise"""
-        self._log = _getlogger(self.__class__.__name__)
-        self.name = deployment if deployment else self._find_deployment()
-        self.deployment = self._validate(self.name)
-        self.proxy = None
-        self._aliases = {}
-        if self.deployment and self.deployment.get('proxy', None):
-            self.proxy = EasiCachingProxy()
-        if self.deployment:
-            self._log.info(f'Successfully found configuration for deployment "{self.name}"')
-
-    def _validate(self, deployment) -> dict:
-        """Return the dict associated with the deployment name"""
-        names = deployment_map.keys()
-        if deployment is None or deployment not in names:
-            self._log.error(f'Deployment name not recognised: {deployment}')
-            self._log.error(f'Select one of: {", ".join(names)}')
-            return None
-        return deployment_map[deployment]
-
-    def _find_deployment(self) -> str:
-        """Use the deployment's database environment variable as a lookup into the deployment_map dict"""
-        db_database = os.environ['DB_DATABASE']
-        deployment_name = [item for item in deployment_map if deployment_map[item]["db_database"] == db_database]
-        msg = 'Try specifying one using EasiDefaults(deployment="deployment_name").'
-        if len(deployment_name) == 0:
-            self._log.error(f'Deployment could not be found automatically. {msg}')
-            return None
-        elif len(deployment_name) > 1:
-            self._log.error(f'More than one deployment found. {msg}')
-            return None
-        return deployment_name[0]
-
-
-    @property
-    def domain(self):
-        """Deployment domain"""
-        return self.deployment['domain']
-
-    @property
-    def db_database(self):
-        """Database name"""
-        return self.deployment['db_database']
-
-    @property
-    def training_shapefile(self):
-        """A local shapefile"""
-        return self.deployment['training_shapefile']
-
-    @property
-    def hub(self):
-        """JupyterLab URL"""
-        return f'https://hub.{self.domain}'
-
-    @property
-    def explorer(self):
-        """Explorer URL"""
-        return f'https://explorer.{self.domain}'
-
-    @property
-    def ows(self):
-        """OWS URL"""
-        if not self.deployment.get('ows', True):
-            self._log.warning(f'Deployment does not have an OWS service: {self.name}')
-            return None
-        return f'https://ows.{self.domain}'
-
-    @property
-    def terria(self):
-        """Terria Map URL"""
-        if not self.deployment.get('map', True):
-            self._log.warning(f'Deployment does not have a Map service: {self.name}')
-            return None
-        return f'https://map.{self._domain()}'
-
-    @property
-    def scratch(self):
-        """Scratch bucket"""
-        return self.deployment['scratch']
-
-    @property
-    def location(self):
-        """Default location name"""
-        return self.deployment['location']
-
-    @property
-    def latitude(self):
-        """Default latitude range"""
-        return self.deployment['latitude']
-
-    @property
-    def longitude(self):
-        """Default longitude range"""
-        return self.deployment['longitude']
-
-    @property
-    def latitude_big(self):
-        """Default big latitude range"""
-        if 'latitude_big' in self.deployment:
-            return self.deployment['latitude_big']
-        self._log.warning(f'Default big latitude range not defined for "{self.deployment}". Using default latitude range')
-        return self.latitude
-
-    @property
-    def longitude_big(self):
-        """Default big longitude range"""
-        if 'longitude_big' in self.deployment:
-            return self.deployment['longitude_big']
-        self._log.warning(f'Default big longitude range not defined for "{self.deployment}". Using default longitude range')
-        return self.latitude
-
-    @property
-    def time(self):
-        """Default time range"""
-        return self.deployment['time']
-
-    def product(self, family='landsat'):
-        """Product name. Family loosely describes products from a satellite series or product type."""
-        p = self.deployment['productmap'].get(family, None)
-        if p is None:
-            self._log.warning(f'Product family not defined for "{self.name}": {family}')
-            out = ', '.join([f'{k} > {v}' for k,v in self.deployment['productmap'].items()])
-            self._log.warning(f'{self.name}: {out}')
-            return None
-        return p
-
-    def crs(self, family='landsat'):
-        """Default resolution. Family loosely describes products from a satellite series or product type."""
-        return self.deployment.get('target', {}).get(family, {}).get('crs', None)
-
-    def resolution(self, family='landsat'):
-        """Default resolution. Family loosely describes products from a satellite series or product type."""
-        return self.deployment.get('target', {}).get(family, {}).get('resolution', None)
-
-    def aliases(self, family='landsat') -> collections.UserDict:
-        """Return a dict-like object that maps a common name to a specific measurement/alias name.
-        Family loosely describes products from a satellite series or product type.
-
-        The common name is returned if there is no specific measurement/alias name defined.
-        That is, the common name should work as a measurement/alias name for the family in this deployment.
-        Else, provide a specific measurement/alias name in the defaults above.
-        """
-        if family not in self._aliases:
-            self._aliases[family] = EasiAlias(self.deployment.get('aliases', {}).get(family, {}))
-        return self._aliases[family]
-
-    def qa_mask(self, family='landsat') -> dict:
-        """Default QA mask values. Family loosely describes products from a satellite series or product type."""
-        return self.deployment.get('qa_mask', {}).get(family, {})
-
-
-class EasiAlias(collections.UserDict):
-    """Custom UserDict that returns a default measurement name for a given key if defined.
-    Else returns the key as the value. Items can not be set."""
-    def __init__(self, default:dict = {}):
-        self.data = default
-        self._log = _getlogger(self.__class__.__name__)
-    def __getitem__(self, key):
-        if key in self.data:
-            return self.data[key]
-        return key
-    def __setitem__(self, key, val):
-        self._log.error(f'Error <{self.__class__.__name__}>: Can not set items')
-
-
-class EasiCachingProxy():
-    """Set, unset and return information about the user's caching-proxy configuration"""
-    def __init__(self):
-        pass
-
-
-def _getlogger(name):
-    """Return a logger. Define here to limit external dependencies"""
-    # Default logger
-    #   log.hasHandlers() = False
-    #   log.getEffectiveLevel() = 30 = warning
-    #   log.propagate = True
-    logger = logging.getLogger(name)
-    logger.setLevel(logging.INFO)
-    if not len(logger.handlers):
-        logger.addHandler(logging.StreamHandler(sys.stdout))
-    logger.propagate = False  # Do not propagate up to root logger, which may have other handlers
-    return logger

