Variation of dominant discharge along the riverbed based on numerical and deep-learning models: A case study in the Middle Huaihe River, China

River morphology plays an important role in water environment and resources. The dominant discharge (QD) is a crucial indicator for understanding river morphology and bed evolution under the impact of various interacting processes. At present, the identification of QD mainly depends on the analysis of a large number of hydrological data derived from measuring stations, leading to difficulty in obtaining detailed QD distributions along the study reach. In this paper, QD is approximately expressed as the bed-steadying discharge (QS) which is based on major factors of water level and sediment-carrying capacity. Subsequently, an integrated model combining a numerical fluid-flow and sediment model with a deep-learning algorithm is applied to analyze the changing process of the QS. The flow and sediment transport processes are simulated by the calibrated mathematical model, which are then adopted as the input sequences for the long short-term memory (LSTM) module. The verification results of the established LSTM model show robustness and accuracy in predicting the flow and sediment transport processes under multi-stage incoming flow and sediment conditions. Furthermore, the proposed integrated model is applied to identify the detailed process of QS in the Middle Huaihe River. Results show that the changing process of QS along the study reach is characterized by a particular trend of "increase-decrease-rapid increase" due to natural changes and human activities. Additionally, the QS agrees well with QD at the hydrological station, showing that QS can be applied as an approximation for QD along the study reach. By analyzing longitudinal and transverse profiles, the rationality of using QS as obtained by the newly presented model is demonstrated. Its temporal variation is also consistent with the cross-sectional changes for the specified stations.