Keywordsbioenergy land use; MODIS; phenological mixture analysis; spatial constraint; endmember variability; the U.S. Midwest; rice fields mapping; HJ-1A/B CCD images; classification; phenology; crop mapping; Hidden Markov Models; time series analysis; phenology; multi-sensor; multi-temporal; temporal windows; data fusion; Mediterranean; rice; leaf area index; light distribution; canopy vertical architecture; model; remote sensing; ground-based measurement; hyperspectral; LAI; sensitivity; site-specific crop management; winter wheat; time series length; MODIS; feature selection; Random Forest; classification certainty; phenology; typhoon; rice; Philippines; rapid damage assessments; daily mean air temperature; land surface temperature; MODIS; meteorological station data; Shaanxi; rice; MODIS; Yangtze River Delta region; Normalized Weighted Difference Water Index; Enhanced Vegetation Index; temporal dependence; fruit yield and quality estimation; pyrus communis “conference”; hyperspectral remote sensing; satellite remote sensing; nitrogen status diagnosis; precision nitrogen management; chlorophyll meter; nitrogen nutrition index; rice; FORMOSAT-2; Crop temporal dynamics; Geostationary Ocean Color Imager (GOCI); MODIS; Nadir BRDF-adjusted reflectance (NBAR); normalized difference vegetation index (NDVI); semi-empirical BRDF model; agriculture; summer crops; Landsat 8 OLI; COSMO-SkyMed; rule-based classification; Random Forest; Enhanced Vegetation Index (EVI); Red Green Ratio Index (RGRI); Normalized Difference Flood Index (NDFI); multi-temporal; ground-based spectral measurements; vegetation indices; croplands; PROSAIL; chlorophyll fluorescence; FluorMODleaf; model inversion; Bayesian approach; hyperspectral remote sensing; radiative transfer; six algorithms; comparative analysis; number of wavelengths; leaf nitrogen concentration; monitoring accuracy; winter wheat; crop status; crop monitoring; crop mapping; canopy reflectance; spectral; optical; SAR; phenology
