Predicting future evapotranspiration based on remote sensing and deep learning

The watersheds of the four flux sites in the United States were selected as the study areas for this research. This study validates the efficiency of Convolutional Long Short-Term Memory Network (ConvLSTM) models for site-scale ET a prediction. We enhanced the ConvLSTM model by adding a Spatial Pyramid Pooling module (SPPM) and a Multi-head Self-Attention Module (MSA-Module), creating the Multi-head Self-Attention ConvLSTM (MSA-ConvLSTM) model, which we applied to predicting regional-scale actual evapotranspiration ( ET a ). This study aims to investigate whether the MSA-ConvLSTM model can enhance the accuracy of predicting regional-scale ET a , considering multiple feature variables. Furthermore, we evaluated different performance indicators, discussed possible reasons for errors in regional ET a prediction, and conducted sensitivity analysis of the model characteristics. The MSA-ConvLSTM model accurately predicts the future state of ET a . The average R 2 was 0.81, which is 11.6 % and 5.5 % higher than those of the ConvLSTM and Self-Attention ConvLSTM (SA-ConvLSTM) models, respectively. The average RMSE is 11.94 mm/m, which is 21.5 % and 13.7 % lower than ConvLSTM and SA-ConvLSTM, respectively. The average MAE is 9.46 mm/m, which is 21.3 % and 13 % lower than ConvLSTM and SA-ConvLSTM, respectively. Incorporating of a multi-head self-attention module enhances the model’s capacity for comprehensive understanding of input data features. This improvement allows the model to better adapt to feature relationships at varying scales and angles, enhancing its representational capacity and enabling effective adaptation to complex environmental changes. • Validation of the efficiency of ConvLSTM site-scale ET a prediction. • MSA-ConvLSTM was developed by incorporating the multi-head self-attention mechanism. • Validation of the efficiency of the MSA-ConvLSTM for regional-scale ET a prediction. • Limitations of factors influencing regional-scale ET a predictions are discussed.