EUVIMEDEUVIMED entdecken
Crossref

Interpretable machine learning and rolling-origin validation identify two distinct control and predictability regimes in full-scale aerated lagoon performance

Ahmed Farghaly, Mahmoud Owais, Ahmed M A Sattar, Mahmoud Elhadidy

Journal of Environmental Management · 2026-07 · 413 · 130281

DOI: 10.1016/j.jenvman.2026.130281 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Environmental Management, 2026-07. Verfasst von Ahmed Farghaly und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Civil and Environmental Engineering, College of Engineering, Majmaah University, Al-Majmaah, 11952, Saudi Arabia; Engineering Research …. Hauptthemen laut MEDLINE: Machine Learning, Waste Disposal, Fluid. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: Majmaah University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study develops an interpretable machine learning-global sensitivity analysis (ML-GSA) framework to diagnose dominant process drivers in a 9-year dataset (2000-2008) from a full-scale aerated lagoon system (90,000 m3 d-1). XGBoost surrogate models were trained for six effluent indicators and coupled with bootstrap-resolved Sobol' analysis to generate uncertainty-bounded sensitivity rankings. Predictive performance was assessed under rolling-origin validation, which revealed two distinct predictability regimes: hydraulically governed outputs generalized forward in time (TSS R2 = 0.848 ± 0.05; BOD5 R2 = 0.449 ± 0.23), whereas maturation-pond outputs (pH, VSS, DO, fecal coliform) showed pronounced temporal non-stationarity, consistent with a 35% decadal increase in hydraulic loading. Sobol'-based attribution revealed a parallel two-regime control structure. Organic matter and solids removal were governed primarily by treatment stage with strong total effects (Sᵀ = 0.67 for BOD5; Sᵀ = 0.94 for TSS), confirming hydraulic configuration as the dominant operational lever. In contrast, maturation-pond behavior was dominated by seasonal and ecological attributions. Date was the largest variance-attributing variable for VSS, and a leading driver for pH and DO, while influent VSS dominated fecal-coliform variance (Sᵀ = 0.62) through particulate shielding. Date-decomposition experiment, in which Date was replaced by Year and harmonic day-of-year terms, showed that the original Date attribution contained both long-term operational drift and within-year seasonality. Sobol' Sᵀ rankings agreed strongly with SHAP and Shapley-effect estimates (ρ ≥ 0.79), supporting robustness under input dependence. Environmentally, effluent breached BOD5, TSS, and fecal-coliform limits in 41-87% of the record; seasonal maturation-pond disinfection was the binding constraint.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningWaste Disposal, FluidBoosting Machine Learning AlgorithmsPredictive Learning Models

Stichwörter der Autor:innen

Aerated lagoonGlobal sensitivity analysisInterpretable machine learningRolling-origin validationSeasonal forcingWastewater treatment

Autor:innen und Institutionen

  • Department of Civil and Environmental Engineering, College of Engineering, Majmaah University, Al-Majmaah, 11952, Saudi Arabia; Engineering Research and Applied Sciences Center, Majmaah University, Al-Majmaah, 11952, Sa…
  • Civil Engineering Department, Assiut University, Assiut, 71515, Egypt.
  • Department of Irrigation & Hydraulics, Cairo University, Cairo, 12613, Egypt.

Förderung

  • Majmaah University

Zitieren

APA

Farghaly, A., Owais, M., Sattar, A. M. A., & Elhadidy, M. (2026). Interpretable machine learning and rolling-origin validation identify two distinct control and predictability regimes in full-scale aerated lagoon performance. Journal of Environmental Management, 413, 130281. https://doi.org/10.1016/j.jenvman.2026.130281

Vancouver

Farghaly A, Owais M, Sattar AMA, Elhadidy M. Interpretable machine learning and rolling-origin validation identify two distinct control and predictability regimes in full-scale aerated lagoon performance. Journal of Environmental Management. 2026;413:130281. doi:10.1016/j.jenvman.2026.130281

BibTeX
@article{Farghaly2026,
  author = {Farghaly, Ahmed and Owais, Mahmoud and Sattar, Ahmed M A and Elhadidy, Mahmoud},
  title = {Interpretable machine learning and rolling-origin validation identify two distinct control and predictability regimes in full-scale aerated lagoon performance},
  journal = {Journal of Environmental Management},
  year = {2026},
  volume = {413},
  pages = {130281},
  doi = {10.1016/j.jenvman.2026.130281}
}
Kostenlos starten →