The simplified hybrid model based on BP to predict the reference crop evapotranspiration in Southwest China

The accurate prediction of reference crop evapotranspiration is of great significance to climate research and regional agricultural water management. In order to realize the high-precision prediction of ET(O) in the absence of meteorological data, this study use XGBoost to select key influencing factors and BP algorithm to construct ET(O) prediction model of 12 meteorological stations in South West China in this study. ACO, CSO and CS algorithms are used to optimize the model and improve the adaptability of the model. The results show that T(max), n and Ra can be used as the input combination of ET(O) model construction, and T(max) is the primary factor affecting ET(O). ET(O) model constructed by BP algorithm has good goodness of fit with the ET(O) calculated by FAO-56 PM and ACO, CSO and CS have significant optimization effect on BP algorithm, among which CSO algorithm has the best optimization ability on BP, with RMSE, R(2), MAE, NSE, GPI ranging 0.200–0.377, 0.932–0.984, 0.140–0.261, 0.920–0.984, 1.472–2.000, GPI ranking is 1–23. Therefore, the input combination (T(max), n and Ra) and CSO-BP model are recommended as a simplified model for ET(O) prediction in Southwest China.