easi_tools/load_s2l2a.py

@@ -1,293 +0,0 @@
-#!python
-
-# Sentinel-2 L2A Collection 0 scaling and offset corrections.
-# - Applies to data indexed from https://earth-search.aws.element84.com/v1/collections/sentinel-2-l2a
-# - The newer https://earth-search.aws.element84.com/v1/collections/sentinel-2-c1-l2a (Collection 1) may not be affected in the same way
-#
-# TL;DR:
-# DN values in COG files have different definitions depending on the processing baseline version
-# and whether the offset change has been pre-applied by the cloud data custodian.
-#
-# Background:
-#
-# ESA has undertaken a reprocessing of the Sentinel-2 L2A product that includes
-# a change to the offset value used to convert digital numbers (in file) to
-# scientific values (reflectances).
-#
-# https://sentinels.copernicus.eu/web/sentinel/technical-guides/sentinel-2-msi/level-2a-algorithms-products
-#
-# L2A algorithm and products: Starting with the PB 04.00 (25th January 2022), the dynamic
-# range of the Level-2A products is shifted by a band-dependent constant: BOA_ADD_OFFSET.
-# This offset will allow encoding negative surface reflectances that may occur over very 
-# dark surfaces.
-#
-# L2A_SRi = (L2A_DNi + BOA_ADD_OFFSETi) / QUANTIFICATION_VALUEi
-#
-# QUANTIFICATION_VALUEi = 10000
-# BOA_ADD_OFFSETi = -1000
-#
-# refl = (dn -1000) / 10000
-# refl = dn/10000 - 1000/10000
-# refl = dn * 0.0001 - 0.1
-# 
-# These are the values in the EASI product definition, e.g.
-# https://explorer.asia.easi-eo.solutions/products/s2_l2a.odc-product.yaml
-#
-# Example workflow:
-#
-# ESA's reprocessing is flowing through to the AWS open data repository of S2 L2A but
-# while this stabilises we may see inconsistencies in time series queries due to:
-# - More than one processed version of a dataset (scene) in the AWS bucket and indexed in an EASI database
-# - Datasets (scenes) that indicate they have an offset applied by ESA but the offset correction
-#   has been not been applied to the COG
-#
-# Element-84 discussion:
-# https://github.com/Element84/earth-search/issues/23#issuecomment-1834674853
-
-
-import xarray as xr
-import pandas as pd
-import logging
-from pathlib import Path
-import sys, re
-
-import datacube
-from datacube.api.core import output_geobox
-from datacube.api.query import SPATIAL_KEYS, CRS_KEYS, OTHER_KEYS
-from datacube.utils import masking
-
-
-# Set logger
-log = logging.getLogger(Path(__file__).stem)
-log.setLevel(logging.INFO)
-log.addHandler(logging.StreamHandler(sys.stdout))
-
-# Constants
-search_keys = (
-    'product',
-    'time',
-    'geopolygon',
-    'like',
-    'limit',
-    'ensure_location',
-    'dataset_predicate',
-) + SPATIAL_KEYS + CRS_KEYS + OTHER_KEYS
-
-# TODO: get measurement aliases from the ODC product record
-refl_bands = {
-    'coastal','band_01','B01','coastal_aerosol',
-    'blue','band_02','B02',
-    'green','band_03','B03',
-    'red','band_04','B04',
-    'rededge1','band_05','B05','red_edge_1',
-    'rededge2','band_06','B06','red_edge_2',
-    'rededge3','band_07','B07','red_edge_3',
-    'nir','band_08','B08','nir_1',
-    'nir08','band_8a','B8A','nir_2',
-    'nir09','band_09','B09','nir_3',
-    'swir16','band_11','B11','swir_1','swir_16',
-    'swir22','band_12','B12','swir_2','swir_22',
-}
-scale_factor = 0.0001
-add_offset = -0.1
-
-
-def highest_sequence_number(matches: list) -> dict:
-    """Filter for the highest element84 processing sequence number per scene (scene label excluding the sequence number)
-    
-    : return : { scene_id_excluding_sequence_number : { highest_sequence_number : datacube.model.Dataset }}
-    """
-    p = re.compile(r'(S2.+)_([0-9]+)_(L2A)')
-    sorter = {}
-    for ds in matches:
-        # Separate the scene label from the sequence number
-        label = ds.metadata_doc['label']
-        m = p.match(label)
-        if not m:
-            log.warning(f'Dataset label does not match expected pattern: {label}')
-            continue
-        key = f'{m.group(1)}_{m.group(3)}'
-        seq = int(m.group(2))
-        # Retain the highest sequence number
-        if key in sorter:
-            if list(sorter[key])[0] < seq:
-                sorter[key] = {seq: ds}
-        else:
-            sorter[key] = {seq: ds}
-    return sorter
-
-
-def ds_requires_offset(ds: datacube.model.Dataset) -> bool:
-    """Return True if a dataset's metadata indicates that the offset correction should be applied"""
-    props = ds.metadata_doc['properties']
-    
-    # If baseline is less than '04.00' then offset correction does not apply
-    baseline = props.get('s2:processing_baseline', '0.0')
-    p = re.compile(r'(\d+)\.(\d+)')
-    m = p.match(baseline)
-    if not m:
-        log.warning(f'Dataset processing_baseline does not match expected pattern: {baseline}')
-        return None
-    if int(m.group(1)) < 4:
-        return False
-
-    # If the boa_offset_applied has been applied then offset correction is not required
-    boa_offset_applied = props.get('earthsearch:boa_offset_applied', False)
-    return not boa_offset_applied
-
-
-def apply_correction_to_data(ds: xr.Dataset, offset: float = 0) -> xr.Dataset:
-    """Apply the scale and offset correction to each reflectance band where there is valid data (not nodata)"""
-    refl_vars = [x for x in ds.data_vars if x in refl_bands]
-    mask = masking.valid_data_mask(ds[refl_vars])
-    # Save on a dask step?
-    if offset == 0:
-        ds[refl_vars] = ds[refl_vars].where(mask) * scale_factor
-    else:
-        ds[refl_vars] = ds[refl_vars].where(mask) * scale_factor + offset
-    return ds
-    
-
-def load_s2l2a_with_offset(
-    dc: datacube.Datacube,
-    query: dict,
-) -> xr.Dataset:
-    """
-    Replaces datacube.load(**query) for s2_l2a products.
-
-    Method:
-    - Find all datasets matching the query (dc.find_datasets)
-    - Filter for the highest element84 processing sequence number per scene (scene label excluding the sequence number)
-    - Filter into two lists for datasets that have
-      - "s2:processing_baseline" >= "04.00" and "earthsearch:boa_offset_applied" == False (offset correction required)
-      - everything else (no correction required)
-    - If either list is empty then load the non-empty list, apply scale (and offset if required), and return the xarray Dataset
-    - Load and combine the two lists of datasets
-      - Load each list, apply scale (and offset if required)
-      - Concat on time dimension and sort by time
-      - Return the combined xarray Dataset
-    
-    Notes:
-    - Any 'groupby' function is applied to each of the xarray Datasets prior to them being combined.
-      This could create "extra" (non-grouped) time layers in the combined Dataset if the groupby function
-      would have grouped datasets (scenes) from both lists.
-    - Scale and offset are applied to the reflectance bands where there is valid data (not `nodata`).
-      This includes applying the "scale_factor" even if no datasets require the offset correction.
-      Other masks can be applied by the user (e.g. pixel quality or cloud masking).
-    """
-
-    product = query.get('product', '<all products>')
-    if product != 's2_l2a':
-        log.error(f'This function only applies to the "s2_l2a" product, not: {product}')
-        return None
-    
-    # Find all datasets matching the query
-    matches = None
-    if 'datasets' in query:
-        matches = query['datasets']
-        del query['datasets']
-    if matches is None:
-        search_params = {k:v for k,v in query.items() if k in search_keys}
-        matches = dc.find_datasets(**search_params)
-    if 'skip_broken_datasets' not in query:
-        # This helps to avoid data loading error messages
-        query['skip_broken_datasets'] = True
-    
-    # Filter for the highest element84 processing sequence number
-    sorter = highest_sequence_number(matches)
-
-    # Filter into two lists
-    offset_applied, offset_required = [], []
-    for key in sorter.keys():
-        ds = list(sorter[key].values())[0]
-        isrequired = ds_requires_offset(ds)
-        if isrequired is None:
-            continue
-        elif isrequired:
-            offset_required.append(ds)
-        else:
-            offset_applied.append(ds)
-    matches_combined = offset_applied + offset_required
-
-    # If either list is empty then no separation and merge is required
-    this_offset = None
-    if len(offset_applied) == 0:
-        log.info('All datasets require offset correction')
-        msg = 'The valid_data_mask, scale and offset have been applied to the reflectance bands'
-        this_offset = add_offset
-    if len(offset_required) == 0:
-        log.info('No datasets require offset correction')
-        msg = 'The valid_data_mask and scale (no offset) have been applied to the reflectance bands'
-        this_offset = 0
-    if this_offset is not None:
-        data = dc.load(
-            datasets = matches_combined,
-            **query
-        )
-        xx = apply_correction_to_data(data, this_offset)
-        log.info(msg)
-        return xx
-
-    # DEBUG: What do we have
-    # def func(s):
-    #     p = re.compile('(\d{8})')
-    #     m = p.search(s[0])
-    #     if m:
-    #         return m.group(1)
-    # log.info(f'Number of datasets in initial query: {len(matches)}')
-    # log.info(f'{sorted([(x.metadata_doc["label"],x.id) for x in matches], key=func)}')
-    # log.info(f'Number of datasets with offset applied: {len(offset_applied)}')
-    # log.info(f'{sorted([(x.metadata_doc["label"],x.id) for x in offset_applied], key=func)}')
-    # log.info(f'Number of datasets without offset applied: {len(offset_required)}')
-    # log.info(f'{sorted( [(x.metadata_doc["label"],x.id) for x in offset_required], key=func)}')
-    # return
-
-    # Else, load data into two Datasets
-    log.info('Mix of datasets found with either offset required or not.')
-    log.info('We will load two xarrays, apply offset where required, and merge into one xarray.')
-
-    # 1. Ensure the target geobox covers all datasets
-    target_geobox = output_geobox(
-        datasets = matches_combined,
-        **query,
-    )
-    
-    # 2. Edit the query for our needs
-    # Ensure that dask time chunking = 1
-    dask_input = None
-    if 'dask_chunks' in query:
-        dask_input = query['dask_chunks']  # Save
-        if dask_input.get('time', 1) != 1:
-            query['dask_chunks'].update({'time': 1})
-    # Remove keys that are not compatible with 'like'
-    for x in ('output_crs', 'resolution', 'align'):
-        if x in query:
-            del query[x]
-    
-    # 3. Load two xarrays
-    data_offset_applied = dc.load(
-        datasets = offset_applied,
-        like = target_geobox,
-        **query
-    )
-    data_offset_required = dc.load(
-        datasets = offset_required,
-        like = target_geobox,
-        **query
-    )
-
-    # 4. Apply respective scale and offsets
-    data_offset_applied = apply_correction_to_data(data_offset_applied)
-    data_offset_required = apply_correction_to_data(data_offset_required, add_offset)
-    
-    # 5. Combine the two xarrays
-    combined = xr.concat([data_offset_applied, data_offset_required], dim='time')
-    combined = combined.sortby('time')
-    
-    # 6. Reapply any time > 1 chunking
-    if dask_input is not None:
-        if dask_input.get('time', 1) != 1:
-            combined = combined.chunk(dask_input)
-
-    log.info('The valid_data_mask, scale and offset have been applied to the reflectance bands')
-    return combined

easi_tools/notebook_utils.py

@@ -1,171 +0,0 @@
-#!python3
-
-# A collection of utilities that can be used in Python notebooks.
-#
-# License: Apache 2.0
-
-# Created for EASI Hub training notebooks, https://dev.azure.com/csiro-easi/easi-hub-public/_git/hub-notebooks
-
-# Data tools
-import numpy as np
-import xarray as xr
-import pandas as pd
-import geopandas as gpd
-import datacube
-from datacube.utils import masking
-from datetime import datetime
-
-# hvPlot, Holoviews, Datashader and Bokeh
-import hvplot.pandas
-import hvplot.xarray
-import panel as pn
-import holoviews as hv
-# hv.extension("bokeh", logo=False)  # Its likely set from in the notebooks
-
-# Jupyter Lab
-from IPython.display import HTML
-
-# Python
-import sys, os, re
-import logging
-from pathlib import Path
-from collections import Counter
-import contextlib
-
-# Dask
-import dask
-from dask.distributed import Client, LocalCluster
-from dask_gateway import Gateway
-
-# EASIDefaults
-from . import EasiDefaults
-
-# Set logger
-logger = logging.getLogger(Path(__file__).stem)
-logger.setLevel(logging.INFO)
-if not len(logger.handlers):
-    logger.addHandler(logging.StreamHandler(sys.stdout))
-
-
-def display_table(
-    df: pd.DataFrame,
-    panel: bool = False,
-):
-    """Display the full pandas dataframe. If panel is True use a panel object"""
-    table = None
-    if panel:
-        #  Dicts are rendered as "[object Object]". Need to set a formatter, I guess.
-        table = pn.widgets.DataFrame(df,
-            # sizing_mode='stretch_width',  # equal column widths, full screen
-            autosize_mode='fit_viewport',  # fitted columns, about 90-95% width
-            # reorderable=True,  # didn't work first try
-        )
-    else:
-        with pd.option_context("display.max_rows", None,
-                               "display.max_columns", None,
-                               "display.max_colwidth", -1):
-            table = HTML( df.to_html().replace(r"\n", "<br>") )
-    display(table)
-    
-        
-def heading(txt: str):
-    """Print a simple HTML heading"""
-    display(HTML( f"<h4>{txt}</h4>" ))
-    
-    
-def hv_table_hook(plot, element):
-    """Selected options for hv.table() formatting
-    
-    Use: df.hv.table().opts(hooks=[hv_table_hook])
-    """
-    plot.handles["table"].autosize_mode="fit_viewport"
-    # Other examples
-    # plot.handles['table'].row_height = 40
-    # from bokeh.models.widgets import DateFormatter
-    # plot.handles['table'].columns[6].formatter = DateFormatter(format='%Y-%m-%d')
-    
-
-def xarray_object_size(data):
-    """Return a formatted string"""
-    val, unit = data.nbytes / (1024 ** 2), "MB"
-    if val > 1024:
-        val, unit = data.nbytes / (1024 ** 3), "GB"
-    return f"Dataset size: {val:.2f} {unit}"
-
-
-def mostcommon_crs(dc, query):
-    """Adapted from https://github.com/GeoscienceAustralia/dea-notebooks/blob/develop/Tools/dea_tools/datahandling.py"""
-    matching_datasets = dc.find_datasets(**query)
-    crs_list = [str(i.crs) for i in matching_datasets]
-    crs_mostcommon = None
-    if len(crs_list) > 0:
-        # Identify most common CRS
-        crs_counts = Counter(crs_list)
-        crs_mostcommon = crs_counts.most_common(1)[0][0]
-    else:
-        logger.warning("No data was found for the supplied product query")
-    return crs_mostcommon
-
-
-def initialize_dask(use_gateway=False, workers=(1,2), wait=False, local_port=8786, **kwargs):
-    """Initialize a Dask Gateway or Local cluster"""
-    # Check inputs
-    if isinstance(workers, (int, float)):
-        workers = (int(workers), int(workers))
-    if len(workers) != 2:
-        logger.error("Require workers to be a single integer or a 2-element tuple/list")
-        return None, None
-    if isinstance(local_port, (str, float)):
-        local_port = int(local_port)
-    
-    # Dask gateway
-    if use_gateway:
-        gateway = Gateway()
-        clusters = gateway.list_clusters()
-        if not clusters:
-            logger.info("Starting new cluster")
-            cluster = gateway.new_cluster(**kwargs)
-        else:
-            logger.info(f"An existing cluster was found. Connecting to: {clusters[0].name}")
-            cluster = gateway.connect(clusters[0].name)
-        client = cluster.get_client()
-        cluster.adapt(minimum=workers[0], maximum=workers[1])
-        if wait:
-            logger.info("Waiting for at least one cluster worker")
-            # client.wait_for_workers(n_workers=1)  # Before release 2023.10.0
-            client.sync(client._wait_for_workers,n_workers=1) # Since release 2023.10.0
-
-    # Local cluster
-    else:
-        cluster = LocalCluster(n_workers=4)
-        client = Client(cluster)
-        server = f'https://hub.{EasiDefaults().domain}'  # Or replace if not using EasiDefaults
-        user = os.environ.get('JUPYTERHUB_SERVICE_PREFIX')  # Current user
-        dask.config.set({"distributed.dashboard.link": f'{server}{user}' + "proxy/{port}/status"})  # port is evaluated by dask
-        
-    return cluster, client
-
-
-def localcluster_dashboard(client, server="https://hub.csiro.easi-eo.solutions"):
-    """Return a dashboard link using jupyter proxy"""
-    dashboard_link = client.dashboard_link
-    for host in ("127.0.0.1", "localhost"):
-        if host in dashboard_link:
-            port = re.search(r":(\d+)\/status", dashboard_link).group(1)
-            dashboard_link = f'{server}{os.environ["JUPYTERHUB_SERVICE_PREFIX"]}proxy/{port}/status'
-            break
-    return dashboard_link
-
-
-@contextlib.contextmanager
-def unset_cachingproxy():
-    """Unset the EASI caching proxy with a context manager"""
-    # Inspired by https://stackoverflow.com/a/34333710
-    env = os.environ
-    remove = ("AWS_HTTPS", "GDAL_HTTP_PROXY")
-    update_after = {k: env[k] for k in remove}
-    try:
-        [env.pop(k, None) for k in remove]
-        yield
-    finally:
-        env.update(update_after)

