Akademik Veri Yönetim Sistemi
Frontiers in Earth Science, cilt.13, 2025 (SCI-Expanded)
This study predicted daily-scale drought for the Fenhe River (FHR) Basin and applied the explainable artificial intelligence (XAI) method to the model’s prediction results. Daily-scale drought prediction can provide more timely and detailed drought information, while deep learning interpretable methods can help understand the impact of different predictors on droughts and improve the credibility of the model. The standardized antecedent precipitation evapotranspiration index (SAPEI) was selected as an index for evaluating drought conditions. Five classical deep learning prediction models, namely, long short-term memory (LSTM), gated recurrent unit (GRU), bidirectional long short-term memory (biLSTM) networks, transformer (TFR), and informer (IFR), were applied in the experiment, and the performance of each model was comprehensively evaluated. The results of the test set show that all models make effective predictions of droughts in the FHR Basin, with a Pearson correlation coefficient (R) higher than 0.75. BiLSTM performs better in short-term prediction, while TFR and IFR are better at long-term prediction. The results of the deep learning interpretable model show that, aside from the strong influence of the SAPEI itself in the prediction process, the mean temperature (TM) has the greatest influence among the auxiliary predictors, followed by precipitation (PRE) and relative humidity (RHU), with potential evapotranspiration (PET) being the weakest. Our work emphasizes the importance of timely warnings of drought and the role of XAI in the development of artificial intelligence.