%0 Journal Article
%A YOU  Yu-jun
%A BAI  Yun-gang
%A LU  Zhen-lin
%A ZHANG  Jiang-hui
%A CAO  Biao
%A LI  Wen-zhong
%A YU  Qi-ying
%T Medium- Long-Term Runoff Forecasting Using Interpretable Hybrid Machine Learning Model for Data-Scarce Regions
%D 2025
%R 10.11988/ckyyb.20240319
%J Journal of Changjiang River Scientific Research Institute
%P 52-59
%V 42
%N 7
%X <p id="p00005"><strong>[Objectives]</strong> This study aims to analyze the applicability of existing precipitation, temperature, and runoff data in data-scarce regions, and to develop and evaluate a deep learning hybrid model driven by multi-source information for improving the accuracy of monthly runoff forecasting. <strong>[Methods]</strong> Based on historical precipitation, temperature, and runoff sequences from the Yulongkashi River, a Convolutional Neural Network-Bidirectional Gated Recurrent Unit-Attention (CNN-BiGRU-Attention) model was developed. An Improved Particle Swarm Optimization (IPSO) algorithm was used to optimize this model, forming the IPSO-CNN-BiGRU-Attention hybrid model. The performance of this model was compared with that of the Gated Recurrent Unit (GRU) model and the ABCD water balance model. <strong>[Results]</strong> The IPSO-CNN-BiGRU-Attention model that incorporated precipitation and temperature data overall outperformed the CNN-BiGRU-Attention and GRU models, showing better agreement with the observed values. As the predication period increased, the proposed model achieved a root mean square error (RMSE) of 2.11 m<sup>3</sup>/s, a mean absolute error (MAE) of 1.32 m<sup>3</sup>/s, a mean absolute percentage error (MAPE) of 73.76%, and a Nash-Sutcliffe efficiency (NSE) coefficient of 0.94. The highest forecast accuracy was observed in the first three months. <strong>[Conclusions]</strong> The IPSO-CNN-BiGRU-Attention model effectively integrates precipitation, temperature, and runoff information, significantly enhancing the accuracy of monthly runoff forecasts in data-scarce regions. The model demonstrates robust performance across different forecast horizons, particularly suitable for short-term predictions of 1-3 months. This approach offers a practical and reliable tool for hydrological forecasting and flood control/drought management in data-scarce basins.</p>
%U http://ckyyb.crsri.cn/EN/10.11988/ckyyb.20240319