Auditable Automation of Activated Sludge Modeling for Wastewater Treatment Diagnosis Using LLM-Agents
Environmental Science & Technology · 2026
DOI: 10.1021/acs.est.6c09278 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Science & Technology, 2026. Verfasst von Yu-Qi Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Urban-Rural Water Resource and Environment, School of Eco-Environment, Harbin Institute of Technology, Shenzhen518055, China. Hauptthemen laut MEDLINE: Sewage, Wastewater. Die Arbeit nennt 56 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shanghai Tongji Gao Tingyao Environmental Science Technology Development Foundation, Shenzhen Science and Technology Program.
Abstract (Originalsprache)
Wastewater treatment plants (WWTPs) need mechanistic models that explain carbon, nitrogen, and phosphorus transformations under changing operating conditions. Building activated sludge models (ASMs) still depends heavily on expert choices about boundaries, components, and reactions. We developed AutoWWTP-ASM, an auditable large-language-model agent (LLM-Agent) workflow for library-constrained ASM configuration, execution, and calibration. The workflow converts wastewater-process descriptions into structured configurations and combines a predefined ASM library with boundary specification and optional human review. In a coupled carbon−nitrogen−phosphorus task, AutoWWTP-ASM instantiated a model containing 21 state components and 41 biochemical reactions. Across 37 evaluation tasks, the average accuracy scores of ten LLM backbones ranged from 0.596 to 0.627, indicating a narrow range of backbone-level performance within the tested workflow. Ablation experiments evaluated the knowledge, planning, and reflection modules. Comparisons with a single agent, an 8B LLM, and human modelers assessed deployment and efficiency trade-offs. Additional evaluations using six IWA BSM1 scenarios and data from a full-scale WWTP provided further evidence of applicability under standardized and real-data conditions. We provide open-source LangGraph code, together with Codex, Claude Code, and Agent Skill implementations, to support the reproducible development of auditable LLM-Agent workflows for environmental modeling.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- State Key Laboratory of Urban-Rural Water Resource and Environment, School of Eco-Environment, Harbin Institute of Technology, Shenzhen518055, China.
- School of Energy and Environment, City University of Hong Kong, Hong Kong, Hong Kong SAR999077, China.
- Key Laboratory of Environmental Biotechnology, Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences, Beijing100085, China.
ORCID-Profile: Yu-Qi Wang, Yun-Peng Song, Hong-Cheng Wang
Förderung
- National Natural Science Foundation of China
- Shanghai Tongji Gao Tingyao Environmental Science Technology Development Foundation
- Shenzhen Science and Technology Program
- State Key Laboratory of Urban-rural Water Resources and Environment (Harbin Institute of Technology)
Zitieren
APA
Wang, Y. Q., Yang, H. L., Chen, J. J., Wang, W. Z., Song, Y. P., Wang, A. J., & Wang, H. C. (2026). Auditable Automation of Activated Sludge Modeling for Wastewater Treatment Diagnosis Using LLM-Agents. Environmental Science & Technology. https://doi.org/10.1021/acs.est.6c09278
Vancouver
Wang YQ, Yang HL, Chen JJ, Wang WZ, Song YP, Wang AJ, et al. Auditable Automation of Activated Sludge Modeling for Wastewater Treatment Diagnosis Using LLM-Agents. Environmental Science & Technology. 2026. doi:10.1021/acs.est.6c09278
BibTeX
@article{Wang2026,
author = {Wang, Yu-Qi and Yang, Hao-Lin and Chen, Jia-Ji and Wang, Wen-Zhe and Song, Yun-Peng and Wang, Ai-Jie and Wang, Hong-Cheng},
title = {Auditable Automation of Activated Sludge Modeling for Wastewater Treatment Diagnosis Using LLM-Agents},
journal = {Environmental Science & Technology},
year = {2026},
doi = {10.1021/acs.est.6c09278}
}
EUVIMED