基于改进麻雀搜索算法的黄河花园口日径流预测研究  

Prediction of Daily Runoff in Huayuan Estuary of Yellow River Based on Improved Sparrow Search Algorithm

作　　者：张兆卫 王娜[1] ZHANG Zhaowei;WANG Na(College of Information Engineering,Xizang Minzu University,Xianyang Shanxi 712082,China)

机构地区：[1]西藏民族大学信息工程学院,陕西咸阳712082

出　　处：《甘肃科技纵横》2024年第2期30-38,共9页Scientific & Technical Information of Gansu

摘　　要：为准确预测河南省内黄河径流量,减少黄河泛滥隐患,帮助防洪工作开展。文章提出以改进麻雀搜索算法(ISSA)为基础的EMD-ISSA-LSTM径流预测模型。选取花园口水文站2009—2022年日径流数据作为实验数据,均方误差(MSE)、平均绝对百分比误差(MAPE)和纳什效率系数(NSE)作为模型评价指标。实验结果表明:EMDISSA-LSTM模型在花园口日径流预测中具有较好的准确性和稳定性,其中,预见期为1 d时NSE达到0.965。该研究为花园口水文站日径流预测工作提供了有效的工具,有利于水资源优化管理和水库的防洪调度。In order to accurately predict the runoff of the Yellow River in Henan Province,reduce the hidden danger of the Yellow River flooding,and help the flood prevention work.In this paper,this article proposes an EMD-ISA-LSTM runoff prediction model based on improving the Sparrow Search algorithm(ISSA).The daily run⁃off data of Huayuankou Hydrology Station from 2009 to 2022 were selected as experimental data,and the mean square error(MSE),mean absolute percentage error(MAPE)and Nash efficiency coefficient(NSE)were used as model evaluation indexes.The experimental results show that the EMD-ISA-LSTM model has good accuracy and stability in the daily runoff prediction of Huayuankou,among them,when the prediction period is 1 day,the NSE reaches 0.965.This study provides an effective tool for the daily runoff prediction of Huayuankou hydrology station,which is conducive to the management of water resources optimization and the flood control scheduling in reservoirs.

关 键 词：LSTM神经网络 经验模态分解 麻雀搜索算法 日径流预测 花园口水文站 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]