Advanced geospatial analytics for evapotranspiration dynamics: Integration of Sentinel-1A and FAO Penman-Monteith method

Evapotranspiration (ET0) is vital for agriculture and environmental management, facing challenges from climate change. Optical remote sensing overcomes reliance on weather station data. The modeled ET0 using the FAO Penman-Monteith method and Partial Least Squares Regression on Sentinel-1A data with 2016-2017 meteorological archives. Comparative analyses revealed stability in transportation areas within deciduous forests and wetlands, contrasting temporal variations. ET0 was significantly influenced by relative humidity (RH) (70.80% to 89.89%), with temperature (T) playing a crucial role. Urban vegetated areas maintained stable T values (29.37°C), while forests exhibited dynamic T variations (24.24°C to 28.94°C). VH polarization captured diverse climatic influences, resulting in a broader range of dynamic ET0 values (7.38 to 10.76 mm/day) compared to VV polarization (6.74 to 9.34 mm/day). VH sensor performance varied; in October 2016 showed moderate accuracy R2 was 0.50 with slight underestimation Bias -0.08, while exceptional accuracy was seen in December 2017 R2 was 1.00 with positive bias (0.57) and excellent agreement KGE was 0.92. VV sensors in October 2016 had a firm fit R2 was 0.55, with moderate underestimation Bias -0.87, and in December 2017 displayed a good fit the R2 was 0.57, with slight overestimation Bias 0.44, and good agreement KGE 0.44. Integrating machine learning and satellite imagery enhances ET0 accuracy for real-time monitoring in adaptive management, addressing climate change, and showcasing sensor-specific variations. Future research should integrate multi-source synthetic aperture radar satellite data and machine learning for precise ET0 estimation in adaptive environmental management.