2025-5-13- Wednesday
HomeIntroductionEditorial boardContact usChinese
Home > Archive>Volume 51, Issue 2, 2023 >229-237. DOI:10.11908/j.issn.0253-374x.21448
PDF HTML XML Export Cite reminder
A DenseNet Network Based Surrogate Model for Simulating Contaminant Transport in Groundwater Systems
CSTR:
[cstr]
Author:
Affiliation:

1.College of Civil Engineering， Tongji University， Shanghai 200092， China;2.Yangtze Ecology and Environment Co.， Ltd.， Nanjing 210019， China;3.School of Environment and Architecture， University of Shanghai for Science and Technology， Shanghai 200093， China

Clc Number:

P641.2;X523

  • Article
    • | |
  • Metrics
    • |
  • Reference [25]
    • |
  • Related [20]
    • | | |
  • Comments
    Abstract:

    Groundwater inverse problems such as groundwater contaminant identification and aquifer parameter inversion problems are usually restricted by the computational load. In order to reduce the computational cost of groundwater inversion， the surrogate method is a feasible solution. In this paper， imitating the image recognition process of the convolutional neural network， the groundwater flow movement and contaminant transport problem is transformed into an image regression problem of the functional relationship between input image （hydraulic conductivity field， pollution source information， etc.） and output image （groundwater level， contaminant concentration， etc.）. The surrogate model of groundwater flow movement and contaminant transport is constructed by using AR-Net-WL based on the DenseNet network. The case study shows that， for the overfitting of the surrogate model， a 10% improvement in accuracy can be obtained by selecting training samples as large as possible. When there are no conditions to increase the training sample， AR-Net-WL with an optimal regularization coefficient can also achieve a good performance with fewer training samples （500 training samples） and can accurately predict the groundwater flow movement and contaminant transport.

