Assessing forecast performance of daily reference evapotranspiration: A comparison of equations, machine and deep learning using weather forecasts

• Published in: Journal of hydrology (Amsterdam) Vol. 644; p. 132101
• Main Authors: Qian, Haiyang, Wang, Weiguang, Chen, Gang
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.11.2024
• Subjects: Machine and deep learning; North China Plain; Reference evapotranspiration; Short-term daily forecasting; Weather forecasts; Bi-LSTM; Short-term daily forecasting; RT; PT; DL; Machine and deep learning; HS; RPM; BP; SVR; Reference evapotranspiration; Tmin; ML; North China Plain; ET0; NSE; LSTM; RMSE; Weather forecasts; n; MAE; r; s; RF; RH; Tmax; NCP; PM; APM; ETPM 0
• ISSN: 0022-1694
• DOI: 10.1016/j.jhydrol.2024.132101

•Daily ET0 forecasts are compared by using conventional equations, machine and deep learning models.•Machine and deep learning models generally outperform equations based on weather forecasts.•Adding meteorological data mildly enhances machine learning but greatly uplifts deep learning accuracy.•The Bi-LSTM performed well in forecasting daily ET0 for 7-days lead time in the North China Plain. An accurate forecast of short-term reference evapotranspiration (ET0) is crucial for effective farm and irrigation scheduling management. The techniques of forecasting ET0 have progressed from empirical equations to artificial intelligence-based models. However, gaps have remained in comprehensively evaluating the ET0 forecast performance discrepancies between various methods based on weather forecasts in addition to historical meteorological data, as well as investigating the effect of the amount of input variables on ET0 forecast accuracy. Here, the study evaluated the forecast accuracy of five conventional equations calibrated and six machine learning (ML) and deep learning (DL) models in predicting daily ET0 for a lead time of 1–7 days in the North China Plain (NCP). Comparative evaluations indicate that the Analytical Penman-Monteith (APM) is the optimum empirical equation for forecasting ET0, but its accuracy decreases as lead times increase. Conversely, ML and DL models consistently outperform empirical equations, characterized by lower mean absolute error (MAE) and root mean square error (RMSE) as well as correlation coefficient and Nash-Sutcliffe efficiency coefficient approaching 1 across all lead times. Notably, the Bidirectional Long short-term memory (Bi-LSTM) model outperforms other models, maintaining robust and effective forecast performance even on day 7. Moreover, with the increasing input variables, combining weather forecasts and historical meteorological data, the forecast performance of all models is improved, with significant enhancement observed in the Bi-LSTM model. This work provides valuable insights for choosing appropriate models to forecast ET0, holding essential in regional managing farm and irrigation systems.