Effluent parameters prediction of a biological nutrient removal (BNR) process using different machine learning methods: A case study


Manav-Demir N., Gelgor H. B., ÖZ E., İLHAN F., Altuntaş K., Tiwary A., ...More

Journal of Environmental Management, vol.351, 2024 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 351
  • Publication Date: 2024
  • Doi Number: 10.1016/j.jenvman.2023.119899
  • Journal Name: Journal of Environmental Management
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, International Bibliography of Social Sciences, PASCAL, Aerospace Database, Agricultural & Environmental Science Database, Aqualine, Aquatic Science & Fisheries Abstracts (ASFA), BIOSIS, CAB Abstracts, Communication Abstracts, Environment Index, Geobase, Greenfile, Index Islamicus, Metadex, Pollution Abstracts, Public Affairs Index, Veterinary Science Database, Civil Engineering Abstracts
  • Keywords: Biological nutrient removal (BNR) process, Machine learning, Machine learning algorithms, Municipal wastewater treatment
  • Istanbul Technical University Affiliated: Yes

Abstract

This paper proposes a novel targeted blend of machine learning (ML) based approaches for controlling wastewater treatment plant (WWTP) operation by predicting distributions of key effluent parameters of a biological nutrient removal (BNR) process. Two years of data were collected from Plajyolu wastewater treatment plant in Kocaeli, Türkiye and the effluent parameters were predicted using six machine learning algorithms to compare their performances. Based on mean absolute percentage error (MAPE) metric only, support vector regression machine (SVRM) with linear kernel method showed a good agreement for COD and BOD5, with the MAPE values of about 9% and 0.9%, respectively. Random Forest (RF) and EXtreme Gradient Boosting (XGBoost) regression were found to be the best algorithms for TN and TP effluent parameters, with the MAPE values of about 34% and 27%, respectively. Further, when the results were evaluated together according to all the performance metrics, RF, SVRM (with both linear kernel and RBF kernel), and Hybrid Regression algorithms generally made more successful predictions than Light GBM and XGBoost algorithms for all the parameters. Through this case study we demonstrated selective application of ML algorithms can be used to predict different effluent parameters more effectively. Wider implementation of this approach can potentially reduce the resource demands for active monitoring the environmental performance of WWTPs.