Monthly Streamflow Forecasting Using Convolutional Neural Network

Monthly streamflow forecasting is vital for managing water resources. Recently, numerous studies have explored and evidenced the potential of artificial intelligence (AI) models in hydrological forecasting. In this study, feasibility convolutional neural network (CNN), a deep learning method, monthly CNN can automatically extract critical features from inputs with its convolution–pooling mechanism, which distinct advantage compared other AI models. Hydrological large-scale atmospheric circulation variables, including rainfall, streamflow, factors are used to establish forecast Huanren Reservoir Xiangjiaba Hydropower Station, China. The (ANN) extreme machine (ELM) identified based on cross-correlation mutual information analyses established comparative analyses. performances these assessed several statistical metrics graphical evaluation methods. results show that outperforms ANN ELM all measures. Moreover, shows better stability accuracy.