Groundwater Level Prediction by Wavelet Deep Learning with Smart Pumping Data

Tsai-Ning Weng, Ray-Shyan Wu, Tzu-Han Weng, Yi-Ho Chen, Tsai-Chun Lai, Jui-Yun Hsieh, Chu-Chun Hsu and Yuan-Chien Lin ()
Additional contact information
Tsai-Ning Weng: National Central University
Ray-Shyan Wu: National Central University
Tzu-Han Weng: National Central University
Yi-Ho Chen: National Central University
Tsai-Chun Lai: National Central University
Jui-Yun Hsieh: National Central University
Chu-Chun Hsu: National Central University
Yuan-Chien Lin: National Central University

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), 2025, vol. 39, issue 6, No 14, 2717-2742

Abstract: Abstract Groundwater is a relatively stable water resource and vital for human existence and economic development. Therefore, properly utilizing groundwater becomes very important when faced with water shortages. However, it is difficult to obtain information about the pumping amount, which has crucial impact on the groundwater hydrological cycle. Most studies use monthly groundwater data and previous time steps of groundwater information to model and predict without considering pumping information. Therefore, this study proposes a wavelet-deep learning model, combining wavelet analysis and deep learning, using the Daliao area of Kaohsiung, Taiwan as an example, which has considerable historical data from a smart groundwater real-time IoT pumping meter system to monitor pumping quantities for the main wells. We extracted relevant features from hourly observation data from 23 August 2017 through 30 January 2020, and investigated each factor’s features relative to groundwater level by wavelet transform, and then used recurrent neural networks (RNN) and long short-term memory (LSTM) deep learning models to summarize and predict multiple factor impacts on groundwater level under different time lags. Hourly prediction models of the LSTM and RNN achieved reliable cross validation performance with 0.81 and 0.78 coefficient of determination ( $${\text{R}}^{2}$$ ), respectively. Especially after the feature extraction by wavelet analysis and the addition of artificial groundwater pumping information, it will greatly increase the prediction accuracy. This study provides a feasible and accurate approach for groundwater level prediction, and hence will be an important reference for groundwater resources management and risk assessment, helping to achieve sustainable groundwater use.

Keywords: Groundwater prediction; Wavelet transform; Smart pumping system; Deep learning; IoT (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11269-024-04088-0 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:waterr:v:39:y:2025:i:6:d:10.1007_s11269-024-04088-0

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11269

DOI: 10.1007/s11269-024-04088-0

Access Statistics for this article

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) is currently edited by G. Tsakiris

More articles in Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) from Springer, European Water Resources Association (EWRA)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().