Reinforcement-Learning-Enabled Supervisory Control of a Full-Scale Anaerobic Digestion Facility Using a Calibrated Digital Twin
Environmental Science & Technology · 06.10.2026 · 60 (39) · 28064-28078
DOI: 10.1021/acs.est.6c05822 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Science & Technology, online erschienen am 24.09.2026. Verfasst von Ahmed I Yunus und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Civil and Environmental Engineering, Georgia Institute of Technology, Atlanta, Georgia30318, United States. Hauptthemen laut MEDLINE: Anaerobiosis. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Renewable Bioproducts Institute.
Abstract (Originalsprache)
Anaerobic digestion (AD) is a cornerstone of energy recovery and decarbonization at wastewater resource recovery facilities (WRRFs), yet full-scale digesters are often operated conservatively due to delayed process feedback, nonlinear stability constraints, and limited observability. This study presents a novel reinforcement learning (RL)-enabled supervisory control framework for full-scale AD that integrates a calibrated mechanistic digital twin model (DTM) with offline policy learning and counterfactual uncertainty evaluation. Specifically, the DTM was calibrated to reproduce control-relevant digester behavior. Using 2.7 years of simulated operation, a batch-constrained Q (BCQ)-reinforcement learning policy was trained to maximize biogas production while penalizing instability associated with pH excursions and elevated volatile fatty acids (VFAs)/alkalinity (ALK) ratios. Counterfactual evaluation against historical, greedy, and heuristic controls used 1 year unseen DTM simulation and 1 year of full-scale operational data. The RL policy achieved comparable mean daily biogas production (+0.35%) in simulated testing. Under the 1 year operational data, it achieved plant-equivalent mean production of 9802 m3/day, corresponding to a modest potential cumulative improvement (+2.7%, 93 405 m3/year) subject to substantial uncertainty P(Δ > 0) = 0.524. These results indicate that offline-trained RL, combined with a mechanistic digital twin and counterfactual evaluation, provides a feasible and interpretable framework for developing and assessing supervisory AD control without live-plant experimentation while showing that the resulting benefit must be interpreted under explicit model-plant uncertainty.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Civil and Environmental Engineering, Georgia Institute of Technology, Atlanta, Georgia30318, United States.
- Jimmy and Rosalynn Carter School of Public Policy, Georgia Institute of Technology, Atlanta, Georgia30332, United States.
ORCID-Profile: Ahmed I Yunus, Joe F Bozeman, Yongsheng Chen
Förderung
- Renewable Bioproducts Institute
Zitieren
APA
Yunus, A. I., Jalla, S., Bozeman, J. F., & Chen, Y. (2026). Reinforcement-Learning-Enabled Supervisory Control of a Full-Scale Anaerobic Digestion Facility Using a Calibrated Digital Twin. Environmental Science & Technology, 60(39), 28064-28078. https://doi.org/10.1021/acs.est.6c05822
Vancouver
Yunus AI, Jalla S, Bozeman JF, Chen Y. Reinforcement-Learning-Enabled Supervisory Control of a Full-Scale Anaerobic Digestion Facility Using a Calibrated Digital Twin. Environmental Science & Technology. 2026;60(39):28064-28078. doi:10.1021/acs.est.6c05822
BibTeX
@article{Yunus2026,
author = {Yunus, Ahmed I and Jalla, Srinivas and Bozeman, Joe F and Chen, Yongsheng},
title = {Reinforcement-Learning-Enabled Supervisory Control of a Full-Scale Anaerobic Digestion Facility Using a Calibrated Digital Twin},
journal = {Environmental Science & Technology},
year = {2026},
volume = {60},
number = {39},
pages = {28064--28078},
doi = {10.1021/acs.est.6c05822}
}
EUVIMED