A Comparison of Inversion Methods for Surrogate-Based Groundwater Contamination Source Identification With Varying Degrees of Model Complexity

Chang, Zhenbo1,2; Guo, Zhilin1,2; Chen, Kewei1,2; Wang, Zibo3; Zhan, Yang1,2; Lu, Wenxi3; Zheng, Chunmiao1,2,4

2024-04-01

10.1029/2023WR036051

WATER RESOURCES RESEARCH   影响因子和分区

0043-1397

1944-7973

["Accurate identification of groundwater contamination sources is important for designing efficacious site remediation strategies. Currently, the methods for identifying contamination sources mainly fall into three distinct categories: simulation optimization, Bayesian inference, and data assimilation. Each method has its own advantages and disadvantages under specific site conditions. To evaluate the applicability of these methods, we chose one representative inversion algorithm from each category, namely the Improved Butterfly Optimization Algorithm (IBOA) for simulation optimization, the Ensemble Smoother with Multiple Data Assimilation (ES-MDA) for data assimilation, and the DiffeRential Evolution Adaptive Metropolis with a Snooker Update and Sampling from a Past Archive (DREAM(ZS)) for Bayesian inference. We conducted a comprehensive evaluation of these methods' performance under different model complexities, employing a surrogate model as a substitute for the complex forward model. By addressing two distinct problems involving conservative pollutant transport and Light Non-Aqueous Phase Liquid (LNAPL) transport with biodegradation, we employed four criteria (elapsed time, result accuracy, posterior probability distribution, and noise resistance) for evaluation. The findings unequivocally indicate that DREAM(ZS) outperforms others in terms of result accuracy and posterior probability distribution. It also adeptly navigates the interrelations among disparate unknown variables. The strength of ES-MDA lies in its efficiency. It achieves relatively satisfactory results with a reduced computational burden. In contrast, IBOA underperforms in both test problems. In terms of resistance to noise, both DREAM(ZS) and ES-MDA perform better than IBOA does.","Hyperparameter optimization improves the accuracy of shallow learning surrogate models, making them comparable to deep learning models Three mainstream inversion methods were compared in elapsed time, result accuracy, posterior probability distribution and noise resistance Data assimilation and Bayesian inference methods are recommended for groundwater contamination source identification"]

simulation optimization Bayesian inference surrogate model data assimilation groundwater contamination source identification hyperparameter optimization

SCI ; EI

英语

第一 ; 通讯

Guangdong Provincial Basic and Applied Basic Research Fund[2021A1515110781] ; Shenzhen Science and Technology Innovation Committee[JCYJ20210324105009024] ; Guangdong Provincial Key Laboratory of Soil and Groundwater Pollution Control[2023B1212060002] ; null[42377045] ; null[42207062]

Environmental Sciences & Ecology ; Marine & Freshwater Biology ; Water Resources

Environmental Sciences ; Limnology ; Water Resources

WOS:001192218800001

AMER GEOPHYSICAL UNION

ENVIRONMENT/ECOLOGY

Web of Science

1.Southern Univ Sci & Technol, Sch Environm Sci & Engn, State Environm Protect Key Lab Integrated Surface, Shenzhen, Peoples R China
2.Southern Univ Sci & Technol, Sch Environm Sci & Engn, Guangdong Prov Key Lab Soil & Groundwater Pollut C, Shenzhen, Peoples R China
3.Jilin Univ, Coll New Energy & Environm, Changchun, Peoples R China
4.EIT Inst Adv Study, Ningbo, Peoples R China

Chang, Zhenbo,Guo, Zhilin,Chen, Kewei,et al. A Comparison of Inversion Methods for Surrogate-Based Groundwater Contamination Source Identification With Varying Degrees of Model Complexity[J]. WATER RESOURCES RESEARCH,2024,60(4).

Chang, Zhenbo.,Guo, Zhilin.,Chen, Kewei.,Wang, Zibo.,Zhan, Yang.,...&Zheng, Chunmiao.(2024).A Comparison of Inversion Methods for Surrogate-Based Groundwater Contamination Source Identification With Varying Degrees of Model Complexity.WATER RESOURCES RESEARCH,60(4).

Chang, Zhenbo,et al."A Comparison of Inversion Methods for Surrogate-Based Groundwater Contamination Source Identification With Varying Degrees of Model Complexity".WATER RESOURCES RESEARCH 60.4(2024).