Meta-modeling based efficient global sensitivity analysis for wastewater treatment plants – An application to the BSM2 model

Resul Al, Chitta Ranjan Behera, Alexandr Zubov, Krist V. Gernaey, Gürkan Sin*

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

Global sensitivity analysis (GSA) is a powerful tool for quantifying the effects of model parameters on the performance outputs of engineering systems, such as wastewater treatment plants (WWTP). Due to the ever-growing sophistication of such systems and their models, significantly longer processing times are required to perform a system-wide simulation, which makes the use of traditional Monte Carlo (MC) based approaches for calculation of GSA measures, such as Sobol indices, impractical. In this work, we present a systematic framework to construct and validate highly accurate meta-models to perform an efficient GSA of complex WWTP models such as the Benchmark Simulation Model No. 2 (BSM2). The robustness and the efficacy of three meta-modeling approaches, namely polynomial chaos expansion (PCE), Gaussian process regression (GPR), and artificial neural networks (ANN), are tested on four engineering scenarios. The results reveal significant computational gains of the proposed framework over the MC-based approach without compromising accuracy.
Original languageEnglish
JournalComputers & Chemical Engineering
Volume127
Pages (from-to)233-246
ISSN0098-1354
DOIs
Publication statusPublished - 2019

Keywords

  • Global sensitivity analysis
  • Sobol method
  • Wastewater treatment plant modeling
  • Polynomial chaos expansions
  • Gaussian process regression
  • Artificial neural networks

Cite this

@article{7b633ab67be247638e89e46457d6f947,
title = "Meta-modeling based efficient global sensitivity analysis for wastewater treatment plants – An application to the BSM2 model",
abstract = "Global sensitivity analysis (GSA) is a powerful tool for quantifying the effects of model parameters on the performance outputs of engineering systems, such as wastewater treatment plants (WWTP). Due to the ever-growing sophistication of such systems and their models, significantly longer processing times are required to perform a system-wide simulation, which makes the use of traditional Monte Carlo (MC) based approaches for calculation of GSA measures, such as Sobol indices, impractical. In this work, we present a systematic framework to construct and validate highly accurate meta-models to perform an efficient GSA of complex WWTP models such as the Benchmark Simulation Model No. 2 (BSM2). The robustness and the efficacy of three meta-modeling approaches, namely polynomial chaos expansion (PCE), Gaussian process regression (GPR), and artificial neural networks (ANN), are tested on four engineering scenarios. The results reveal significant computational gains of the proposed framework over the MC-based approach without compromising accuracy.",
keywords = "Global sensitivity analysis, Sobol method, Wastewater treatment plant modeling, Polynomial chaos expansions, Gaussian process regression, Artificial neural networks",
author = "Resul Al and Behera, {Chitta Ranjan} and Alexandr Zubov and Gernaey, {Krist V.} and G{\"u}rkan Sin",
year = "2019",
doi = "10.1016/j.compchemeng.2019.05.015",
language = "English",
volume = "127",
pages = "233--246",
journal = "Computers & Chemical Engineering",
issn = "0098-1354",
publisher = "Elsevier",

}

TY - JOUR

T1 - Meta-modeling based efficient global sensitivity analysis for wastewater treatment plants – An application to the BSM2 model

AU - Al, Resul

AU - Behera, Chitta Ranjan

AU - Zubov, Alexandr

AU - Gernaey, Krist V.

AU - Sin, Gürkan

PY - 2019

Y1 - 2019

N2 - Global sensitivity analysis (GSA) is a powerful tool for quantifying the effects of model parameters on the performance outputs of engineering systems, such as wastewater treatment plants (WWTP). Due to the ever-growing sophistication of such systems and their models, significantly longer processing times are required to perform a system-wide simulation, which makes the use of traditional Monte Carlo (MC) based approaches for calculation of GSA measures, such as Sobol indices, impractical. In this work, we present a systematic framework to construct and validate highly accurate meta-models to perform an efficient GSA of complex WWTP models such as the Benchmark Simulation Model No. 2 (BSM2). The robustness and the efficacy of three meta-modeling approaches, namely polynomial chaos expansion (PCE), Gaussian process regression (GPR), and artificial neural networks (ANN), are tested on four engineering scenarios. The results reveal significant computational gains of the proposed framework over the MC-based approach without compromising accuracy.

AB - Global sensitivity analysis (GSA) is a powerful tool for quantifying the effects of model parameters on the performance outputs of engineering systems, such as wastewater treatment plants (WWTP). Due to the ever-growing sophistication of such systems and their models, significantly longer processing times are required to perform a system-wide simulation, which makes the use of traditional Monte Carlo (MC) based approaches for calculation of GSA measures, such as Sobol indices, impractical. In this work, we present a systematic framework to construct and validate highly accurate meta-models to perform an efficient GSA of complex WWTP models such as the Benchmark Simulation Model No. 2 (BSM2). The robustness and the efficacy of three meta-modeling approaches, namely polynomial chaos expansion (PCE), Gaussian process regression (GPR), and artificial neural networks (ANN), are tested on four engineering scenarios. The results reveal significant computational gains of the proposed framework over the MC-based approach without compromising accuracy.

KW - Global sensitivity analysis

KW - Sobol method

KW - Wastewater treatment plant modeling

KW - Polynomial chaos expansions

KW - Gaussian process regression

KW - Artificial neural networks

U2 - 10.1016/j.compchemeng.2019.05.015

DO - 10.1016/j.compchemeng.2019.05.015

M3 - Journal article

VL - 127

SP - 233

EP - 246

JO - Computers & Chemical Engineering

JF - Computers & Chemical Engineering

SN - 0098-1354

ER -