EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid computational fluid dynamics model for dissolved oxygen field prediction in a full-scale wastewater aeration basin

Petri Ukkonen iD, M Mulas iD, A Mikola iD

Water Science & Technology · 2026

DOI: 10.2166/wst.2026.310 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water Science & Technology, 2026. Verfasst von Petri Ukkonen und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Built Environment, Aalto University, Tietotie 1 E, Espoo 02150, Finland E-mail: petri.ukkonen@aalto.fi. Hauptthemen laut MEDLINE: Oxygen, Hydrodynamics, Wastewater, Models, Theoretical. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Maa- ja Vesitekniikan Tuki Ry.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graphical abstract showing that calibrated CFD of a full-scale 12.6 m aeration basin was converted into a deep-learning surrogate, reducing dissolved-oxygen prediction time from 1,856 s to 61–67 ms with 0.11–0.40 mg/L error. This study aimed to develop a fast surrogate model for spatial dissolved oxygen prediction in a deep, full-scale activated sludge aeration basin and to evaluate its suitability for operational use. A two-phase water-air computational fluid dynamics model was built in COMSOL Multiphysics 6.3 for a basin with a water depth of 12.6 m using a realizable k-epsilon turbulence model. A computational fluid dynamics-informed deep neural network was then trained on computational fluid dynamics-generated datasets using Bayesian hyperparameter optimization. Model performance was evaluated against measured dissolved oxygen data from two independent 24-hour field campaigns. Bootstrap analysis yielded 95% confidence intervals of 0.11–0.40 mg/L for the MAE and 6.0–17.7% for the normalized root mean square error. The surrogate reduced evaluation time from 1,856 seconds to 61–67 milliseconds, corresponding to an average speed-up of about 27,900-fold. These results indicate that the framework can provide real-time spatial dissolved oxygen estimates and show strong potential for plant-specific monitoring and aeration control support.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

OxygenHydrodynamicsWastewaterModels, TheoreticalWaste Disposal, FluidComputer SimulationNeural Networks, Computer

Stichwörter der Autor:innen

aerationcomputational fluid dynamicsdeep neural networkdissolved oxygenmachine learningsurrogate modelling

Substanzen

OxygenWastewater

Autor:innen und Institutionen

  • Department of Built Environment, Aalto University, Tietotie 1 E, Espoo 02150, Finland E-mail: petri.ukkonen@aalto.fi.
  • Department of Built Environment, Aalto University, Tietotie 1 E, Espoo 02150, Finland.
  • Department of Teleinformatics Engineering, Federal University of Ceará, Campus do Pici, Fortaleza, Brazil.

ORCID-Profile: Petri Ukkonen, M Mulas, A Mikola

Förderung

  • Maa- ja Vesitekniikan Tuki Ry

Zitieren

APA

Ukkonen, P., Mulas, M., & Mikola, A. (2026). Hybrid computational fluid dynamics model for dissolved oxygen field prediction in a full-scale wastewater aeration basin. Water Science & Technology. https://doi.org/10.2166/wst.2026.310

Vancouver

Ukkonen P, Mulas M, Mikola A. Hybrid computational fluid dynamics model for dissolved oxygen field prediction in a full-scale wastewater aeration basin. Water Science & Technology. 2026. doi:10.2166/wst.2026.310

BibTeX
@article{Ukkonen2026,
  author = {Ukkonen, Petri and Mulas, M and Mikola, A},
  title = {Hybrid computational fluid dynamics model for dissolved oxygen field prediction in a full-scale wastewater aeration basin},
  journal = {Water Science & Technology},
  year = {2026},
  doi = {10.2166/wst.2026.310}
}
Kostenlos starten →