model_train/model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a446d333bf7f6d0cb7df014f12b0da3f7298f85bdfb4de06893173e90fbd5ccb
+size 14112695

model_train/model_cnn_20251214_180423.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae2f82f6c837396729cc63efa41ee3048d9a7de3197e28318dc846be830239b9
+size 41536

model_train/model_cnn_20251214_180423_info.json

@@ -0,0 +1,33 @@
+{
+  "timestamp": "2025-12-14T18:04:27.406540",
+  "data_source": "Microsoft Planetary Computer STAC",
+  "collections": [
+    "sentinel-2-l2a",
+    "sentinel-1-rtc"
+  ],
+  "features": [
+    "NDVI_mean",
+    "VH_dB_mean",
+    "VV_dB_mean"
+  ],
+  "training_samples": 510,
+  "testing_samples": 128,
+  "train_accuracy": 0.515686274509804,
+  "test_accuracy": 0.5,
+  "model_type": "cnn",
+  "device": "cpu",
+  "n_estimators": 50,
+  "max_depth": null,
+  "learning_rate": null,
+  "cnn_epochs": 25,
+  "n_features": 3,
+  "n_classes": 7,
+  "bbox": [
+    105.6,
+    9.3,
+    106.2,
+    9.8
+  ],
+  "time_range": "2023-03-01/2023-05-31",
+  "resolution": 20
+}

model_train/model_cnn_20251214_181104.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc03d62c7f620b88150a6481143026d516fd3a34bd5ab67c734adac4a8900f9
+size 41536

model_train/model_cnn_20251214_181104_info.json

@@ -0,0 +1,33 @@
+{
+  "timestamp": "2025-12-14T18:17:48.399298",
+  "data_source": "Microsoft Planetary Computer STAC",
+  "collections": [
+    "sentinel-2-l2a",
+    "sentinel-1-rtc"
+  ],
+  "features": [
+    "NDVI_mean",
+    "VH_dB_mean",
+    "VV_dB_mean"
+  ],
+  "training_samples": 510,
+  "testing_samples": 128,
+  "train_accuracy": 0.4803921568627451,
+  "test_accuracy": 0.484375,
+  "model_type": "cnn",
+  "device": "cpu",
+  "n_estimators": 50,
+  "max_depth": null,
+  "learning_rate": null,
+  "cnn_epochs": 25,
+  "n_features": 3,
+  "n_classes": 7,
+  "bbox": [
+    105.6,
+    9.3,
+    106.2,
+    9.8
+  ],
+  "time_range": "2023-03-01/2023-05-25",
+  "resolution": 20
+}

model_train/model_cnn_20251214_182307.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21f906aa2a61d2e793a3463df95fe3e364134934af326771efae90d80caca419
+size 41536

model_train/model_cnn_20251214_182307_info.json

@@ -0,0 +1,33 @@
+{
+  "timestamp": "2025-12-14T18:23:10.713912",
+  "data_source": "Microsoft Planetary Computer STAC",
+  "collections": [
+    "sentinel-2-l2a",
+    "sentinel-1-rtc"
+  ],
+  "features": [
+    "NDVI_mean",
+    "VH_dB_mean",
+    "VV_dB_mean"
+  ],
+  "training_samples": 510,
+  "testing_samples": 128,
+  "train_accuracy": 0.46862745098039216,
+  "test_accuracy": 0.4609375,
+  "model_type": "cnn",
+  "device": "cpu",
+  "n_estimators": 50,
+  "max_depth": null,
+  "learning_rate": null,
+  "cnn_epochs": 25,
+  "n_features": 3,
+  "n_classes": 7,
+  "bbox": [
+    105.6,
+    9.3,
+    106.2,
+    9.8
+  ],
+  "time_range": "2023-03-01/2023-05-31",
+  "resolution": 20
+}

model_train/model_new.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eec576dffe1cc1393fdb584fb99d28db62abdd0977d41030aee5c4fa5377180
+size 11474743

model_train/model_xgboost_gpu_20251212_125754.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe99f96ad3d3ba7aaacc0e742572a8f5b22947a328c74b245e0aa5f2913c757
+size 1347520

model_train/model_xgboost_gpu_20251212_125754_info.json

@@ -0,0 +1,24 @@
+{
+  "timestamp": "2025-12-12T12:57:54.509336",
+  "data_source": "Microsoft Planetary Computer STAC",
+  "collections": [
+    "sentinel-2-l2a",
+    "sentinel-1-rtc"
+  ],
+  "features": [
+    "NDVI_mean",
+    "VH_dB_mean",
+    "VV_dB_mean"
+  ],
+  "training_samples": 510,
+  "testing_samples": 128,
+  "train_accuracy": 1.0,
+  "test_accuracy": 0.578125,
+  "model_type": "XGBClassifier",
+  "device": "cuda:0",
+  "gpu_device": "RTX 4060",
+  "tree_method": "hist",
+  "n_estimators": 100,
+  "max_depth": 20,
+  "learning_rate": 0.1
+}

model_train/model_xgboost_gpu_20251212_220850.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b717f564f9413a6e5c9cd3f7011cbc18be02479691d01c554986defb400f0490
+size 1347520

model_train/model_xgboost_gpu_20251212_220850_info.json

@@ -0,0 +1,31 @@
+{
+  "timestamp": "2025-12-12T22:15:25.794614",
+  "data_source": "Microsoft Planetary Computer STAC",
+  "collections": [
+    "sentinel-2-l2a",
+    "sentinel-1-rtc"
+  ],
+  "features": [
+    "NDVI_mean",
+    "VH_dB_mean",
+    "VV_dB_mean"
+  ],
+  "training_samples": 510,
+  "testing_samples": 128,
+  "train_accuracy": 1.0,
+  "test_accuracy": 0.578125,
+  "model_type": "XGBClassifier",
+  "device": "cuda:0",
+  "tree_method": "hist",
+  "n_estimators": 100,
+  "max_depth": 20,
+  "learning_rate": 0.1,
+  "bbox": [
+    105.6,
+    9.3,
+    106.2,
+    9.8
+  ],
+  "time_range": "2023-03-01/2023-05-31",
+  "resolution": 20
+}

model_train/model_xgboost_gpu_20251212_223236.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c6cabb59d9cdbba22a438ae935911f1711d7434dcf3728db4e518ec1b90190
+size 556184

model_train/model_xgboost_gpu_20251212_223236_info.json

@@ -0,0 +1,31 @@
+{
+  "timestamp": "2025-12-12T22:33:42.950629",
+  "data_source": "Microsoft Planetary Computer STAC",
+  "collections": [
+    "sentinel-2-l2a",
+    "sentinel-1-rtc"
+  ],
+  "features": [
+    "NDVI_mean",
+    "VH_dB_mean",
+    "VV_dB_mean"
+  ],
+  "training_samples": 904,
+  "testing_samples": 226,
+  "train_accuracy": 0.19911504424778761,
+  "test_accuracy": 0.19911504424778761,
+  "model_type": "XGBClassifier",
+  "device": "cuda:0",
+  "tree_method": "hist",
+  "n_estimators": 100,
+  "max_depth": 20,
+  "learning_rate": 0.1,
+  "bbox": [
+    104.89032,
+    10.944563,
+    104.972717,
+    11.016689
+  ],
+  "time_range": "2023-03-01/2023-05-31",
+  "resolution": 20
+}

model_train/model_xgboost_gpu_20251214_133256.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b717f564f9413a6e5c9cd3f7011cbc18be02479691d01c554986defb400f0490
+size 1347520

