Accessible remote sensing data based reference evapotranspiration estimation modelling

Estimating reference evapotranspiration (ET0) is a fundamental requirement of agricultural water management. The FAO Penman-Monteith (FAO-PM) equation has been used as the standard for ET0 estimation. However, the lack of necessary meteorological data makes it difficult to estimate spatially distributed ET0 using the FAO-PM method in the wider ungauged areas. In this study, the aim is to explore the methodology for estimating reference evapotranspiration based on remote sensing data. In this method, remote sensing data are combined with machine learning algorithms to establish a model for spatially distributed ET0 estimation. Three machine learning algorithms were tested, including support vector machine (SVM), back-propagation neural network (BP), and adaptive neuro fuzzy inference system (ANFIS). Results showed this method had good ability in estimating ET0. Application of the method in Northwest China indicated that the land surface temperature (LST) can be used to accurately estimate ET0 with high correlation coefficients (r2 of 0.897-0.915). The surface reflectance has potential for estimating ET0 with LST and can slightly improve model accuracy based on LST. Evaluation showed LST was more essential than surface reflectance and the model only based on LST had satisfactory performance. This method could be applicability in worldwide with available remote sensing and meteorological data due to the relationship between LST and ET0.