基于EEMD-SVM-ELM模型的月降水量预测研究
Monthly Precipitation Prediction Based on EEMD-SVM-ELM Model
李明 1刘东岳 1赵良伟 1蒋一波2
作者信息
- 1. 河海大学 商学院,江苏 南京 211100;河海大学 项目管理信息化研究所,江苏 南京 211100
- 2. 江苏淮阴水利建设有限公司,江苏 淮安 223005
- 折叠
摘要
针对地表降水量数据的非线性、非平稳特征,首先利用 EEMD 对月降水量初始数据进行分解,再利用Lempel-Ziv复杂度算法将分量划分为高频及低频分量,使用粒子群算法(PSO)优化基学习器参数,最终构建EEMD-SVR-ELM月降水量预测模型,并采用该模型对长江下游部分城市的月降水量实际数据进行预测.结果表明,该模型的综合性能最优,具有更高的精确度.相较于单一模型,在MMAE、RRMSE、MMAPE 指标上分别降低了 37.4%、41.4%、42.5%,DM检验表明该模型显著优于其他模型,说明该模型可作为月降水量预测的一种有效新方法.
Abstract
Aiming at the nonlinearity and non-stationary characteristics of surface precipitation data,a support vector regression(SVR)and extreme learning machine(ELM)are constructed as base learners.Firstly,the initial monthly pre-cipitation data is decomposed based on Empirical Mode Decomposition(EEMD).Then the Lempel-Ziv complexity algo-rithm is used to divide the components into high-frequency and low-frequency components.The parameters of the base learner are optimized by particle swarm optimization(PSO).Finally,the EEMD-SVR-ELM monthly precipitation predic-tion model was constructed.Compared with other models,the model has the best comprehensive performance,higher ac-curacy and generalization.Especially compared with the single model,the MMAE,RRMSE,and MMAPE indicators were re-duced by 37.4%,41.4%and 42.5%.The DM test showed that this model was significantly better than other models.This model can be used as an effective new method for monthly precipitation prediction.
关键词
月降水量预测/经验模态分解/极限学习机/支持向量回归Key words
monthly precipitation forecast/EEMD/ELM/SVR引用本文复制引用
基金项目
国家社会科学基金规划项目(17BGL156)
中央高校基本科研业务费专项河海大学项目(B220207039)
出版年
2024
NETL
NSTL
万方数据