model_train/model_xgboost_gpu_20251214_133256_info.json

@@ -0,0 +1,31 @@
+{
+  "timestamp": "2025-12-14T13:40:03.325930",
+  "data_source": "Microsoft Planetary Computer STAC",
+  "collections": [
+    "sentinel-2-l2a",
+    "sentinel-1-rtc"
+  ],
+  "features": [
+    "NDVI_mean",
+    "VH_dB_mean",
+    "VV_dB_mean"
+  ],
+  "training_samples": 510,
+  "testing_samples": 128,
+  "train_accuracy": 1.0,
+  "test_accuracy": 0.578125,
+  "model_type": "XGBClassifier",
+  "device": "cuda:0",
+  "tree_method": "hist",
+  "n_estimators": 100,
+  "max_depth": 20,
+  "learning_rate": 0.1,
+  "bbox": [
+    105.6,
+    9.3,
+    106.2,
+    9.8
+  ],
+  "time_range": "2023-03-01/2023-05-31",
+  "resolution": 20
+}

model_train/model_xgboost_gpu_20251214_164426.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44efc173619782c8add224e9024f33ef0150ab192b5435d009cb119c379f03c
+size 2088632

model_train/model_xgboost_gpu_20251214_164426_info.json

@@ -0,0 +1,31 @@
+{
+  "timestamp": "2025-12-14T16:52:19.862770",
+  "data_source": "Microsoft Planetary Computer STAC",
+  "collections": [
+    "sentinel-2-l2a",
+    "sentinel-1-rtc"
+  ],
+  "features": [
+    "NDVI_mean",
+    "VH_dB_mean",
+    "VV_dB_mean"
+  ],
+  "training_samples": 859,
+  "testing_samples": 215,
+  "train_accuracy": 0.9976717112922002,
+  "test_accuracy": 0.6837209302325581,
+  "model_type": "XGBClassifier",
+  "device": "cuda:0",
+  "tree_method": "hist",
+  "n_estimators": 100,
+  "max_depth": 20,
+  "learning_rate": 0.1,
+  "bbox": [
+    105.6,
+    9.3,
+    106.2,
+    9.8
+  ],
+  "time_range": "2023-03-01/2023-12-31",
+  "resolution": 20
+}

new_import_ODC.py

@@ -81,187 +81,48 @@ from sklearn.metrics import mean_squared_error, r2_score
 import joblib
 
 
-def load_data_from_rasterio(dc, date_range, longtitude_range, latitude_range):
-    """
-    Load Sentinel-2 L2A data directly from S3 COGs using rasterio.
-    Returns a xarray Dataset with 10980x10980 resolution data.
-    
-    This approach:
-    - Loads ALL available data without spatial filtering
-    - Uses direct S3 COG access (rasterio) for reliability
-    - Returns data at native 10m resolution
-    - Matches the pipeline's downstream processing requirements
-    """
-    
-    print(f'Loading Sentinel-2 data from S3 COGs (rasterio)...')
-    print(f'  Date range: {date_range}')
-    print(f'  Target area: Lon {longtitude_range}, Lat {latitude_range}')
-    
-    try:
-        # Get first matching scene
-        datasets = list(dc.find_datasets(
-            product='s2_l2a',
-            time=date_range
-        ))
-        
-        if not datasets:
-            print(f'❌ No datasets found for date range {date_range}')
-            return None
-            
-        selected = datasets[0]
-        print(f'\n📦 Using scene: {selected.metadata.label}')
-        
-        # Load measurements from S3 COGs
-        measurements_to_load = ['red', 'green', 'blue', 'nir', 'scl']
-        data_dict = {}
-        
-        print(f'\n⏳ Loading bands from S3 COGs...')
-        for band_name in measurements_to_load:
-            if band_name in selected.measurements:
-                band_path = selected.measurements[band_name]['path']
-                
-                try:
-                    with rasterio.open(band_path) as src:
-                        data = src.read(1)
-                        data_dict[band_name] = data
-                        print(f'   ✅ {band_name}: {data.shape}, dtype={data.dtype}')
-                except Exception as e:
-                    print(f'   ⚠️ Could not load {band_name}: {e}')
-        
-        if not data_dict:
-            print('❌ Could not load any bands')
-            return None
-        
-        # Create xarray Dataset
-        print(f'\n🔄 Converting to xarray Dataset...')
-        
-        # Get dimensions from red band (highest resolution)
-        red_data = data_dict['red']
-        y_size, x_size = red_data.shape
-        
-        # Create coordinate arrays (placeholder - real georeferencing would come from rasterio metadata)
-        y_coords = np.arange(y_size)
-        x_coords = np.arange(x_size)
-        
-        # Create data arrays for each variable
-        data_vars = {}
-        for band_name, band_data in data_dict.items():
-            if band_data.shape == red_data.shape:
-                # Same resolution - direct assignment
-                data_vars[band_name] = (['y', 'x'], band_data)
-            else:
-                # Different resolution (e.g., SCL at 20m) - resample to match red
-                from scipy import ndimage
-                scale_factor = red_data.shape[0] // band_data.shape[0]
-                resampled = ndimage.zoom(band_data, scale_factor, order=0)
-                data_vars[band_name] = (['y', 'x'], resampled)
-        
-        # Create xarray Dataset
-        data = xr.Dataset(
-            data_vars,
-            coords={
-                'x': x_coords,
-                'y': y_coords
-            }
-        )
-        
-        print(f'\n✅ Data converted successfully!')
-        print(f'   Dimensions: {dict(data.sizes)}')
-        print(f'   Variables: {list(data.data_vars)}')
-        print(f'   Shape: {red_data.shape}')
-        print(f'   Data type: numpy arrays (in-memory)')
-        
-        return data
-        
-    except Exception as e:
-        print(f'❌ Error loading data: {e}')
-        import traceback
-        traceback.print_exc()
-        return None
-
-
 def load_data(dc, date_range, longtitude_range, latitude_range):
-    """
-    Load Sentinel-2 L2A data using direct datacube.load() 
-    without spatial filtering (which was causing 0 results).
-    
-    Note: Data is loaded in UTM (EPSG:32648) to avoid CRS issues.
-    Spatial filtering on lat/lon is skipped to return maximum data.
-    """
     product = 's2_l2a'
-    native_crs = 'EPSG:32648'  # UTM Zone 48N for Vietnam
+    query = {
+        'product': product,                     # Product name
+        'x': longtitude_range,    # "x" axis bounds
+        'y': latitude_range,      # "y" axis bounds
+        'time': date_range,           # Any parsable date strings
+    }
+    native_crs = notebook_utils.mostcommon_crs(dc, query)
+    print(f'Most common native CRS: {native_crs}')
     measurements = ['red', 'nir', 'scl']
 
-    print(f'Loading Sentinel-2 data (EPSG:32648)...')
-    print(f'  Time range: {date_range}')
-    print(f'  Measurements: {measurements}')
-    
-    try:
-        # Load ALL available data WITHOUT dask_chunks (forces immediate load)
-        # This avoids the metadata issue with dc.load() when using dask_chunks
-        data = dc.load(
-            product=product,
-            time=date_range,
-            measurements=measurements,
-            output_crs=native_crs,
-            resolution=(-10, 10),
-            group_by='solar_day',
-            skip_broken_datasets=True
+    load_params = {
+        'measurements': measurements,                   # Selected measurement or alias names
+        'output_crs': native_crs,                       # Target EPSG code
+        'resolution': (-10, 10),                        # Target resolution
+        'group_by': 'solar_day',                        # Scene grouping
+        'dask_chunks': {'x': 2048, 'y': 2048},          # Dask chunks
+    }
+    data = load_s2l2a_with_offset(
+        dc,
+        query | load_params   # Combine the two dicts that contain our search and load parameters
     )
-        
-        print(f'✅ Data loaded successfully!')
-        print(f'   Dimensions: {dict(data.sizes)}')
-        print(f'   Time steps: {len(data.time)}')
-        print(f'   Spatial extent: x={len(data.x)}, y={len(data.y)}')
-        print(f'   Data type: numpy arrays (not Dask)')
-        
     return data
 
-    except Exception as e:
-        print(f'❌ Error loading data: {e}')
-        import traceback
-        traceback.print_exc()
-        return None
-
 
 def mask_clean(data):
-    """
-    Clean data by masking clouds and bad pixels using the SCL (Scene Classification Layer).
+    flag_name = 'scl'
+    flag_desc = masking.describe_variable_flags(data[flag_name])  # Pandas dataframe
+    display(flag_desc)
+    display(flag_desc.loc['qa'].values[1])
+    # Create a "data quality" Mask layer
+    flags_def = flag_desc.loc['qa'].values[1]
+    good_pixel_flags = [flags_def[str(i)] for i in [2, 4, 5, 6]]  # To pass strings to enum_to_bool()
 
-    SCL classes:
-    - 0: No Data
-    - 1: Saturated/Defective
-    - 2: Dark Area Pixels
-    - 3: Cloud Shadows
-    - 4: Vegetation ✓ GOOD
-    - 5: Not Vegetated ✓ GOOD
-    - 6: Water ✓ GOOD
-    - 7: Unclassified ✓ GOOD
-    - 8: Cloud Medium Probability ✗ BAD
-    - 9: Cloud High Probability ✗ BAD
-    - 10: Thin Cirrus ✗ BAD
-    - 11: Snow/Ice ✗ BAD
-    """
-    
-    # Good pixel classes (keep these)
-    good_pixel_classes = [4, 5, 6, 7]
-    
-    # Create mask: 1 where SCL is in good_pixel_classes, 0 otherwise
-    good_pixel_mask = data['scl'].isin(good_pixel_classes)
-    
-    print(f'✅ Cloud masking applied')
-    print(f'   Good pixel classes: {good_pixel_classes}')
-    print(f'   Mask created (dask-backed, not yet computed)')
-    
-    # Get all variables except SCL
+    # enum_to_bool calculates the pixel-wise "or" of each set of pixels given by good_pixel_flags
+    # 1 = good data
+    # 0 = "bad" data
+    good_pixel_mask = enum_to_bool(data[flag_name], good_pixel_flags)
     data_layer_names = [x for x in data.data_vars if x != 'scl']
-    
-    # Apply mask to all layers
+    # Apply good pixel mask to blue, green, red and nir.
     result = data[data_layer_names].where(good_pixel_mask).persist()
-    
-    print(f'   Data variables masked: {data_layer_names}')
-    print(f'   Result persisted to workers')
-    
     return result
 
 
@@ -499,17 +360,7 @@ def load_data_sen2(dc, date_range, coordinates):
         'y': latitude_range,      # "y" axis bounds
         'time': date_range,           # Any parsable date strings
     }
-    
-    # Try to get native CRS, default to EPSG:32648 (UTM Zone 48N) for Vietnam
-    try:
     native_crs = notebook_utils.mostcommon_crs(dc, query)
-        if native_crs is None:
-            print('⚠️ Could not determine native CRS, using EPSG:32648 (UTM Zone 48N)')
-            native_crs = 'EPSG:32648'
-    except Exception as e:
-        print(f'⚠️ Error determining CRS: {e}, using EPSG:32648')
-        native_crs = 'EPSG:32648'
-    
     print(f'Most common native CRS: {native_crs}')
     
