|Table of Contents|

Coupled Sensitivity Analysis and Two-stage MCMC Algorithm for Groundwater Pollution Source Identification(PDF)

《地球科学与环境学报》[ISSN:1672-6561/CN:61-1423/P]

Issue:
2024年第05期
Page:
702-710
Research Field:
水资源与水文地质
Publishing date:

Info

Title:
Coupled Sensitivity Analysis and Two-stage MCMC Algorithm for Groundwater Pollution Source Identification
Author(s):
LI Zi-le1; 2;  AN Yong-kai1; 2*;  YAN Xue-man3
(1. School of Water and Environment, Chang'an University, Xi'an 710054, Shaanxi, China; 2. Key Laboratory of Subsurface Hydrology and Ecological Effect in Arid Region of Ministry of Education, Chang'an University, Xi'an 710054, Shaanxi, China; 3. College of Urban and Environmental Sciences, Northwest University, Xi'an 710127, Shaanxi, China)
Keywords:
groundwater;  pollution transport;  source identification;  numerical model;  two-stage MCMC algorithm;  sensitivity analysis;  MLP;  surrogate model
PACS:
X523
DOI:
10.19814/j.jese.2024.05006
Abstract:
To achieve high-precision groundwater pollution source identification, the two-stage Markov Chain Monte Carlo(MCMC)algorithm was used to identify the pollution source parameters based on sensitivity analysis of pollution source parameters. At the same time, the surrogate model of the numerical model of groundwater pollution transport using multi-layer perceptron(MLP)method was explored to improve the efficiency of groundwater pollution source identification. Two numerical examples were implemented to verify the effectiveness and feasibility of the above methods. The results show that the surrogate models constructed by the MLP method has high approximation accuracy for the numerical model of groundwater pollution transport, which can not only effectively improve the efficiency of groundwater pollution source identification, but also maintain good calculation accuracy. The proposed coupled sensitivity analysis and two-stage MCMC algorithm can significantly improve the identification accuracy of pollution source parameters with low sensitivity.

References:

