Water Quality Prediction in Urban Waterways Based on Wavelet Packet Denoising and LSTM

Jiafeng Pang, Wei Luo (), Zeyu Yao, Jing Chen, Chunyu Dong and Kairong Lin ()
Additional contact information
Jiafeng Pang: Sun Yat-Sen University
Wei Luo: Sun Yat-Sen University
Zeyu Yao: Sun Yat-Sen University
Jing Chen: Guangzhou Feng Ze-Yuan Water Conservancy Technology Co., Ltd
Chunyu Dong: Sun Yat-Sen University
Kairong Lin: Sun Yat-Sen University

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), 2024, vol. 38, issue 7, No 8, 2399-2420

Abstract: Abstract The prediction of water quality in urban rivers plays a crucial role in supporting water environment management. This study collected real-time water quality monitoring data from four stations in the Fenjiang River Basin of Foshan City, spanning from 2016 to 2021. Then the Wavelet Packet Denoising (WPD) technique was applied to reduce noise interference in historical monitoring data. Subsequently, a single-factor water quality prediction model was developed, which is based on Long Short-Term Memory (LSTM), focusing on chemical oxygen demand (COD) and ammonia nitrogen (NH3-N). The results of this study demonstrate that the integration of WPD with LSTM, referred to as WPD-LSTM, outperformed conventional LSTM models in terms of predictive accuracy. Notably, the WPD-LSTM model exhibited superior performance in predicting the impact of COD and NH3-N on water quality in the Fenjiang River, surpassing the traditional LSTM model over a prediction period of 12 h and 3 days. In the 12-h prediction, the RMSE values of NH3-N predictions in the four monitoring sections decreased by 55% to 67%, and the RMSE values of COD predictions decreased by 18% to 51%.. In the 3-day prediction, the RMSE values of NH3-N predictions in the four monitoring sections decreased by 40% to 83%, and the RMSE values of COD predictions decreased by 50% to 69%. By employing the WPD-LSTM method, this study contributes to improving the precision of water quality prediction, thereby providing valuable insights for effective water environment management in urban river systems.

Keywords: Water quality prediction; Wavelet denoising; Long short-term memory; Water environment treatment (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11269-024-03774-3 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:38:y:2024:i:7:d:10.1007_s11269-024-03774-3

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

DOI: 10.1007/s11269-024-03774-3

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 ().