remote-sensing/model_comparison_results.md

📊 BẢNG SO SÁNH KẾT QUẢ CÁC MÔ HÌNH

1. Nhóm Phân loại Lớp phủ (Land Classification)

Model	Accuracy	Precision	Recall	F1-Score	Parameters
XGBoost	0.287611	0.353394	0.287611	0.234607	estimators:200, depth:6
swin-unet	0.724771	0.536633	0.59274	0.562804	N/A
swin-unet	0.600917	0.569649	0.590866	0.564547	N/A
cnn	0.507812	0.490742	0.474017	0.452274	N/A
swin-unet	0.732283	0.722509	0.677869	0.660619	estimators:500, depth:256
swin-unet	0.203791	0.130717	0.167561	0.126147	N/A
LightGBM_Balanced	0.185841	0.284595	0.185841	0.147651	estimators:300, depth:-1
svm	0.582677	0.441728	0.464997	0.433273	N/A
random_forest	0.614173	0.503912	0.522185	0.509931	N/A
swin-unet	0.724771	0.536905	0.59274	0.562949	N/A
swin-unet	0.724771	0.537078	0.59274	0.562875	N/A
xgboost	0.274336	0.297502	0.203779	0.146772	N/A
swin-unet	0.720183	0.533799	0.589064	0.559531	N/A
xgboost	0.637795	0.5391	0.546491	0.538521	N/A
swin-unet	0.706422	0.523141	0.574641	0.547069	N/A
random_forest	0.376106				N/A
swin-unet	0.234375	0.0334821	0.142857	0.0542495	N/A
xgboost	0.578125	0.568048	0.534613	0.541406	N/A
mobilenet-lraspp	0.566929	0.543959	0.52518	0.477603	N/A
cnn	0.574803	0.476253	0.454007	0.400213	N/A
xgboost	0.756881	0.712478	0.700939	0.704615	N/A
mobilenet-lraspp	0.692661	0.65895	0.691875	0.650169	N/A
RandomForest_RealData	0.274336	0.330072	0.274336	0.215733	estimators:100, depth:15
decision_tree	0.590551	0.604639	0.613393	0.607498	N/A
lightgbm	0.598425	0.479595	0.507168	0.488216	N/A

2. Nhóm Xóa mây (Cloud Removal)

Model	Epochs	Train Loss	Val Loss
SwinUNet_Cloud_Removal	100	0.008	0.009
CNN_Cloud_Removal	50	0.015	0.012
SwinUNet_Cloud_Removal_RealData_GPU	1	0.157653	0.157653

3. Nhóm Dự báo Thực vật (NDVI Forecasting)

Model	RMSE	MAE	Epochs
LSTM Time Series (Real Data & GPU)	0.299411	0.0896472	50
Hybrid Physics-ML (DSSAT/WOFOST)	0.018	0.012	N/A
Multi-Model Ensemble (Real Data & CPU)	0.119913	0.0936021	N/A
LSTM/GRU Time Series	0.03	0.025	200
Statistical (SARIMA)	0.05	0.04	N/A
ConvLSTM Spatial-Temporal	0.02	0.015	100
ConvLSTM Spatial-Temporal (Real Data & GPU)	0.312591	0.0977133	20
Hybrid Physics-ML (Real Data & GPU)	0.0010379	0.000608871	N/A
Multi-Model Ensemble	0.015	0.01	N/A