Application of a hybrid deep learning approach with attention mechanism for evapotranspiration prediction: a case study from the Mount Tai region, China

Evapotranspiration is one of the most critical features in hydrology. In order to address the prediction of evapotranspiration accurately and scientifically, this study proposes a novel deep learning-based evapotranspiration prediction model, the CNN-BiLSTM-Attention model, using the climatically complex Mount Tai region in China as a case study. The model integrates the feature extraction capabilities of Convolutional Neural Networks (CNN), the temporal dependency capturing of Bidirectional Long Short-Term Memory Networks (BiLSTM), and the feature weighting abilities of the Attention mechanism. In order to enhance prediction accuracy with fewer climate parameters, various input parameter combinations are explored and compared with other classical models in this study. The model's performance is assessed across daily, weekly, and monthly time increments, using evaluation metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R 2 ). This study holds significant implications for mountain hydrological cycles, as accurate evapotranspiration prediction aids in more informed decision-making for agricultural production, water resource management, and climate change research.