A hybrid deep learning algorithm and its application to streamflow prediction

Abstract Process-based streamflow prediction is subjected to large uncertainties in model parameters and parameterizations related to the complex processes involved in streamflow generation. The data-driven models offer efficient alternatives without considering the physical processes, but their applications are limited by non-stationarity existing in observations. In this study, we propose a hybrid model, namely the DIFF-FFNN-LSTM model, to predict hourly streamflow. The model comprises three components, namely the first-order difference (DIFF), feedforward neural network (FFNN), and long short-term memory network (LSTM). When applied to the Andun basin of China, the proposed DIFF-FFNN-LSTM model performs very well in hourly streamflow prediction, with a RMSE of 9.31 m3/s with average streamflow rate of 54 m3/s and a MAE of 3.63 m3/s for all the flood events in the testing period. The comparison with five other machine learning models (of similar complexity or model structure) and four statistical models show superiority of our proposed DIFF-FFNN-LSTM model. The Shapley Additive exPlanations was used to quantify the contribution of each model input to the prediction skill. Streamflow at the previous hour was identified as the most important input, and streamflow generally contribute more than precipitation. Inputs closer to the prediction time do not necessarily have a greater impact on the model prediction. The study highlights the power of the combining of different data-driven methods and the promising prospect of our hybrid model in hydrological predictions.