Multi-step-ahead forecasting of daily reference evapotranspiration using hybrid deep learning models for the Taklamakan Desert oasis

Study region

This research focuses on the Taklamakan Desert oasis in southern Xinjiang, China, which represents one of the most hydrologically challenging and climatically extreme agricultural regions in the world.

Study focus

In this study, we address the short-term forecasting of daily reference evapotranspiration (ET₀) using six advanced hybrid deep learning models—LSTM, BiLSTM, CNN-LSTM, CNN-BiLSTM, CNN-LSTM-Attention, and CNN-BiLSTM-Attention. Historical daily meteorological data collected from 25 stations were utilized, with records from 1991 to 2020 used for model training and data from 2021 to 2023 reserved exclusively for independent testing. Forecasts were produced for 1-, 3-, and 5-day lead times. Model performance was evaluated using the Global Performance Index (GPI), and interpretability was further enhanced by applying Shapley Additive Explanations (SHAP) to analyze feature contributions under different climatic conditions.

New hydrological insight for the region

BiLSTM-based models demonstrated higher ET₀ forecasting accuracy than long short-term memory networks (LSTM)-based models, while the incorporation of convolutional neural networks (CNN) and attention mechanisms further improved forecasting performance. The CNN-BiLSTM-Attention model consistently exhibited the highest accuracy and robustness across different stations and forecast horizons, making it the most suitable for operational deployment in desert oasis regions. SHAP analysis indicated that temperature and solar radiation are the principal drivers of ET₀ at most stations, highlighting the spatial heterogeneity in feature importance. Thus, this study provides robust and interpretable ET₀ forecasting models along with new hydrological insights, offering practical support for localized water resource management and enhancing confidence in the deployment of precision irrigation models in hyper-arid agricultural systems.