     # measurements = ['red','green', 'blue', 'nir', 'scl']
@@ -522,27 +373,10 @@ def load_data_sen2(dc, date_range, coordinates):
         'group_by': 'solar_day',                        # Scene grouping
         'dask_chunks': {'x': 2048, 'y': 2048},          # Dask chunks
     }
-    
-    try:
     data = load_s2l2a_with_offset(
         dc,
         query | load_params   # Combine the two dicts that contain our search and load parameters
     )
-    except Exception as e:
-        print(f'❌ Error loading data: {e}')
-        print('Attempting direct dc.load without offset correction...')
-        data = dc.load(
-            product=product,
-            x=longtitude_range,
-            y=latitude_range,
-            time=date_range,
-            measurements=measurements,
-            output_crs=native_crs,
-            resolution=(-10, 10),
-            group_by='solar_day',
-            dask_chunks={'x': 2048, 'y': 2048},
-            skip_broken_datasets=True
-        )
     return data
 
 def mask_cloud(data):

new_train.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb89e36fa4f4c740d5a079baf53b02bec2ef1120ac770bed6b6be4aa9fc99a1b
+size 208470

predictions/prediction_20251212_230423.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179d3a61420c1552e9653de5c7657665c9880ad29d751e56bae646fb3b634687
+size 73272920

predictions/prediction_20251212_230549.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179d3a61420c1552e9653de5c7657665c9880ad29d751e56bae646fb3b634687
+size 73272920

predictions/prediction_20251214_100243.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179d3a61420c1552e9653de5c7657665c9880ad29d751e56bae646fb3b634687
+size 73272920

predictions/prediction_20251214_165405.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8fb13c2e466b9811104cbd7747ea6ca8c14ddb44802d934aadfe52a4b5dd916
+size 73272920

predictions/prediction_20251214_182353.tif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2fe092e1fd96e56da519acffe5ca5c9a8246e796bc5700cffb9694dc99f3aec
+size 73272920

processMask-test.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809b41520bb499e1032042e806ffb9f3c798609a88edc771efb75e39dd80f20d
+size 1335865

processMask.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c282f1a104a47a2837f1882da8011293051f507b0bb1d7e6ab27ba68b24dc19
+size 787409

