基于VMD-PSO-LSSVM的降雨量预测研究
Research on Rainfall Prediction Based on VMD-PSO-LSSVM
申杨 1王文波1
作者信息
- 1. 武汉科技大学理学院 武汉 430065
- 折叠
摘要
降雨事件具有高度随机性,为了对复杂的降雨量进行科学有效地预测,提出VMD-PSO-LSSVM的降雨量预测模型.首先利用VMD方法分解原始降雨量序列;然后运用粒子群算法优化最小二乘支持向量机的关键参数,使用精准构建的预测模型对一系列子序列进行预测;最后合成所有的预测子序列,获得最终预测结果.仿真结果表明,VMD-PSO-LSSVM模型预测结果误差更小,准确度更高,可以成为有效的降雨量预测工具,为农业和水利部门制定水资源管理决策提供参考,降低旱涝灾害的风险.
Abstract
Rainfall events are highly random.In order to scientifically and effectively predict complex rainfall,a rainfall pre-diction model based on VMD-PSO-LSSVM is proposed.Firstly,VMD method is used to decompose the original rainfall series.Then,particle swarm optimization is used to optimize the key parameters of least squares support vector machine,and a series of subsequences are predicted by accurately constructed prediction model.Finally,all prediction subsequences are synthesized to ob-tain the final prediction results.The simulation results show that the prediction results of VMD-PSO-LSSVM model have less error and higher accuracy.It can become an effective rainfall prediction tool,provide reference for agriculture and water conservancy de-partments to make water resources management decisions,and reduce the risk of drought and flood disasters.
关键词
变分模态分解/粒子群算法/最小二乘支持向量机/降雨量Key words
variational modal decomposition/particle swarm optimization/least squares support vector machine/rainfall引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据