Flood and Sediment Transport Prediction in Major River Channels of Beijing Area
In order to construct a prediction model for flood and sediment transport of major river channels of Beijing area,this paper uses long-term measured runoff and sediment data from the Baihe River,North Canal,and Juma rivers.Based on a Bidirectional Long Short-Term Memory(BiLSTM)neural network model,the paper employs the Sheep Flock Movement Optimization algorithm(SFMO),the Pigeon-Inspired Optimization algorithm(PIO),and the Grey Wolf Optimizer(GWO)to build an optimal estimation model for river water and sediment content.The results indicate that the SFMO-BiLSTM model has the highest accuracy among all models and is recommended for estimating river water and sediment volume.
river water and sediment volumeBidirectional Long Short-Term Memory neural networkSheep Flock Movement Optimization algorithm
NETL
NSTL
万方数据