    Reference
    [1] 吴剑锋, 郑春苗. 地下水污染监测网的设计研究进展[J]. 地球科学进展, 2004, 19(3): 429.WU Jianfeng, ZHENG Chunmiao. Contaminant monitoring network design: Recent advances and future directions[J]. Advance in Earth Sciences, 2004, 19(3): 429.
    [2] LI L, ZHOU H, GóMEZ-HERNáNDEZ J J. A comparative study of three-dimensional hydraulic conductivity upscaling at the macro-dispersion experiment (MADE) site, Columbus Air Force Base, Mississippi (USA)[J]. Journal of Hydrology, 2011, 404(3/4): 278.
    [3] WHITE J T. A model-independent iterative ensemble smoother for efficient history-matching and uncertainty quantification in very high dimensions[J]. Environmental Modelling & Software, 2018, 109: 191.
    [4] MIRGHANI B Y, MAHINTHAKUMAR K G, TRYBY M E, et al. A parallel evolutionary strategy based simulation–optimization approach for solving groundwater source identification problems[J]. Advances in Water Resources, 2009, 32(9): 1373.
    [5] YAN S, MINSKER B. Optimal groundwater remediation design using an adaptive neural network genetic algorithm: Optimal groundwater remediation design[J]. Water Resources Research, 2006, 42(5).
    [6] XIA X, ZHOU N, WANG L, et al. Identification of transient contaminant sources in aquifers through a surrogate model based on a modified self-organizing-maps algorithm[J]. Hydrogeology Journal, 2019, 27(7): 2535.
    [7] ZHENG Q, ZHANG J, XU W, et al. Adaptive multifidelity data assimilation for nonlinear subsurface flow problems[J]. Water Resources Research, 2019, 55(1): 203.
    [8] MAN J, ZHENG Q, WU L, et al. Adaptive multi-fidelity probabilistic collocation-based Kalman filter for subsurface flow data assimilation: Numerical modeling and real-world experiment[J]. Stochastic Environmental Research and Risk Assessment, 2020, 34(8): 1135.
    [9] LIN G, TARTAKOVSKY A M. An efficient, high-order probabilistic collocation method on sparse grids for three-dimensional flow and solute transport in randomly heterogeneous porous media[J]. Advances in Water Resources, 2009, 32(5): 712.
    [10] ASHER M J, CROKE B F W, JAKEMAN A J, et al. A review of surrogate models and their application to groundwater modeling: Surrogates of groundwater models[J]. Water Resources Research, 2015, 51(8): 5957.
    [11] LIAO Q, ZHANG D, TCHELEPI H. A two-stage adaptive stochastic collocation method on nested sparse grids for multiphase flow in randomly heterogeneous porous media[J]. Journal of Computational Physics, 2017, 330: 828.
    [12] ZHU Y, ZABARAS N, P-S KOUTSOURELAKIS , et al. Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data[J]. Journal of Computational Physics, 2019, 394: 56.
    [13] ZHU Y, ZABARAS N. Bayesian deep convolutional encoder–decoder networks for surrogate modeling and uncertainty quantification[J]. Journal of Computational Physics, 2018, 366: 415.
    [14] PETERSON T J, WESTERN A W. Nonlinear time-series modeling of unconfined groundwater head[J]. Water Resources Research, 2014, 50(10): 8330.
    [15] MO S, ZABARAS N, SHI X, et al. Deep autoregressive neural networks for high‐dimensional inverse problems in groundwater contaminant source identification[J]. Water Resources Research, 2019, 55(5): 3856.
    [16] 张江江. 地下水污染源解析的贝叶斯监测设计与参数反演方法[D]. 杭州: 浙江大学, 2017.ZHANG Jiangjiang. Bayesian monitoring design and parameter inversion for groundwater contaminant source identification[D]. Hangzhou: Zhejiang University, 2017.
    [17] MGM M, AW H. MODFLOW, A modular three-dimensional finite difference ground-water flow model[M]. Denver: [S.n.], 1988.
    [18] ZHENG C, WANG P P. MT3DMS: A modular three-dimensional multispecies transport model for simulation of advection, dispersion, and chemical reactions of contaminants in groundwater systems； documentation and user's guide[R]. Vicksburg: U.S. Army Engineer Research and Development Center, 1999.
    [19] JU L, ZHANG J, WU L, et al. Bayesian monitoring design for streambed heat tracing: Numerical simulation and sandbox experiments[J]. Groundwater, 2019, 57(4): 534.
    [20] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 770–778.
    [21] HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 2261–2269.
    [22] ZHANG J, LIN G, LI W, et al. An iterative local updating ensemble smoother for estimation and uncertainty assessment of hydrologic model parameters with multimodal distributions[J]. Water Resources Research, 2018, 54(3): 1716.
    [23] ZHANG D, LU Z. An efficient, high-order perturbation approach for flow in random porous media via Karhunen–Loève and polynomial expansions[J]. Journal of Computational Physics, 2004, 194(2): 773.
    [24] ZHENG H, YANG Z, LIU W, et al. Improving deep neural networks using softplus units[C]//2015 International Joint Conference on Neural Networks (IJCNN). Killarney: IEEE, 2015: 1–4.
    [25] 周志华. 机器学习[M]. 北京: 清华大学出版社, 2016.ZHOU Zhihua. Machine learning[M]. Beijing: Tsinghua University Press, 2016.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

JIANG Simin, KONG Weiming, WU Yanhao, LIU Jinbing, ZHANG Chunqiu, XIA Xuemin. A DenseNet Network Based Surrogate Model for Simulating Contaminant Transport in Groundwater Systems[J].同济大学学报(自然科学版),2023,51(2):229~237

Copy
Share
Article Metrics
  • Abstract:218
  • PDF: 534
  • HTML: 82
  • Cited by: 0
History
  • Received:September 26,2021
  • Online: March 03,2023
Article QR Code

Youare the 97861 visitor to this site

Copyright:JOURNAL OF TONGJI UNIVERSITY     Director:The Ministry of Education    The host:Tongji university.

Address:上海市四平路1239号同济大学内    Postcode:200092    TEL:86-21-65982344     E-mail:zrxb@tongji.edu.cn

Supported byBeijing E-Tiller Technology Development Co.,Ltd.