requirement.txt

@@ -0,0 +1,309 @@
+affine @ file:///home/conda/feedstock_root/build_artifacts/affine_1733762038348/work
+aiobotocore==2.25.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.15
+aioitertools==0.12.0
+aiosignal==1.4.0
+alembic==1.16.5
+annotated-doc==0.0.4
+annotated-types==0.7.0
+antimeridian @ file:///home/conda/feedstock_root/build_artifacts/antimeridian_1753706324394/work
+anyio @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_anyio_1758634638/work
+argon2-cffi @ file:///home/conda/feedstock_root/build_artifacts/argon2-cffi_1749017159514/work
+argon2-cffi-bindings @ file:///home/conda/feedstock_root/build_artifacts/argon2-cffi-bindings_1649500328244/work
+arrow @ file:///home/conda/feedstock_root/build_artifacts/arrow_1733584251875/work
+asciitree==0.3.3
+asttokens @ file:///home/conda/feedstock_root/build_artifacts/asttokens_1733250440834/work
+async-lru @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_async-lru_1742153708/work
+async-timeout==3.0.1
+attrs @ file:///home/conda/feedstock_root/build_artifacts/attrs_1741918516150/work
+babel @ file:///home/conda/feedstock_root/build_artifacts/babel_1738490167835/work
+beautifulsoup4 @ file:///home/conda/feedstock_root/build_artifacts/beautifulsoup4_1759146011391/work
+bleach @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_bleach_1737382993/work
+blinker==1.9.0
+bokeh==3.7.3
+boto3==1.40.18
+botocore==1.40.49
+Bottleneck @ file:///croot/bottleneck_1731058641041/work
+branca @ file:///croot/branca_1675157607453/work
+Brotli @ file:///croot/brotli-split_1736182456865/work
+brotlicffi @ file:///croot/brotlicffi_1736182461069/work
+cached-property @ file:///home/conda/feedstock_root/build_artifacts/cached_property_1615209429212/work
+cachetools==6.2.0
+Cartopy==0.25.0
+certifi @ file:///home/conda/feedstock_root/build_artifacts/certifi_1759648874697/work/certifi
+cffi @ file:///croot/cffi_1736182485317/work
+cftime @ file:///home/conda/feedstock_root/build_artifacts/cftime_1649636873066/work
+chardet @ file:///home/conda/feedstock_root/build_artifacts/chardet_1649184137891/work
+charset-normalizer @ file:///croot/charset-normalizer_1721748349566/work
+ciso8601==2.3.3
+click @ file:///home/conda/feedstock_root/build_artifacts/click_1747811314515/work
+click-plugins @ file:///home/conda/feedstock_root/build_artifacts/click-plugins_1750848229740/work
+cligj @ file:///home/conda/feedstock_root/build_artifacts/cligj_1733749956636/work
+cloudpickle @ file:///home/conda/feedstock_root/build_artifacts/cloudpickle_1736947526808/work
+colorama==0.4.6
+colorcet==3.1.0
+comm @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_comm_1753453984/work
+contourpy @ file:///croot/contourpy_1732540045555/work
+cycler @ file:///tmp/build/80754af9/cycler_1637851556182/work
+cytoolz==0.11.2
+dask @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_dask-core_1760473436/work
+dask-gateway @ file:///Users/runner/miniforge3/conda-bld/bld/rattler-build_dask-gateway_1744370153/work/dask-gateway
+dask-glm @ file:///home/conda/feedstock_root/build_artifacts/dask-glm_1701346265909/work
+dask-image==2024.5.3
+dask-ml @ file:///home/conda/feedstock_root/build_artifacts/dask-ml_1679705292494/work
+datacube==1.8.15
+datacube_ows==1.9.4
+datashader==0.18.2
+dea-tools==0.3.0
+debugpy @ file:///home/task_175706711740264/conda-bld/debugpy_1757067131873/work
+decorator @ file:///home/conda/feedstock_root/build_artifacts/decorator_1740384970518/work
+deepdiff==8.6.1
+defusedxml @ file:///home/conda/feedstock_root/build_artifacts/defusedxml_1615232257335/work
+deprecat @ file:///home/conda/feedstock_root/build_artifacts/deprecat_1734684036993/work
+distributed @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_distributed_1760476147/work
+eo-tides==0.8.2
+exceptiongroup @ file:///home/conda/feedstock_root/build_artifacts/exceptiongroup_1746947292760/work
+executing @ file:///home/conda/feedstock_root/build_artifacts/executing_1756729339227/work
+fastapi==0.124.3
+fasteners @ file:///home/conda/feedstock_root/build_artifacts/fasteners_1734943108928/work
+fastjsonschema @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_python-fastjsonschema_1755304154/work/dist
+filelock==3.19.1
+fiona==1.10.1
+Flask==3.1.2
+flask-babel==4.0.0
+flatbuffers==25.2.10
+folium==0.20.0
+fonttools @ file:///croot/fonttools_1737039080035/work
+fqdn @ file:///home/conda/feedstock_root/build_artifacts/fqdn_1733327382592/work/dist
+frozenlist==1.7.0
+fsspec @ file:///home/conda/feedstock_root/build_artifacts/fsspec_1756908513222/work
+GDAL @ file:///croot/gdal-split_1734448174900/work/build/swig/python
+GeoAlchemy2 @ file:///home/conda/feedstock_root/build_artifacts/geoalchemy2_1753372953474/work
+geographiclib==2.1
+geojson==3.2.0
+geomad==1.0.0
+geopandas @ file:///croot/geopandas-split_1755761494241/work
+geopy==2.4.1
+greenlet @ file:///home/conda/feedstock_root/build_artifacts/greenlet_1648882383677/work
+h11 @ file:///home/conda/feedstock_root/build_artifacts/h11_1745526374115/work
+h2 @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_h2_1756364871/work
+h3==4.3.1
+hdstats==0.2.1
+holoviews==1.21.0
+hpack @ file:///home/conda/feedstock_root/build_artifacts/hpack_1737618293087/work
+httpcore @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_httpcore_1745602916/work
+httpx @ file:///home/conda/feedstock_root/build_artifacts/httpx_1733663348460/work
+hvplot==0.12.1
+hyperframe @ file:///home/conda/feedstock_root/build_artifacts/hyperframe_1737618333194/work
+idna==3.10
+imagecodecs==2025.3.30
+imageio==2.37.0
+importlib_metadata @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_importlib-metadata_1747934053/work
+ipykernel @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_ipykernel_1760459840/work
+ipyleaflet==0.20.0
+ipython @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_ipython_1748711175/work
+ipywidgets==8.1.7
+iso8601==2.1.0
+isoduration @ file:///home/conda/feedstock_root/build_artifacts/isoduration_1733493628631/work/dist
+itsdangerous==2.2.0
+jedi @ file:///home/conda/feedstock_root/build_artifacts/jedi_1733300866624/work
+Jinja2 @ file:///croot/jinja2_1741710844255/work
+jmespath @ file:///home/conda/feedstock_root/build_artifacts/jmespath_1733229141657/work
+joblib @ file:///home/conda/feedstock_root/build_artifacts/joblib_1756321760188/work
+json5 @ file:///home/conda/feedstock_root/build_artifacts/json5_1755034879854/work
+jsonpointer @ file:///home/conda/feedstock_root/build_artifacts/jsonpointer_1756754132747/work
+jsonschema @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_jsonschema_1755595646/work
+jsonschema-specifications==2025.4.1
+jupyter-events @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_jupyter_events_1738765986/work
+jupyter-leaflet==0.20.0
+jupyter-lsp @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_jupyter-lsp_1756388269/work/jupyter-lsp
+jupyter-ui-poll==1.0.0
+jupyter_client @ file:///home/conda/feedstock_root/build_artifacts/jupyter_client_1733440914442/work
+jupyter_core @ file:///home/conda/feedstock_root/build_artifacts/jupyter_core_1748333051527/work
+jupyter_server @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_jupyter_server_1755870522/work
+jupyter_server_terminals @ file:///home/conda/feedstock_root/build_artifacts/jupyter_server_terminals_1733427956852/work
+jupyterlab @ file:///home/conda/feedstock_root/build_artifacts/jupyterlab_1758913905644/work
+jupyterlab_pygments @ file:///home/conda/feedstock_root/build_artifacts/jupyterlab_pygments_1733328101776/work
+jupyterlab_server @ file:///home/conda/feedstock_root/build_artifacts/jupyterlab_server_1733599573484/work
+jupyterlab_widgets==3.0.15
+kiwisolver @ file:///croot/kiwisolver_1737039087198/work
+lark==1.2.2
+lark-parser==0.12.0
+lazy_loader==0.4
+linkify-it-py==2.0.3
+llvmlite @ file:///croot/llvmlite_1741209858218/work
+locket @ file:///home/conda/feedstock_root/build_artifacts/locket_1650660393415/work
+lxml==5.4.0
+lz4 @ file:///croot/lz4_1736366683208/work
+Mako @ file:///home/conda/feedstock_root/build_artifacts/mako_1744317760971/work
+mapclassify @ file:///croot/mapclassify_1675157730177/work
+Markdown==3.9
+markdown-it-py==4.0.0
+MarkupSafe @ file:///croot/markupsafe_1738584038848/work
+matplotlib==3.10.5
+matplotlib-inline @ file:///home/conda/feedstock_root/build_artifacts/matplotlib-inline_1733416936468/work
+mdit-py-plugins==0.5.0
+mdurl==0.1.2
+mistune @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_mistune_1756495311/work
+mpmath==1.3.0
+msgpack @ file:///home/conda/feedstock_root/build_artifacts/msgpack-python_1648745999384/work
+multidict @ file:///home/conda/feedstock_root/build_artifacts/multidict_1648882415384/work
+multipledispatch @ file:///home/conda/feedstock_root/build_artifacts/multipledispatch_1721907546485/work
+narwhals==2.3.0
