A combined search method based on a deep learning combined surrogate model for groundwater DNAPL contamination source identification

Wang, Zibo; Lu, Wenxi; Chang, Zhenbo; Luo, Jiannan

doi:10.1016/j.jhydrol.2022.128854

Cited by 11 publications

(6 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The advent of artificial intelligence and deep learning methods has further expanded the scope of GCSI research, with a growing number of scholars employing cutting‐edge deep learning surrogate models in their studies (Kang et al., 2022; Mo et al., 2019; Zhang, Zheng, et al., 2020). Similar attempts have been made in our previous researches (Chang et al., 2022; Wang et al., 2023). Nevertheless, it is essential to acknowledge that training deep learning surrogate models comes with a considerable computational cost.…”

Section: Introductionsupporting

confidence: 86%

“…Therefore, Wang et al. (2023) proposed an improved Butterfly Optimization Algorithm (IBOA), which enhances a key parameter (switching probability) to allow for dynamic changes with each iteration, resulting in improved optimization results.…”

Section: Methodsmentioning

confidence: 99%

“…However, in the original algorithm, many key parameters were fixed throughout the entire optimization process, which cannot be adjusted at different optimization stages. Therefore, Wang et al (2023) proposed an improved Butterfly Optimization Algorithm (IBOA), which enhances a key parameter (switching probability) to allow for dynamic changes with each iteration, resulting in improved optimization results.…”

Section: Improved Butterfly Optimization Algorithmmentioning

confidence: 99%

“…In recent years, data assimilation has received widespread attention in GCSI (Mo et al., 2019; Wang et al., 2023; Xu & Gomez‐Hernandez, 2016; Zhang et al., 2018). This method leverages the covariance matrix to capture the relationship between the unknown variables and the system output, effectively utilizing observation data to update the values of the unknown variables, resulting in high search efficiency (Chang, Lu, & Wang, 2021).…”

Section: Introductionmentioning

confidence: 99%

“…But these methods often get stuck in local optima and miss global optima (Gómez‐Hernández & Xu, 2021). To solve this problem, some heuristic algorithms have been proposed, such as the genetic algorithm, particle swarm optimization algorithm, simulated annealing algorithm, and butterfly optimization algorithm (Han et al., 2020; Jiang et al., 2021; Prakash & Datta, 2015; Singh & Datta, 2006; Wang et al., 2023; Zhao et al., 2020), etc. Although significant progress has been made in the simulation optimization method, it cannot perform uncertainty analysis for the inverse problem.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

Chang,

Guo,

Chen

et al. 2024

Water Resources Research

Self Cite

View full text Add to dashboard Cite

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.

show abstract