Multi-Step-Ahead Monthly Streamflow Forecasting Using Convolutional Neural Networks

Many hydrological applications related to water resource planning and management primarily rely on a succession of streamflow forecasts with extensive lead times. In this study, two innovative models, termed as DirCNN and DRCNN, are proposed for multi-step-ahead (MSA) monthly streamflow forecasting based on the direct (Dir) and direct-recursive (DR) strategies and using the convolutional neural network (CNN) to automatically extract input variables. Compared to traditional MSA forecasting models, DirCNN and DRCNN can automatically extract input variables and predict streamflow for multiple lead times simultaneously. Xiangjiaba Hydropower Station, Huanren Reservoir, and Fengman Reservoir in China were included as case studies, and three artificial neural networks based models are used as comparative models. The most important results are highlighted below. First, the proposed DirCNN and DRCNN exhibit comparable prediction performances but outperform the comparison models. Second, with the increase in lead time, DirCNN and DRCNN demonstrate good consistency in forecasting accuracy. Third, the stacking order of candidate sequences has little effect on the DirCNN and DRCNN forecasting accuracy. These results suggest that DirCNN and DRCNN could be ahead of MSA monthly streamflow forecasting and thus would be helpful in the judicious use of water resources.