Application of Combined Multiple Linear Regression Model in Runoff Prediction
In order to improve the hydrological prediction accuracy,a shuffled frog leaping algorithm (SFLA)-combined multiple linear regression (CMLR) runoff prediction model is proposed.This paper first builds a CMLR model based on principal component analysis (PCA) data with and without dimensionality reduc...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Pearl River
2021-01-01
|
| Series: | Renmin Zhujiang |
| Subjects: | |
| Online Access: | http://www.renminzhujiang.cn/thesisDetails#10.3969/j.issn.1001-9235.2021.07.007 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In order to improve the hydrological prediction accuracy,a shuffled frog leaping algorithm (SFLA)-combined multiple linear regression (CMLR) runoff prediction model is proposed.This paper first builds a CMLR model based on principal component analysis (PCA) data with and without dimensionality reduction;then optimizes the CMLR constant term,partial regression coefficient and combined weight coefficient by the SFLA to establish a SFLA-CMLR runoff prediction model;finally apply the SFLA-CMLR model on two examples of annual runoff prediction,and establishes the SFLA-PCA-MLR,SFLA-PCA-SVM (support vector machine),(least squares) LS-PCA-MLR,PCA-SVM,with dimensionality reduction of PCA,as well as SFLA-MLR,SFLA-SVM,LS-MLR,SVM,without dimensionality reduction as comparative prediction models.The results show that the average relative error of the SFLA-CMLR model for the annual runoff prediction of the two examples is 1.54% and 4.63%,respectively,and the prediction accuracy is better than that of SFLA-PCA-MLR and other 8 models.Therefore,it has better prediction accuracy and generalization ability. |
|---|---|
| ISSN: | 1001-9235 |