Article
Engineering, Civil
Xue Jiang, Rui Ma, Yanxin Wang, Wenlong Gu, Wenxi Lu, Jin Na
Summary: This study proposes a new two-stage surrogate-assisted Markov chain Monte Carlo-based Bayesian framework for identifying contaminant source parameters in groundwater. An adaptive update feedback process and a multiobjective feasibility-enhanced particle swarm optimization algorithm are utilized to enhance the accuracy and efficiency of the framework.
JOURNAL OF HYDROLOGY
(2021)
Article
Engineering, Civil
Zibo Wang, Wenxi Lu, Zhenbo Chang, Jiannan Luo
Summary: In this paper, a improved butterfly optimization algorithm is proposed and combined with Ensemble Kalman filter and optimization methods to build a more robust and practical combined search method (CSM) for groundwater contamination source identification. The CSM significantly improves the identification accuracy and effectiveness compared with any single method.
JOURNAL OF HYDROLOGY
(2023)
Article
Environmental Sciences
Zidong Pan, Wenxi Lu, Yue Fan, Jiuhui Li
Summary: A simulation-optimization method based on Bayesian regularization deep neural network (BRDNN) surrogate model was proposed to efficiently solve high-nonlinear inverse problem, identifying eight variables including locations and release intensities of pollution sources and hydraulic conductivities. The three hidden layers in the BRDNN surrogate model significantly improved the fitting capacity of nonlinear mapping relationship to the simulation model, while Bayesian regularization was applied to solve the overfitting problem.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2021)
Article
Environmental Sciences
Yuanbo Ge, Wenxi Lu, Zidong Pan
Summary: In the traditional linked simulation-optimization method, a surrogate model is developed to reduce the computational load. In this study, the surrogate model built using the BiLSTM method shows higher accuracy and better generalization performance compared to other methods. The surrogate model is linked to the optimization model, and a more efficient search algorithm is utilized for reliable identification of contamination sources.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Engineering, Environmental
Na Zheng, Jinbing Liu, Xuemin Xia, Simin Gu, Yanhao Wu, Xianwen Li, Simin Jiang
Summary: This study proposes a modified self-organizing map (SOM) based surrogate model, named ILUES-SOM, to simultaneously identify contaminant source parameters and hydraulic conductivity field in the groundwater system. The robustness of ILUES-SOM model was verified by comparing its parameter estimation accuracy and computational efficiency with the original SOM and SGSIM-ILUES inversion models. The results indicate that ILUES-SOM model can successfully retrieve unknown contaminant source and heterogeneous hydraulic conductivity field in the groundwater system.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2023)
Article
Engineering, Multidisciplinary
Jiannan Luo, Yong Liu, Xueli Li, Xin Xin, Wenxi Lu
Summary: In this study, a two-stage adaptive surrogate model-assisted trust region GA (TSASM-TRGA) framework was developed to improve the accuracy and stability of groundwater contamination source inversion. The results showed that the TSASM-TRGA framework outperformed other frameworks in terms of accuracy and stability.
APPLIED MATHEMATICAL MODELLING
(2022)
Article
Environmental Sciences
Zeynep Demiray, Nihat Hakan Akyol, Gokce Akyol, Nadim K. Copty
Summary: This study investigates the synergetic effects of combining surfactant-enhanced dissolution with in-situ oxidation for PCE DNAPL remediation. The results show that the inclusion of oxidation delays the mass flux drop and improves DNAPL removal efficiency.
JOURNAL OF CONTAMINANT HYDROLOGY
(2023)
Article
Engineering, Environmental
Han Wang, Wenxi Lu, Zhenbo Chang
Summary: The SRS method is effective for solving GCSI challenges, with the proposed UHSIP and ACPSO-ELM surrogate system enhancing identification and approximation accuracy.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2021)
Article
Environmental Sciences
Jiuhui Li, Zhengfang Wu, Hongshi He, Wenxi Lu
Summary: The location and release history of groundwater contaminant sources (GCSs) are usually unknown, but previous studies have used prior information to identify GCSs. This study compared two methods for GCSs identification and found that the S/O method is more suitable for GCSs identification than the EnKF method.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Environmental Sciences
Yidan Li, Wenxi Lu, Zidong Pan, Zibo Wang, Guangqi Dong
Summary: Groundwater contaminant source identification (GCSI) is important for remediation and liability. This paper proposes a new optimization algorithm called flying foxes optimization (FFO) to solve the high-dimensional unknown variables in GCSI. The results show that FFO outperforms genetic algorithm (GA) with an average relative error of 2.12%. In addition, the surrogate model of multilayer perception (MLP) is better than the commonly used backpropagation algorithm (BP) for reducing computational load.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Biotechnology & Applied Microbiology
Chukwuemeka Onaa, Emmanuel A. Olaobaju, Mohammed M. Amro
Summary: This study utilizes numerical methods to describe and predict the transport of LNAPL contaminants in the subsurface. The results highlight the importance of factors such as exposure time, fluid properties, contaminant supply, and porous matrix characteristics in LNAPL contaminant migration underground.
ENVIRONMENTAL TECHNOLOGY & INNOVATION
(2021)
Article
Engineering, Environmental
Sondipon Paul, Brian Waldron, Farhad Jazaei, Daniel Larsen
Summary: The study aims to reduce the risk of contamination of groundwater and find suitable locations for future well construction. By developing various strategies and numerical groundwater modeling techniques, the research finds that optimizing well positions and pumping methods can increase the lifespan of wells, offer sustainable management, and reduce contaminant migration.
JOURNAL OF THE AMERICAN WATER RESOURCES ASSOCIATION
(2023)
Article
Multidisciplinary Sciences
Anna Pietrenko-Dabrowska, Slawomir Koziel, Ubaid Ullah
Summary: Electromagnetic simulation tools are essential in contemporary antenna design, but the associated computational overhead can be a major setback. This paper proposes a novel modeling technique that incorporates response feature technology into the constrained modeling framework, allowing for accurate surrogates with small training data sets. The technique can be applied in other fields with costly simulation models.
SCIENTIFIC REPORTS
(2022)
Article
Thermodynamics
Lei Wang, Jianliang Xu, Juntao Wei, Qinghua Guo, Yan Gong, Guangsuo Yu
Summary: This study investigated multiphase flow and heat transfer in the throat region of a radiant syngas cooler, validating the reliability and accuracy of the mathematical models with a maximum relative error of 3.7%. The simulation results showed that the annular step and tapered region altered the flow field distribution and resulted in increased dissipation of the central jet flow.
APPLIED THERMAL ENGINEERING
(2022)
Article
Environmental Sciences
Yukun Bai, Wenxi Lu, Jiuhui Li, Zhengbo Chang, Han Wang
Summary: The study proposed an adaptive mutation differential evolution Markov chain (AM-DEMC) algorithm for groundwater contamination source identification, which showed stronger search-ability and higher accuracy compared to traditional MCMC and DE-MC algorithms. Using the Kriging method to establish a surrogate model also improved computational efficiency.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)