[1] 吴延浩,江思珉,吴自军.地下水污染强度及渗透系数场的反演识别研究[J].水文地质工程地质,2023,50(4):193-203.
WU Yan-hao,JIANG Si-min,WU Zi-jun.Identification of Groundwater Pollution Intensity and Hydraulic Conductivity Field[J].Hydrogeology & Engineering Geology,2023,50(4):193-203.
[2] HOU Z Y,LU W X.Comparative Study of Surrogate Models for Groundwater Contamination Source Identification at DNAPL-Contaminated Sites[J].Hydrogeology Journal,2018,26(3):923-932.
[3] 闫雪嫚.基于贝叶斯理论的地下水DNAPLs污染源反演识别研究[D].长春:吉林大学,2021.
YAN Xue-man.Identification of DNAPLs-contaminated Groundwater Pollution Sources Based on Bayes Theory[D].Changchun:Jilin University,2021.
[4] AYVAZ M T.A Hybrid Simulation-optimization Approach for Solving the Areal Groundwater Pollution Source Identification Problems[J].Journal of Hydro-logy,2016,538:161-176.
[5] HAN K X,ZUO R,NI P C,et al.Application of a Genetic Algorithm to Groundwater Pollution Source Identification[J].Journal of Hydrology,2020, 589:125343.
[6] AN Y K,YAN X M,LU W X,et al.An Improved Bayesian Approach Linked to a Surrogate Model for Identifying Groundwater Pollution Sources[J].Hy-drogeology Journal,2022,30(2):601-616.
[7] BORAH T,BHATTACHARJYA R K.Development of an Improved Pollution Source Identification Model Using Numerical and ANN Based Simulation-optimization Model[J].Water Resources Management,2016,30(14):5163-5176.
[8] LUO J N,LI X L,XIONG Y,et al.Groundwater Pollution Source Identification Using Metropolis-hasting Algorithm Combined with Kalman Filter Algorithm[J].Journal of Hydrology,2023,626:130258.
[9] JIANG X,MA R,WANG Y X,et al.Two-stage Surrogate Model-assisted Bayesian Framework for Grou-ndwater Contaminant Source Identification[J].Journal of Hydrology,2021,594:125955.
[10] ZENG X K,WU J C,WANG D,et al.Assessing the Pollution Risk of a Groundwater Source Field at Western Laizhou Bay Under Seawater Intrusion[J].Environmental Research,2016,148:586-594.
[11] YAN X M,DONG W H,AN Y K,et al.A Bayesian-based Integrated Approach for Identifying Groundwater Contamination Sources[J].Journal of Hydrology,2019,579:124160.
[12] 安永凯,张岩祥,闫雪嫚.基于自适应多保真度Co-Kriging代理模型的地下水污染源反演识别[J].中国环境科学,2024,44(3):1376-1385.
AN Yong-kai,ZHANG Yan-xiang,YAN Xue-man.Identification of Groundwater Pollution Sources Based on Self-adaption Co-Kriging Multi-fidelity Surrogate Model[J].China Environmental Science,2024,44(3):1376-1385.
[13] 刘墉达,陈 喜,高 满,等.基于MCMC和ES-MDA方法的地下水数值模型非均质参数场及开采量的反演研究[J].水利学报,2023,54(10):1236-1247.
LIU Yong-da,CHEN Xi,GAO Man,et al.Inversion of Heterogeneous Parameters Field and Extraction Amount of Groundwater Numerical Model Based on MCMC and ES-MDA Methods[J].Journal of Hydraulic Engineering,2023,54(10):1236-1247.
[14] GUO J Y,LU W X,YANG Q C,et al. The Application of 0-1 Mixed Integer Nonlinear Programming Optimization Model Based on a Surrogate Model to Identify the Groundwater Pollution Source[J].Journal of Contaminant Hydrology,2019,220:18-25.
[15] CHANG Z B,GUO Z L,CHEN K W,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):e2023WR036051.
[16] LAL A,DATTA B.Development and Implementation of Support Vector Machine Regression Surrogate Mo-dels for Predicting Groundwater Pumping-induced Saltwater Intrusion into Coastal Aquifers[J].Water Resources Management,2018,32(7):2405-2419.
[17] ZHOU Y C,LU Z Z.An Enhanced Kriging Surrogate Modeling Technique for High-dimensional Problems[J].Mechanical Systems and Signal Processing,2020,140:106687.
[18] MENGISTU T,GHALY W.Aerodynamic Optimization of Turbomachinery Blades Using Evolutionary Methods and ANN-based Surrogate Models[J].Optimization and Engineering,2008,9(3):239-255.
[19] LI J H,LU W X,WANG H,et al.Groundwater Contamination Source Identification Based on a Hybrid Particle Swarm Optimization-extreme Learning Machine[J].Journal of Hydrology,2020,584:124657.
[20] 后 锐,张毕西.基于MLP神经网络的区域物流需求预测方法及其应用[J].系统工程理论与实践,2005,25(12):43-47.
HOU Rui,ZHANG Bi-xi.A Method for Forecasting Regional Logistics Demand Based on MLP Neural Network and Its Application[J].Systems Engineering—Theory & Practice,2005,25(12):43-47.
[21] GHATE V N,DUDUL S V.Optimal MLP Neural Network Classifier for Fault Detection of Three Phase Induction Motor[J].Expert Systems with Applications,2010,37(4):3468-3481.
[22] 徐会军,陈洋波,李昼阳,等.基于LH-OAT分布式水文模型参数敏感性分析[J].人民长江,2012,43(7):19-23.
XU Hui-jun,CHEN Yang-bo,LI Zhou-yang,et al.Analysis on Parameter Sensitivity of Distributed Hyd-rological Model Based on LH-OAT Method[J].Yangtze River,2012,43(7):19-23.
[23] ZADEH F K,NOSSENT J,WOLDEGIORGIS B T,et al.A Fast and Effective Parameterization of Water Quality Models[J].Environmental Modelling & Software,2022,149:105331.
[24] 秦 萍,王 正,孙兆军,等.基于LH-OAT方法的VG模型参数敏感性分析[J].节水灌溉,2019(10):97-102.
QIN Ping,WANG Zheng,SUN Zhao-jun,et al.Sensitivity Analysis of VG Model Parameter Based on LH-OAT Method[J].Water Saving Irrigation,2019(10):97-102.
[25] 张双圣,强 静,刘汉湖,等.基于贝叶斯公式的地下水污染源识别[J].中国环境科学,2019,39(4):1568-1578.
ZHANG Shuang-sheng,QIANG Jing,LIU Han-hu,et al.Identification of Groundwater Pollution Sources Based on Bayes' Theorem[J].China Environmental Science,2019,39(4):1568-1578.
[26] YAN X M,LU W X,AN Y K,et al.Assessment of Parameter Uncertainty for Non-point Source Pollution Mechanism Modeling:A Bayesian-based Approach[J].Environmental Pollution,2020,263:114570.
[27] 梁识栋.高维参数水质模型参数不确定性分析方法研究[D].北京:清华大学,2016.
LIANG Shi-dong.Research on Parameter Uncertainty Analysis Method for Water Quality Model with High-dimensional Parameter Space[D].Beijing:Tsinghua University,2016.
[28] MUSTAFA S M T,NOSSENT J,GHYSELS G,et al.Integrated Bayesian Multi-model Approach to Quantify Input,Parameter and Conceptual Model Structure Uncertainty in Groundwater Modeling[J].Environmental Modelling & Software,2020,126:104654.
[29] WU W,REN J C,ZHOU X D,et al.Identification of Source Information for Sudden Water Pollution Incidents in Rivers and Lakes Based on Variable-fidelity Surrogate-DREAM Optimization[J].Environmental Modelling & Software,2020,133:104811.
[30] VRUGT J A.Markov Chain Monte Carlo Simulation Using the DREAM Software Package:Theory,Concepts,and MATLAB Implementation[J].Environmental Modelling & Software,2016,75:273-316.
[31] RIEDMILLER M,LERNEN A.Multi Layer Perceptron.Machine Learning Lab Special Lecture[R].Frei-burg:University of Freiburg,2014.
[32] 李含雪.基于气象数据和机器学习的土壤温度和水分预测模型构建[D].哈尔滨:东北农业大学,2022.
LI Han-xue.Construction of Soil Temperature and Moisture Prediction Model Based on Meteorological Data and Machine Learning[D].Harbin:Northeast Agricultural University,2022.

Memo

Memo:
-
Last Update: 2024-10-01