北京地区主要河道洪水及输沙量预报研究  

Flood and Sediment Transport Prediction in Major River Channels of Beijing Area

作　　者：杨峰 YANG Feng(Beijing Jinhe Water Construction Group Co.,Ltd.,Beijing 102206,China)

机构地区：[1]北京金河水务建设集团有限公司,北京102206

出　　处：《中国水能及电气化》2024年第7期28-32,共5页China Water Power & Electrification

摘　　要：为构建北京地区主要河道洪水和输沙量的预测模型,文章基于白河、北运河、拒马河3条河道的长序列实测径流及输沙量数据,以双向长短期记忆神经网络模型(BiLSTM)为基础,分别采用羊群优化算法(SFMO)、鸽群优化算法(PIO)、灰狼优化算法(GWO),构建河道水沙含量最优估算模型,结果表明:SFMO-BiLSTM模型在所有模型中精度最高,可推荐用于估算河道水沙量。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.

关 键 词：河道水沙量 双向长短期记忆神经网络 羊群优化算法 

分 类 号：P333.4[天文地球—水文科学]