Research on Water Demand Prediction in the Yangtze Valley Based on the STL-LSTM Model

DOI

10.2991/978-94-6463-658-1_56How to use a DOI?

Keywords

water demand prediction; LSTM; STL time series decomposition; Yangtze valley

Abstract

Hydraulic engineering involves the utilization of water for various purposes, such as water supply, irrigation and power generation. The efficient utilization and scientific management of water resources constitute an essential research subject. Within the realm of water resources management, accurate water demand prediction is of paramount significance for guaranteeing the sustainable utilization of water resources and fulfilling the water requirements of human society. In order to accurately predict the short-term water demand of the Yangtze valley and support for water resource management and allocation, this paper combines the Long Short Term Memory (LSTM) model and Time Series Decomposition (STL) to construct the STL-LSTM water demand prediction model. The study takes the large-scale water users in the main stream of the Yangtze River as an example to predict water demand. LSTM and ARIMA are used as comparative models, and Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) are used to evaluate the accuracy of the model prediction. The results show that compared with LSTM and ARIMA models, STL-LSTM model can better predict water demand trends, and the MAPE of prediction is reduced by 0.94% and 0.85% respectively, with higher prediction accuracy. STL-LSTM model can be applied to water demand prediction in the Yangtze valley.

Copyright

© 2025 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  - Sheng-Lin Ke
AU  - Jun Zhang
AU  - Dang-Gen Guan
AU  - De-Jing Zeng
AU  - Hong-Ya Qiu
AU  - Zhi-Zhou Feng
AU  - Shu-Fei Li
AU  - Yu Hui
PY  - 2025
DA  - 2025/03/03
TI  - Research on Water Demand Prediction in the Yangtze Valley Based on the STL-LSTM Model
BT  - Proceedings of the 2024 10th International Conference on Architectural, Civil and Hydraulic Engineering (ICACHE 2024)
PB  - Atlantis Press
SP  - 557
EP  - 565
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-658-1_56
DO  - 10.2991/978-94-6463-658-1_56
ID  - Ke2025
ER  -