+nbclient @ file:///home/conda/feedstock_root/build_artifacts/nbclient_1734628800805/work
+nbconvert @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_nbconvert-core_1738067871/work
+nbformat @ file:///home/conda/feedstock_root/build_artifacts/nbformat_1733402752141/work
+nest_asyncio @ file:///home/conda/feedstock_root/build_artifacts/nest-asyncio_1733325553580/work
+netCDF4 @ file:///croot/netcdf4_1743512888672/work
+networkx @ file:///croot/networkx_1737039604450/work
+notebook @ file:///home/conda/feedstock_root/build_artifacts/notebook_1759152069573/work
+notebook_shim @ file:///home/conda/feedstock_root/build_artifacts/notebook-shim_1733408315203/work
+numba @ file:///croot/numba_1750798165355/work
+numcodecs @ file:///croot/numcodecs_1707513121886/work
+numexpr @ file:///croot/numexpr_1755766469354/work
+numpy @ file:///croot/numpy_and_numpy_base_1755590845055/work/dist/numpy-1.26.4-cp310-cp310-linux_x86_64.whl#sha256=1096d33ad9a9757a1b4b46634d809e894263fc8b78780bff36801684b6e8cc88
+nvidia-cublas-cu12==12.8.4.1
+nvidia-cuda-cupti-cu12==12.8.90
+nvidia-cuda-nvrtc-cu12==12.8.93
+nvidia-cuda-runtime-cu12==12.8.90
+nvidia-cudnn-cu12==9.10.2.21
+nvidia-cufft-cu12==11.3.3.83
+nvidia-cufile-cu12==1.13.1.3
+nvidia-curand-cu12==10.3.9.90
+nvidia-cusolver-cu12==11.7.3.90
+nvidia-cusparse-cu12==12.5.8.93
+nvidia-cusparselt-cu12==0.7.1
+nvidia-nccl-cu12==2.27.3
+nvidia-nvjitlink-cu12==12.8.93
+nvidia-nvtx-cu12==12.8.90
+odc-algo==0.2.3
+odc-geo==0.4.10
+odc-io==0.2.2
+odc-loader @ file:///home/conda/feedstock_root/build_artifacts/odc-loader_1743656085024/work
+odc-stac @ file:///home/conda/feedstock_root/build_artifacts/odc-stac_1746136311934/work
+odc-ui==0.2.1
+orderly-set==5.5.0
+overrides @ file:///home/conda/feedstock_root/build_artifacts/overrides_1734587627321/work
+OWSLib==0.34.1
+packaging @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_packaging_1745345660/work
+pandas @ file:///home/task_175982153789305/conda-bld/pandas_1759822248912/work/dist/pandas-2.3.3-cp310-cp310-linux_x86_64.whl#sha256=0de7c83109c411cc2a74419a396c92f65e3d1e457fb4d835e5f100cfb04393a7
+pandocfilters @ file:///home/conda/feedstock_root/build_artifacts/pandocfilters_1631603243851/work
+panel==1.7.5
+param==2.2.1
+parso @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_parso_1755974222/work
+partd @ file:///home/conda/feedstock_root/build_artifacts/partd_1715026491486/work
+pexpect @ file:///home/conda/feedstock_root/build_artifacts/pexpect_1733301927746/work
+pickleshare @ file:///home/conda/feedstock_root/build_artifacts/pickleshare_1733327343728/work
+pillow @ file:///croot/pillow_1738010226202/work
+PIMS==0.7
+planetary-computer==1.0.0
+platformdirs @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_platformdirs_1756227402/work
+prometheus_client==0.22.1
+prometheus_flask_exporter==0.23.2
+prompt_toolkit @ file:///home/conda/feedstock_root/build_artifacts/prompt-toolkit_1756321756983/work
+propcache==0.3.2
+psutil @ file:///home/conda/feedstock_root/build_artifacts/psutil_1653089181607/work
+psycopg2 @ file:///croot/psycopg2_1744919787325/work
+ptyprocess @ file:///home/conda/feedstock_root/build_artifacts/ptyprocess_1733302279685/work/dist/ptyprocess-0.7.0-py2.py3-none-any.whl#sha256=92c32ff62b5fd8cf325bec5ab90d7be3d2a8ca8c8a3813ff487a8d2002630d1f
+pure_eval @ file:///home/conda/feedstock_root/build_artifacts/pure_eval_1733569405015/work
+pyarrow @ file:///home/task_175983338836370/conda-bld/pyarrow_1759833584228/work/python
+pycparser @ file:///tmp/build/80754af9/pycparser_1636541352034/work
+pyct==0.5.0
+pydantic==2.11.7
+pydantic_core==2.33.2
+Pygments @ file:///home/conda/feedstock_root/build_artifacts/pygments_1750615794071/work
+pyogrio @ file:///croot/pyogrio_1741107161422/work
+pyows==0.3.1
+pyparsing @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_pyparsing_1753873557/work
+pyproj @ file:///croot/pyproj_1739284761968/work
+PyQt6==6.7.1
+PyQt6_sip @ file:///croot/pyqt-split_1753427276959/work/pyqt_sip
+pyshp==2.3.1
+PySocks @ file:///home/builder/ci_310/pysocks_1640793678128/work
+pystac @ file:///home/conda/feedstock_root/build_artifacts/pystac_1758218055393/work
+pystac-client==0.9.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.1
+python-json-logger @ file:///home/conda/feedstock_root/build_artifacts/python-json-logger_1677079630776/work
+python-slugify==8.0.4
+pyTMD==2.2.8
+pytz @ file:///home/conda/feedstock_root/build_artifacts/pytz_1742920838005/work
+pyviz_comms==3.0.6
+PyYAML==6.0.2
+pyzmq @ file:///croot/pyzmq_1734687138743/work
+rasterio @ file:///croot/rasterio_1740069178893/work
+rasterstats==0.20.0
+referencing==0.36.2
+regex==2025.9.1
+requests @ file:///croot/requests_1756709366904/work
+rfc3339_validator @ file:///home/conda/feedstock_root/build_artifacts/rfc3339-validator_1733599910982/work
+rfc3986-validator @ file:///home/conda/feedstock_root/build_artifacts/rfc3986-validator_1598024191506/work
+rfc3987==1.3.8
+rfc3987-syntax @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_rfc3987-syntax_1752876729/work
+rioxarray @ file:///home/conda/feedstock_root/build_artifacts/rioxarray_1737140588464/work
+rpds-py @ file:///croot/rpds-py_1736541261634/work
+ruamel.yaml @ file:///home/conda/feedstock_root/build_artifacts/ruamel.yaml_1649033201098/work
+ruamel.yaml.clib==0.2.12
+s3fs==2025.9.0
+s3transfer==0.13.1
+scikit-image==0.25.2
+scikit-learn==1.7.1
+scipy @ file:///croot/scipy_1747238027288/work/dist/scipy-1.15.3-cp310-cp310-linux_x86_64.whl#sha256=2a791554880ad4f358fcc4cd2a982ffe1e9d472e9241011216b2be797457f1f9
+seaborn==0.13.2
+Send2Trash @ file:///home/conda/feedstock_root/build_artifacts/send2trash_1733322040660/work
+setuptools-scm==9.2.0
+shapely @ file:///croot/shapely_1754380812723/work
+simplejson==3.20.1
+sip @ file:///croot/sip_1738856193618/work
+six==1.17.0
+slicerator==1.1.0
+sniffio @ file:///home/conda/feedstock_root/build_artifacts/sniffio_1733244044561/work
+snuggs @ file:///home/conda/feedstock_root/build_artifacts/snuggs_1733818638588/work
+sortedcontainers @ file:///home/conda/feedstock_root/build_artifacts/sortedcontainers_1738440353519/work
+soupsieve @ file:///home/conda/feedstock_root/build_artifacts/soupsieve_1756330469801/work
+sparse @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_sparse_1747799051/work
+SQLAlchemy==1.4.54
+stack_data @ file:///home/conda/feedstock_root/build_artifacts/stack_data_1733569443808/work
+starlette==0.50.0
+sympy==1.14.0
+tblib @ file:///home/conda/feedstock_root/build_artifacts/tblib_1743515515538/work
+terminado @ file:///home/conda/feedstock_root/build_artifacts/terminado_1710262609923/work
+text-unidecode==1.3
+threadpoolctl @ file:///home/conda/feedstock_root/build_artifacts/threadpoolctl_1741878222898/work
+tifffile==2025.5.10
+timescale==0.0.9
+timezonefinder==8.0.0
+tinycss2 @ file:///home/conda/feedstock_root/build_artifacts/tinycss2_1729802851396/work
+tomli @ file:///croot/tomli_1753774587605/work
+toolz @ file:///home/conda/feedstock_root/build_artifacts/toolz_1733736030883/work
+torch==2.8.0
+tornado @ file:///croot/tornado_1748956929273/work
+tqdm==4.67.1
+traitlets @ file:///home/conda/feedstock_root/build_artifacts/traitlets_1733367359838/work
+traittypes==0.2.1
+triton==3.4.0
+types-python-dateutil @ file:///home/conda/feedstock_root/build_artifacts/types-python-dateutil_1759899809376/work
+typing-inspection==0.4.1
+typing_extensions @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_typing_extensions_1756220668/work
+typing_utils @ file:///home/conda/feedstock_root/build_artifacts/typing_utils_1733331286120/work
+tzdata @ file:///croot/python-tzdata_1746123641790/work
+uc-micro-py==1.0.3
+unicodedata2 @ file:///croot/unicodedata2_1736541023050/work
+uri-template @ file:///home/conda/feedstock_root/build_artifacts/uri-template_1733323593477/work/dist
+urllib3 @ file:///croot/urllib3_1750775463400/work
+uvicorn==0.38.0
+wcwidth @ file:///home/conda/feedstock_root/build_artifacts/wcwidth_1733231326287/work
+webcolors @ file:///home/conda/feedstock_root/build_artifacts/webcolors_1733359735138/work
+webencodings @ file:///home/conda/feedstock_root/build_artifacts/webencodings_1733236011802/work
+websocket-client @ file:///home/conda/feedstock_root/build_artifacts/websocket-client_1759928050786/work
+Werkzeug==3.1.3
+widgetsnbextension==4.0.14
+wrapt @ file:///home/conda/feedstock_root/build_artifacts/wrapt_1651495243689/work
+xarray @ file:///home/conda/feedstock_root/build_artifacts/xarray_1749743207754/work
+xgboost==3.1.2
+xyzservices @ file:///croot/xyzservices_1675159059961/work
+yarl==1.20.1
+zarr @ file:///home/conda/feedstock_root/build_artifacts/zarr_1733237197728/work
+zict @ file:///home/conda/feedstock_root/build_artifacts/zict_1733261551178/work
+zipp @ file:///home/conda/feedstock_root/build_artifacts/zipp_1749421620841/work

