AI-Driven Wastewater Management Through Comparative Analysis of Feature Selection Techniques and Predictive Models

dc.authorscopusid59996284900
dc.authorscopusid57189894503
dc.authorscopusid57275295200
dc.authorscopusid57215599346
dc.authorscopusid57791962400
dc.authorscopusid56780249800
dc.authorscopusid57194975731
dc.authorwosidNWI-4014-2025
dc.authorwosidGWD-1541-2022
dc.authorwosidODL-4954-2025
dc.authorwosidFWU-2100-2022
dc.authorwosidAAY-5207-2020
dc.authorwosidITV-2441-2023
dc.authorwosidABW-9013-2022
dc.contributor.authorDikmen, Faruk
dc.contributor.authorDemir, Ahmet
dc.contributor.authorOzkaya, Bestami
dc.contributor.authorRaza, Muhammad Owais
dc.contributor.authorRasheed, Jawad
dc.contributor.authorAşuroğlu, Tunç
dc.contributor.authorAlsubai, Shtwai
dc.contributor.authorRasheed, Jawad
dc.contributor.department-temp
dc.date.accessioned2025-11-29T16:31:21Z
dc.date.available2025-11-29T16:31:21Z
dc.date.issued2025
dc.departmentMühendislik ve Doğa Bilimleri Fakültesi
dc.description.abstractThe integration of artificial intelligence (AI) in wastewater treatment management offers a promising approach to optimizing effluent quality predictions and enhancing operational efficiency. This study evaluates the performance of machine learning models in predicting key wastewater effluent parameters Chemical Oxygen Demand (COD), Biochemical Oxygen Demand (BOD), Total Suspended Solids (TSS), Total Effluent Nitrogen and Total Effluent Phosphorus. Three feature selection techniques were applied: SelectKBest, Mutual Information, and Recursive Feature Elimination (RFE) using Random Forest to identify the most significant predictors. The study leveraged ensemble learning models, including XGBoost, Random Forest, Gradient Boosting, and LightGBM, and compared them with Decision Tree models. The results demonstrate that effluent volatile suspended solids (VSS) consistently held the highest predictive importance across all feature selection methods. Ensemble models significantly outperformed Decision Trees, with Gradient Boosting achieving the best predictive accuracy for TSS and total nitrogen (Mean Absolute Error (MAE): 3.667 : 97.53), XGBoost excelling in COD prediction with MAE and of 6.251 and 83. 41%, respectively, and XGBoost showing superior performance for BOD (MAE: 1.589 :79.64%). LightGBM yielded the highest precision in predicting total phosphate with MAE and a score of 0.230 and 28. 68%, respectively. Decision tree models consistently underperformed, exhibiting the highest error rates. These findings highlight the potential of AI-driven approaches in wastewater management to improve decision-making, regulatory compliance, and resource efficiency. However, limitations such as operational irregularities and seasonal variations remain challenges for further refinement.
dc.identifier.citationDikmen, F., Demir, A., Özkaya, B., et al. (2025). AI-driven wastewater management through comparative analysis of feature selection techniques and predictive models. Scientific Reports, 15, Article 25347. https://doi.org/10.1038/s41598-025-07124-0
dc.identifier.doi10.1038/s41598-025-07124-0
dc.identifier.endpage15
dc.identifier.issn2045-2322
dc.identifier.issue1
dc.identifier.orcid0000-0003-3761-1641
dc.identifier.scopus2-s2.0-105010639787
dc.identifier.startpage1
dc.identifier.urihttps://doi.org/10.1038/s41598-025-07124-0
dc.identifier.urihttps://hdl.handle.net/20.500.12436/8488
dc.identifier.volume15
dc.identifier.wos001529143400029
dc.identifier.wosqualityQ1
dc.indekslendigikaynakScopus
dc.institutionauthorRaza, Muhammad Owais
dc.institutionauthorRasheed, Jawad
dc.language.isoen
dc.publisherNature Research
dc.relation.ispartofScientific Reports
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - İdari Personel ve Öğrenci
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectArtificial intelligence
dc.subjectEnvironmental engineering
dc.subjectFeature selection
dc.subjectMachine learning
dc.subjectWaste water treatment plan
dc.titleAI-Driven Wastewater Management Through Comparative Analysis of Feature Selection Techniques and Predictive Models
dc.typeArticle
dspace.entity.typePublication
relation.isAuthorOfPublicationf9b9b46c-d923-42d3-b413-dd851c2e913a
relation.isAuthorOfPublication.latestForDiscoveryf9b9b46c-d923-42d3-b413-dd851c2e913a

Dosyalar

Orijinal paket

Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
s41598-025-07124-0 (1).pdf
Boyut:
2.42 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Makale dosyası / Article file

Lisans paketi

Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama: