Deep learning for daily potential evapotranspiration using a HS-LSTM approach.

Accurate estimation of potential evapotranspiration (ET 0) is important for the sound design of irrigation schedules, management of water resources, assessment of hydrological drought, and research on atmospheric variations. The present study proposed a novel deep learning (DL) approach for daily ET 0 estimations with limited daily climate data: HS- LSTM. This approach was constructed based on a classic ET 0 model and a long short-term memory neural network (LSTM). Specifically, the Hargreaves-Samani (HS) model was employed as the classic model, and the predictors were restricted to the daily maximum and minimum air temperature data. Ground truth data for ET 0 were employed to train, validate, and test the models. Traditional machine learning (ML) algorithms comprising adaptive neuro-fuzzy inference system (ANFIS), genetic programming (GP), multi-gene genetic programming (MGGP), and one-dimensional CNN (1D-CNN), as well as the HS-ML models (HS-ANFIS, HS-GP, HS-MGGP, HS-1D-CNN), were also established and assessed for daily ET 0 estimations. Compared to the other tested approaches, the errors of the HS-LSTM technique significantly decreased, demonstrating that the novel HS-LSTM approach significantly outperformed the other techniques beyond the study area (in Songliao Basin, Northeast China, which is a semi-humid zone with temperate continental climate). The developed models can then be used to estimate future ET 0 with only air temperature forecasts, which can be readily obtained from public weather forecasts. The present study provides a new and promising strategy that can provide more accurate estimations of daily ET 0 with limited meteorological data, along with significant implications for enhancing atmospheric research. • We propose a novel HS-LSTM approach for improving daily ET 0 estimation. • The approach was applied in Northeast China with a temperate continental climate. • The proposed approach performed better than traditional machine learning approaches. • The developed models can accurately estimate daily ET 0 using only air temperature data. [ABSTRACT FROM AUTHOR]