Calibrating activated sludge models through hyperparameter optimization: a new framework for wastewater treatment plant simulation

Abstract Traditional calibration of Activated Sludge Models (ASM) is often manual, expert-dependent, and inefficient. This study introduces a hyperparameter optimisation framework using Optuna to automate the calibration of the ASM2d model. Built on Python, the model integrates the Tree-structured P...

Full description

Saved in:
Bibliographic Details
Main Authors: Huarong Yu, Yue Wang, Tan Li, Qibo Gan, Dan Qu, Fangshu Qu
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:npj Clean Water
Online Access:https://doi.org/10.1038/s41545-025-00513-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226629536022528
author Huarong Yu
Yue Wang
Tan Li
Qibo Gan
Dan Qu
Fangshu Qu
author_facet Huarong Yu
Yue Wang
Tan Li
Qibo Gan
Dan Qu
Fangshu Qu
author_sort Huarong Yu
collection DOAJ
description Abstract Traditional calibration of Activated Sludge Models (ASM) is often manual, expert-dependent, and inefficient. This study introduces a hyperparameter optimisation framework using Optuna to automate the calibration of the ASM2d model. Built on Python, the model integrates the Tree-structured Parzen Estimator (TPE) for single-objective and NSGA-II for multi-objective optimisation. A 50-day dataset from a full-scale wastewater treatment plant in Shenzhen, China, validates the approach. Compared to traditional methods, TPE reduced average relative errors for TN and COD from 4.587 and 24.846% to 0.798 and 15.291%, respectively, while decreasing iterations by 15–20%. NSGA-II lowered TN and COD errors to 4.72 and 15.17%, further improving to 0.095% and 8.43% with full-parameter tuning. Calibration efficiency increased by 65–75%. By effectively exploring parameter interdependencies, TPE and NSGA-II enhance calibration robustness and generalisation. This automated optimisation method significantly improves the accuracy and efficiency of ASM calibration, advancing intelligent wastewater process modelling.
format Article
id doaj-art-275a88dc0cb04113bdbb70f2479f855a
institution Kabale University
issn 2059-7037
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series npj Clean Water
spelling doaj-art-275a88dc0cb04113bdbb70f2479f855a2025-08-24T11:05:43ZengNature Portfolionpj Clean Water2059-70372025-08-018111210.1038/s41545-025-00513-yCalibrating activated sludge models through hyperparameter optimization: a new framework for wastewater treatment plant simulationHuarong Yu0Yue Wang1Tan Li2Qibo Gan3Dan Qu4Fangshu Qu5School of Civil Engineering and Transportation, Guangzhou UniversitySchool of Civil Engineering and Transportation, Guangzhou UniversitySchool of Civil Engineering and Transportation, Guangzhou UniversitySchool of Civil Engineering and Transportation, Guangzhou UniversityCollege of Environmental Science and Engineering, Beijing Forestry UniversityKey Laboratory for Water Quality and Conservation of the Pearl River Delta, Guangzhou UniversityAbstract Traditional calibration of Activated Sludge Models (ASM) is often manual, expert-dependent, and inefficient. This study introduces a hyperparameter optimisation framework using Optuna to automate the calibration of the ASM2d model. Built on Python, the model integrates the Tree-structured Parzen Estimator (TPE) for single-objective and NSGA-II for multi-objective optimisation. A 50-day dataset from a full-scale wastewater treatment plant in Shenzhen, China, validates the approach. Compared to traditional methods, TPE reduced average relative errors for TN and COD from 4.587 and 24.846% to 0.798 and 15.291%, respectively, while decreasing iterations by 15–20%. NSGA-II lowered TN and COD errors to 4.72 and 15.17%, further improving to 0.095% and 8.43% with full-parameter tuning. Calibration efficiency increased by 65–75%. By effectively exploring parameter interdependencies, TPE and NSGA-II enhance calibration robustness and generalisation. This automated optimisation method significantly improves the accuracy and efficiency of ASM calibration, advancing intelligent wastewater process modelling.https://doi.org/10.1038/s41545-025-00513-y
spellingShingle Huarong Yu
Yue Wang
Tan Li
Qibo Gan
Dan Qu
Fangshu Qu
Calibrating activated sludge models through hyperparameter optimization: a new framework for wastewater treatment plant simulation
npj Clean Water
title Calibrating activated sludge models through hyperparameter optimization: a new framework for wastewater treatment plant simulation
title_full Calibrating activated sludge models through hyperparameter optimization: a new framework for wastewater treatment plant simulation
title_fullStr Calibrating activated sludge models through hyperparameter optimization: a new framework for wastewater treatment plant simulation
title_full_unstemmed Calibrating activated sludge models through hyperparameter optimization: a new framework for wastewater treatment plant simulation
title_short Calibrating activated sludge models through hyperparameter optimization: a new framework for wastewater treatment plant simulation
title_sort calibrating activated sludge models through hyperparameter optimization a new framework for wastewater treatment plant simulation
url https://doi.org/10.1038/s41545-025-00513-y
work_keys_str_mv AT huarongyu calibratingactivatedsludgemodelsthroughhyperparameteroptimizationanewframeworkforwastewatertreatmentplantsimulation
AT yuewang calibratingactivatedsludgemodelsthroughhyperparameteroptimizationanewframeworkforwastewatertreatmentplantsimulation
AT tanli calibratingactivatedsludgemodelsthroughhyperparameteroptimizationanewframeworkforwastewatertreatmentplantsimulation
AT qibogan calibratingactivatedsludgemodelsthroughhyperparameteroptimizationanewframeworkforwastewatertreatmentplantsimulation
AT danqu calibratingactivatedsludgemodelsthroughhyperparameteroptimizationanewframeworkforwastewatertreatmentplantsimulation
AT fangshuqu calibratingactivatedsludgemodelsthroughhyperparameteroptimizationanewframeworkforwastewatertreatmentplantsimulation