Comparative Study on Time Series Feature Decomposition of Water Resources System Based on MLR and Wavelet Decomposition

DOI

10.2991/978-94-6239-600-5_3How to use a DOI?

Keywords

Water resource coupling system; Wavelet decomposition; Time series decomposition; Multiple Linear Regression Model (MLR)

Abstract

As a complex dynamic composite system, the accurate prediction of water resource coupling systems is key to the scientific management and sustainable utilization of water resources. Traditional modeling methods based on raw undecomposed data have limitations in mining deep patterns and latent patterns in the system, and research on time series decomposition of water resource systems is still insufficient. This study innovatively combines wavelet decomposition with time series decomposition, introduces a multiple linear regression (MLR) model, and considers the upstream data of the Yangtze River Basin from 1998 to 2017 as the research object. Through three error indicators, R², MAE, and RMSE, the performance differences of the models between undecomposed data and jointly decomposed data in predicting water resource coupling systems were systematically compared and analyzed. The research results indicate that the joint decomposition technique significantly enhances the model’s ability to capture complex data and significantly improves the prediction accuracy. Taking the effective head variable as an example, after joint decomposition, the R² of the validation set increased from 0.56 to 0.76, and both MAE and RMSE indicators were significantly optimized. This study provides a new technological path for predicting water resource systems, which has important theoretical significance and practical value for the scientific management and decision support of water resources.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jun Guo
AU  - Jiahao Lu
AU  - Zhongzheng He
AU  - Chen Ji
AU  - Jiawei Chen
PY  - 2026
DA  - 2026/02/26
TI  - Comparative Study on Time Series Feature Decomposition of Water Resources System Based on MLR and Wavelet Decomposition
BT  - Proceedings of the 2025 8th International Conference on Civil Architecture, Hydropower and Engineering Management (CAHEM 2025)
PB  - Atlantis Press
SP  - 13
EP  - 21
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-600-5_3
DO  - 10.2991/978-94-6239-600-5_3
ID  - Guo2026
ER  -