Quantifying the mitigation potential of energy and chemical consumption for a full-scale wastewater treatment plant with deep learning methods

Chenyang Yu, Runyao Huang, Jie Yu, Shike Zhang, Sitian Jin, Qianrong Xu, Jing Zhang, Zisheng Ai, Jacek Mąkinia and Hongtao Wang

Applied Energy, 2025, vol. 394, issue C, No S0306261925008530

Abstract: Wastewater treatment plants (WWTPs) play an essential role in urban water system, assisting in realizing urbanization and sustainable development. They consume large amounts of energy and chemicals to remove the wastewater pollutants each year around the world, highlighting an urgent need to explore and discover the energy and chemical saving potential of WWTPs. Recently, deep learning model has attracted increasing attention in various research fields. This study evaluated an Attention optimized bidirectional Gated recurrent unit Long short-term memory (ABGL) model against several benchmark deep learning models. Comparative analysis revealed that while ABGL demonstrates superior performance, the optimal model selection should be carefully evaluated based on data accuracy and computational complexity. Among these models, ABGL showed best accuracy and feasibility for the ability of predicting energy and chemical consumption. The results of the model predictions showed that energy saving and chemical saving of studied WWTP could be as high as 9.21 % and 18.78 %, respectively. Accordingly, the energy intensity of the WWTP should be controlled below 0.28 kWh/m3 and the chemical intensity be controlled below 0.09 kg/m3. Implementation of the deep learning model such as ABGL will assist the decision-makers of WWTPs in optimizing the input efficiency, setting a novel paradigm that guides the smart operations of the whole sector by the state-of-the-art DNN model.

Keywords: Wastewater treatment; Deep neural networks; Energy saving; Chemical conservation; Smart operations (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261925008530
Full text for ScienceDirect subscribers only

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:eee:appene:v:394:y:2025:i:c:s0306261925008530

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2025.126123

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().