EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Comparative analysis of supervised learning models for effluent quality prediction in wastewater treatment plants

Liu Bo-Qi iD, Zhou Ding-Jie, Zhao Yang, Shi Long-Yu

PLOS One · 10.06.2025 · 20 (6) · e0325234

DOI: 10.1371/journal.pone.0325234 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift PLOS One, online erschienen am 10.06.2025. Verfasst von Liu Bo-Qi und 3 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Regional and Urban Ecology, Institute of Urban Environment, Chinese Academy of Sciences, Xiamen, Fujian, China. Hauptthemen laut MEDLINE: Wastewater, Supervised Machine Learning, Water Purification, Waste Disposal, Fluid. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Programmes.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Effluent quality prediction is critical for optimizing Wastewater Treatment Plant (WWTP) operations, ensuring regulatory compliance, and promoting environmental sustainability. This study evaluates the performance of five supervised learning models—AdaBoost, Backpropagation Neural Networks (BP-NN), Support Vector Machine (SVR), XGBoost, and Gradient Boosting (GB)—using data from a WWTP in Zhuhai, China. The Effluent Quality Index (EQI), integrating multiple pollutant concentrations and environmental impacts, was used as the target variable. The models were trained and tested on 84 monthly datasets, with their performances compared using R 2 , Mean Absolute Percentage Error (MAPE), and Mean Bias Error (MBE). XGBoost achieved the best balance between accuracy and robustness, with the lowest MAPE(6.11%) and a high R 2 (0.813), while SVR excelled in fitting accuracy(R 2 = 0.826) but showed limitations in error control. Although we employed GridSearchCV with cross-validation to optimize hyperparameters and ensure a fair model comparison, the study is limited by the reliance on data from a single WWTP and the relatively small dataset size (84 records). Nevertheless, the findings provide valuable insights into selecting effective machine learning models for effluent quality prediction, supporting data-driven decision-making in wastewater management and advancing intelligent process optimization in WWTP.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

WastewaterSupervised Machine LearningWater PurificationWaste Disposal, FluidNeural Networks, ComputerChinaSupport Vector MachineWater QualityWater Pollutants, ChemicalEnvironmental Monitoring

Substanzen

WastewaterWater Pollutants, Chemical

Autor:innen und Institutionen

  • State Key Laboratory of Regional and Urban Ecology, Institute of Urban Environment, Chinese Academy of Sciences, Xiamen, Fujian, China.
  • Rural Revitalization College, Fujian Agriculture and Forestry University, Fuzhou, China.

ORCID-Profile: Liu Bo-Qi

Förderung

  • National Key Research and Development Programmes

Zitieren

APA

Bo-Qi, L., Ding-Jie, Z., Yang, Z., & Long-Yu, S. (2025). Comparative analysis of supervised learning models for effluent quality prediction in wastewater treatment plants. PLOS One, 20(6), e0325234. https://doi.org/10.1371/journal.pone.0325234

Vancouver

Bo-Qi L, Ding-Jie Z, Yang Z, Long-Yu S. Comparative analysis of supervised learning models for effluent quality prediction in wastewater treatment plants. PLOS One. 2025;20(6):e0325234. doi:10.1371/journal.pone.0325234

BibTeX
@article{BoQi2025,
  author = {Bo-Qi, Liu and Ding-Jie, Zhou and Yang, Zhao and Long-Yu, Shi},
  title = {Comparative analysis of supervised learning models for effluent quality prediction in wastewater treatment plants},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {6},
  pages = {e0325234},
  doi = {10.1371/journal.pone.0325234}
}
Kostenlos starten →