requirements_api.txt

@@ -0,0 +1,3 @@
+fastapi
+uvicorn
+pydantic

start.sh

@@ -0,0 +1 @@
+uvicorn api_server:app --reload --host 0.0.0.0 --port 8000

test_VH_VV.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8fa50e2debed3c65b599f956095550a72844082245ae2500d1ab196ae23641e
+size 393276

train_module.py

@@ -0,0 +1,532 @@
+"""
+Training module for land classification using Sentinel-2 and Sentinel-1 data
+from Microsoft Planetary Computer STAC API
+"""
+
+import numpy as np
+import xarray as xr
+import geopandas as gpd
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
+from sklearn.metrics import classification_report, confusion_matrix
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.svm import SVC
+from xgboost import XGBClassifier
+import joblib
+from datetime import datetime
+import json
+import os
+import warnings
+import hashlib
+from pathlib import Path
+warnings.filterwarnings('ignore')
+
+# PyTorch for CNN
+try:
+    import torch
+    import torch.nn as nn
+    import torch.nn.functional as F
+    import torch.optim as optim
+    from torch.utils.data import TensorDataset, DataLoader
+    PYTORCH_AVAILABLE = True
+except ImportError:
+    PYTORCH_AVAILABLE = False
+    print("Warning: PyTorch not available. CNN model will not work.")
+
+# Define CNN model class for PyTorch
+class CNNClassifier(nn.Module):
+    def __init__(self, n_features, n_classes):
+        super(CNNClassifier, self).__init__()
+        self.n_features = n_features
+        self.n_classes = n_classes
+        
+        # For small feature sets (like 3 features), use simpler architecture
+        if n_features < 8:
+            # Simple fully connected network for small features
+            self.use_conv = False
+            self.fc1 = nn.Linear(n_features, 64)
+            self.dropout1 = nn.Dropout(0.3)
+            self.fc2 = nn.Linear(64, 128)
+            self.dropout2 = nn.Dropout(0.5)
+            self.fc3 = nn.Linear(128, n_classes)
+        else:
+            # CNN architecture for larger feature sets
+            self.use_conv = True
+            self.conv1 = nn.Conv1d(in_channels=1, out_channels=32, kernel_size=3, padding=1)
+            self.pool1 = nn.MaxPool1d(kernel_size=2)
+            self.conv2 = nn.Conv1d(in_channels=32, out_channels=64, kernel_size=3, padding=1)
+            self.pool2 = nn.MaxPool1d(kernel_size=2)
+            
+            # Calculate size after convolutions
+            conv_output_size = (n_features // 2 // 2) * 64
+            
+            # Fully connected layers
+            self.fc1 = nn.Linear(conv_output_size, 128)
+            self.dropout = nn.Dropout(0.5)
+            self.fc2 = nn.Linear(128, n_classes)
+    
+    def forward(self, x):
+        # x shape: (batch, n_features) or (batch, 1, n_features)
+        if self.use_conv:
+            # CNN path for larger feature sets
+            if len(x.shape) == 2:
+                x = x.unsqueeze(1)  # Add channel dimension
+            x = F.relu(self.conv1(x))
+            x = self.pool1(x)
+            x = F.relu(self.conv2(x))
+            x = self.pool2(x)
+            x = x.view(x.size(0), -1)  # Flatten
+            x = F.relu(self.fc1(x))
+            x = self.dropout(x)
+            x = self.fc2(x)
+        else:
+            # Fully connected path for small feature sets
+            if len(x.shape) == 3:
+                x = x.squeeze(1)  # Remove channel dimension if present
+            x = F.relu(self.fc1(x))
+            x = self.dropout1(x)
+            x = F.relu(self.fc2(x))
+            x = self.dropout2(x)
+            x = self.fc3(x)
+        return x
+    
+    def predict(self, X):
+        """Scikit-learn style predict method"""
+        self.eval()
+        with torch.no_grad():
+            if isinstance(X, np.ndarray):
+                X = torch.FloatTensor(X)
+            # Handle both 2D and 3D inputs
+            if not self.use_conv and len(X.shape) == 3:
+                X = X.squeeze(1)
+            elif self.use_conv and len(X.shape) == 2:
+                X = X.unsqueeze(1)
+            outputs = self(X)
+            _, predicted = torch.max(outputs, 1)
+            return predicted.cpu().numpy()
+    
+    def score(self, X, y):
+        """Scikit-learn style score method"""
+        predictions = self.predict(X)
+        if isinstance(y, torch.Tensor):
+            y = y.cpu().numpy()
+        return np.mean(predictions == y)
+
+# Microsoft Planetary Computer imports
+import planetary_computer
+from pystac_client import Client
+from odc.stac import load as stac_load
+
+
+def train_model(
+    bbox=[105.6, 9.3, 106.2, 9.8],
+    time_range='2023-03-01/2023-05-31',
+    max_scenes=12,
+    cloud_cover=30,
+    resolution=20,
+    training_shapefile='train/ST_training data_updated_1130points_new.shp',
+    model_type='xgboost',
+    n_estimators=100,
+    max_depth=20,
+    learning_rate=0.1,
+    use_gpu=True,
+    use_cache=True,
+    output_model_path=None,
+    status_callback=None,
+    cancel_check=None
+):
+    """
+    Train a land classification model using Sentinel-2 and Sentinel-1 data
+    
+    Args:
+        bbox: [min_lon, min_lat, max_lon, max_lat]
+        time_range: "YYYY-MM-DD/YYYY-MM-DD"
+        max_scenes: maximum number of scenes to load
+        cloud_cover: maximum cloud cover percentage
+        resolution: resolution in meters (e.g., 20)
+        training_shapefile: path to training shapefile
+        n_estimators: number of trees for XGBoost
+        max_depth: maximum tree depth
+        learning_rate: learning rate for XGBoost
+        use_gpu: whether to use GPU for training
+        output_model_path: path to save trained model (auto-generated if None)
+        status_callback: Optional callback function to report progress
+        cancel_check: Optional function that returns True if training should be cancelled
+    
+    Returns:
+        Dictionary containing training results
+    """
+    
+    def update_status(message, progress=None):
+        """Helper to update status"""
+        if status_callback:
+            # Try calling with both arguments, fallback to just message
+            try:
+                status_callback(message, progress)
+            except TypeError:
+                status_callback(message)
+        print(message)
+    
+    def check_cancellation():
+        """Check if training should be cancelled"""
+        if cancel_check and cancel_check():
+            raise InterruptedError("Training cancelled by user")
+    
+    try:
+        # Auto-generate output path if not provided
+        if output_model_path is None:
+            timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
+            output_model_path = f'model_train/model_{model_type}_{timestamp}.joblib'
+        
+        # ============ CACHE SYSTEM ============
+        # Create cache directory
+        cache_dir = Path("dataset_cache")
+        cache_dir.mkdir(exist_ok=True)
+        
+        # Generate cache key from parameters
+        cache_params = f"{bbox}_{time_range}_{max_scenes}_{cloud_cover}_{resolution}"
+        cache_key = hashlib.md5(cache_params.encode()).hexdigest()
+        cache_file = cache_dir / f"training_data_{cache_key}.joblib"
+        
+        features = None
+        labels = None
+        
+        # Try to load from cache
+        if use_cache and cache_file.exists():
+            update_status(f"📦 Loading cached dataset from {cache_file.name}...", 5)
+            try:
+                cached_data = joblib.load(cache_file)
+                features = cached_data['features']
+                labels = cached_data['labels']
+                update_status(f"✅ Loaded {len(features)} samples from cache (skipped satellite download!)", 50)
+            except Exception as e:
+                update_status(f"⚠️ Cache load failed: {str(e)}, downloading fresh data...", 10)
+                features = None
+        
+        # If no cache or cache failed, download data
+        if features is None:
+            update_status("📡 Cache not found or disabled, downloading satellite data...", 10)
+            
+            # Connect to Microsoft Planetary Computer
+            update_status("Connecting to Microsoft Planetary Computer...", 12)
+            catalog = Client.open("https://planetarycomputer.microsoft.com/api/stac/v1")
+            check_cancellation()
+            
+            # Search for Sentinel-2 scenes
+            update_status("Searching for Sentinel-2 scenes...", 10)
+            query_s2 = catalog.search(
+                collections=["sentinel-2-l2a"],
+                bbox=bbox,
+                datetime=time_range,
+                query={"eo:cloud_cover": {"lt": cloud_cover}}
+            )
+            items_s2 = list(query_s2.item_collection())
+            
+            check_cancellation()
+            
+            # Limit scenes
+            if len(items_s2) > max_scenes:
+                step = len(items_s2) // max_scenes
+                items_s2 = items_s2[::step][:max_scenes]
+            
+            update_status(f"Found {len(items_s2)} Sentinel-2 scenes", 20)
+            
+            # Sign and load Sentinel-2 data
+            update_status("Loading Sentinel-2 data...", 25)
+            items_s2 = [planetary_computer.sign(item) for item in items_s2]
+            ds_s2 = stac_load(
+                items_s2,
+                bands=["B04", "B08", "SCL"],
+                crs="EPSG:32648",
+                resolution=resolution,
+                bbox=bbox,
+                patch_url=planetary_computer.sign,
+                fail_on_error=False,
+            )
+            ds_s2 = ds_s2.rename({"B04": "red", "B08": "nir", "SCL": "scl"})
+            
+            check_cancellation()
+            
+            # Search for Sentinel-1 scenes
+            update_status("Searching for Sentinel-1 scenes...", 35)
+            query_s1 = catalog.search(
+                collections=["sentinel-1-rtc"],
+                bbox=bbox,
+                datetime=time_range,
+            )
+            items_s1 = list(query_s1.item_collection())
+            
+            # Limit scenes
+            if len(items_s1) > max_scenes:
+                step = len(items_s1) // max_scenes
+                items_s1 = items_s1[::step][:max_scenes]
+            
+            update_status(f"Found {len(items_s1)} Sentinel-1 scenes", 40)
+            
+            # Sign and load Sentinel-1 data
+            update_status("Loading Sentinel-1 data...", 45)
+            items_s1 = [planetary_computer.sign(item) for item in items_s1]
+            ds_s1 = stac_load(
+                items_s1,
+                bands=["vv", "vh"],
+                crs="EPSG:32648",
+                resolution=resolution,
+                bbox=bbox,
+                patch_url=planetary_computer.sign,
+                fail_on_error=False,
+            )
+            
+            # Convert to dB
+            ds_s1['vv_db'] = 10 * np.log10(ds_s1['vv'].where(ds_s1['vv'] > 0))
+            ds_s1['vh_db'] = 10 * np.log10(ds_s1['vh'].where(ds_s1['vh'] > 0))
+            
+            check_cancellation()
+            
+            # Calculate NDVI
+            update_status("Calculating NDVI...", 50)
+            ndvi = (ds_s2['nir'] - ds_s2['red']) / (ds_s2['nir'] + ds_s2['red'] + 1e-8)
+            
+            # Apply cloud mask
+            cloud_mask = ds_s2['scl'].isin([1, 3, 8, 9, 10])
+            ndvi_masked = ndvi.where(~cloud_mask)
+            ndvi_mean = ndvi_masked.mean(dim='time')
+            
+            # Load training data
+            update_status("Loading training data...", 55)
+            train_gdf = gpd.read_file(training_shapefile)
+            
+            if train_gdf.crs != 'EPSG:32648':
+                train_gdf = train_gdf.to_crs('EPSG:32648')
+            
+            # Auto-detect label column
+            label_column = None
+            for col in ['HT_code', 'Ma_LU', 'LU2022', 'Hientrang', 'class', 'Class', 'CLASS']:
+                if col in train_gdf.columns:
+                    label_column = col
+                    break
+            
+            if label_column is None:
+                raise ValueError(f"Cannot find label column in shapefile. Available: {list(train_gdf.columns)}")
+            
+            # Extract features
+            update_status("Extracting features from training points...", 60)
+            features = []
+            labels = []
+            
+            for idx, row in train_gdf.iterrows():
+                point = row.geometry
+                x_coord = point.x
+                y_coord = point.y
+                label = row[label_column]
+                
+                try:
+                    ndvi_val = ndvi_mean.sel(x=x_coord, y=y_coord, method='nearest').values
+                    vh_val = ds_s1['vh_db'].sel(x=x_coord, y=y_coord, method='nearest').mean(dim='time').values
+                    vv_val = ds_s1['vv_db'].sel(x=x_coord, y=y_coord, method='nearest').mean(dim='time').values
+                    
+                    feature_vec = [ndvi_val, vh_val, vv_val]
+                    
+                    if not np.isnan(feature_vec).any():
+                        features.append(feature_vec)
+                        labels.append(label)
+                except:
+                    continue
+            
+            features = np.array(features)
+            labels = np.array(labels)
+            
+            check_cancellation()
+            
+            update_status(f"Extracted {len(features)} valid training samples", 70)
+            
+            # ============ SAVE TO CACHE ============
+            if use_cache:
+                update_status(f"💾 Saving dataset to cache for future use...", 72)
+                try:
+                    cache_data = {
+                        'features': features,
+                        'labels': labels,
+                        'bbox': bbox,
+                        'time_range': time_range,
+                        'resolution': resolution,
+                        'timestamp': datetime.now().isoformat()
+                    }
+                    joblib.dump(cache_data, cache_file)
+                    update_status(f"✅ Cached to {cache_file.name}", 75)
+                except Exception as e:
+                    update_status(f"⚠️ Cache save failed: {str(e)}", 75)
+        
+        # Encode labels
+        label_encoder = LabelEncoder()
+        labels_encoded = label_encoder.fit_transform(labels)
+        
+        # Split data
+        X_train, X_test, y_train, y_test = train_test_split(
+            features, labels_encoded, test_size=0.2, random_state=42, stratify=labels_encoded
+        )
+        
+        # Train model based on selected type
+        update_status(f"Training {model_type.upper()} model...", 75)
+        
+        device = 'cuda:0' if use_gpu else 'cpu'
+        
+        if model_type == 'xgboost':
+            model = XGBClassifier(
+                n_estimators=n_estimators,
+                max_depth=max_depth,
+                learning_rate=learning_rate,
+                device=device if use_gpu else 'cpu',
+                tree_method='hist',
+                random_state=42,
+                eval_metric='mlogloss',
+                verbosity=0
+            )
+        elif model_type == 'random_forest':
+            model = RandomForestClassifier(
+                n_estimators=n_estimators,
+                max_depth=max_depth,
+                random_state=42,
+                n_jobs=-1,  # Use all cores
+                verbose=0
+            )
+        elif model_type == 'decision_tree':
+            model = DecisionTreeClassifier(
+                max_depth=max_depth,
+                random_state=42
+            )
+        elif model_type == 'svm':
+            model = SVC(
+                kernel='rbf',
+                random_state=42,
+                verbose=False
+            )
+        elif model_type == 'cnn':
+            if not PYTORCH_AVAILABLE:
+                raise ImportError("PyTorch is required for CNN. Install: pip install torch")
+            
+            # CNN requires reshaping data
+            n_features = X_train.shape[1]
+            n_classes = len(np.unique(y_train))
+            
+            # Build PyTorch CNN model
+            device = torch.device('cuda' if torch.cuda.is_available() and use_gpu else 'cpu')
+            update_status(f"Building CNN model on {device}...", 75)
+            
+            model = CNNClassifier(n_features, n_classes).to(device)
+            
+            # Convert to PyTorch tensors
+            X_train_tensor = torch.FloatTensor(X_train).unsqueeze(1)  # Add channel dim: (N, 1, features)
+            y_train_tensor = torch.LongTensor(y_train)
+            X_test_tensor = torch.FloatTensor(X_test).unsqueeze(1)
+            y_test_tensor = torch.LongTensor(y_test)
+            
+            # Create data loaders
+            train_dataset = TensorDataset(X_train_tensor, y_train_tensor)
+            train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)
+            
+            # Loss and optimizer
+            criterion = nn.CrossEntropyLoss()
+            optimizer = optim.Adam(model.parameters(), lr=0.001)
+            
+            # Train CNN
+            update_status("Training CNN model with PyTorch...", 80)
+            epochs = min(50, n_estimators // 2)  # Use n_estimators as epochs
+            
+            model.train()
+            for epoch in range(epochs):
+                epoch_loss = 0.0
+                for batch_X, batch_y in train_loader:
+                    batch_X, batch_y = batch_X.to(device), batch_y.to(device)
+                    
+                    optimizer.zero_grad()
+                    outputs = model(batch_X)
+                    loss = criterion(outputs, batch_y)
+                    loss.backward()
+                    optimizer.step()
+                    
+                    epoch_loss += loss.item()
+                
+                if (epoch + 1) % 10 == 0:
+                    avg_loss = epoch_loss / len(train_loader)
+                    update_status(f"CNN Epoch {epoch+1}/{epochs}, Loss: {avg_loss:.4f}", 80 + (epoch / epochs) * 10)
+            
+            # Move model to CPU for saving (compatible with non-GPU systems)
+            model = model.cpu()
+            model.device_used = str(device)
+        else:
+            raise ValueError(f"Unknown model type: {model_type}. Choose: xgboost, random_forest, decision_tree, svm, cnn")
+        
+        # Fit non-CNN models
+        if model_type != 'cnn':
+            model.fit(X_train, y_train)
+        
+        # Evaluate
+        update_status("Evaluating model...", 90)
+        if model_type == 'cnn':
+            # PyTorch CNN evaluation
+            train_score = model.score(X_train, y_train)
+            test_score = model.score(X_test, y_test)
+        else:
+            train_score = model.score(X_train, y_train)
+            test_score = model.score(X_test, y_test)
+        
+        # Save model
+        update_status("Saving model...", 95)
+        os.makedirs(os.path.dirname(output_model_path), exist_ok=True)
+        joblib.dump({'model': model, 'label_encoder': label_encoder}, output_model_path)
+        
+        # Save model info
+        info = {
+            "timestamp": datetime.now().isoformat(),
+            "data_source": "Microsoft Planetary Computer STAC",
+            "collections": ["sentinel-2-l2a", "sentinel-1-rtc"],
+            "features": ["NDVI_mean", "VH_dB_mean", "VV_dB_mean"],
+            "training_samples": len(X_train),
+            "testing_samples": len(X_test),
+            "train_accuracy": float(train_score),
+            "test_accuracy": float(test_score),
+            "model_type": model_type,
+            "device": device if model_type == 'xgboost' else 'cpu',
+            "n_estimators": n_estimators if model_type in ['xgboost', 'random_forest', 'cnn'] else None,
+            "max_depth": max_depth if model_type != 'cnn' else None,
+            "learning_rate": learning_rate if model_type == 'xgboost' else None,
+            "cnn_epochs": min(50, n_estimators // 2) if model_type == 'cnn' else None,
+            "n_features": X_train.shape[1],
+            "n_classes": len(np.unique(y_train)),
+            "bbox": bbox,
+            "time_range": time_range,
+            "resolution": resolution
+        }
+        
+        info_path = output_model_path.replace('.joblib', '_info.json')
+        with open(info_path, 'w') as f:
+            json.dump(info, f, indent=2)
+        
+        update_status("Training complete!", 100)
+        
+        return {
+            "success": True,
+            "model_path": output_model_path,
+            "info_path": info_path,
+            "train_accuracy": train_score,
+            "test_accuracy": test_score,
+            "training_samples": len(X_train),
+            "testing_samples": len(X_test),
+            "classes": label_encoder.classes_.tolist()
+        }
+        
+    except InterruptedError as e:
+        update_status(f"Cancelled: {str(e)}", -1)
+        return {
+            "success": False,
+            "error": str(e),
+            "cancelled": True
+        }
+        
+    except Exception as e:
+        update_status(f"Error: {str(e)}", -1)
+        return {
+            "success": False,
+            "error": str(e)
+        }