Groundwater Contamination Source Recognition Based on a Two-Stage Inversion Framework with a Deep Learning Surrogate
Abstract
:1. Introduction
2. Methodology
2.1. Simulation Model
2.2. Low-Cost Surrogate Models
2.2.1. The KELM
2.2.2. The MLP
2.3. Inversion Framework
2.3.1. The ES-MDA
2.3.2. The CDOA
2.3.3. Two-Stage Inversion Framework
3. Site Overview
3.1. Case Description
3.2. Application of the Low-Cost Surrogate Model
3.3. Application of the Two-Stage Inversion Framework
4. Discussion
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Shi, C.; Zhao, Y.; Lu, W. Application of stochastic programming in groundwater pollution source identification. Environ. Forensics 2021, 23, 170–178. [Google Scholar] [CrossRef]
- Covaciu, D.C.; Balint, A.C.; Neamtu, C.V.; Mosneag, S.C.; Bordea, D.; Dirjan, S.; Odagiu, A.C.M. Assessment of Groundwater Quality in Relation to Organic versus Mineral Fertilization. Water 2023, 15, 2895. [Google Scholar] [CrossRef]
- Yang, C.; Dong, J.; Ren, L.; Fan, Y.; Li, B.; Hu, W. Influencing factors on the stabilization of colloid biliquid aphrons and its effectiveness used for density modification of DNAPLs in subsurface environment. Colloid Surf. A-Physicochem. Eng. Asp. 2018, 553, 439–445. [Google Scholar] [CrossRef]
- Chang, Z.; Guo, Z.; Chen, K.; Wang, Z.; Zhan, Y.; Lu, W.; Zheng, C. A comparison of inversion methods for surrogate-based groundwater contamination source identification with varying degrees of model complexity. Water Resour. Res. 2024, 60, e2023WR036051. [Google Scholar] [CrossRef]
- Chen, Z.; Zong, L.; Gómez-Hernández, J.J.; Xu, T.; Jiang, Y.; Zhou, Q.; Yang, H.; Jia, Z.; Mei, S. Contaminant source and aquifer characterization: An application of ES-MDA demonstrating the assimilation of geophysical data. Adv. Water Resour. 2023, 181, 104555. [Google Scholar] [CrossRef]
- Kim, S.; Jung, H.; Choe, J. Enhanced History Matching of Gas Reservoirs with an Aquifer Using the Combination of Discrete Cosine Transform and Level Set Method in ES-MDA. J. Energy Resour. Technol.-Trans. ASME 2019, 141, 072906. [Google Scholar] [CrossRef]
- Todaro, V.; D’Oria, M.; Tanda, M.G.; Gómez-Hernández, J.J. Ensemble smoother with multiple data assimilation to simultaneously estimate the source location and the release history of a contaminant spill in an aquifer. J. Hydrol. 2021, 598, 126215. [Google Scholar] [CrossRef]
- Silva, T.M.D.; Bela, R.V.; Pesco, S.; Barreto, A. ES-MDA applied to estimate skin zone properties from injectivity tests data in multilayer reservoirs. Comput. Geosci. 2021, 146, 104635. [Google Scholar] [CrossRef]
- Todaro, V.; D’Oria, M.; Zanini, A.; Gómez-Hernández, J.J.; Tanda, M.G. Experimental sandbox tracer tests to characterize a two-facies aquifer via an ensemble smoother. Hydrogeol. J. 2023, 31, 1665–1678. [Google Scholar] [CrossRef]
- Cui, F.; Bao, J.C.; Cao, Z.D.; Li, L.P.; Zheng, Q. Soil hydraulic parameters estimation using ground penetrating radar data via ensemble smoother with multiple data assimilation. J. Hydrol. 2020, 583, 124552. [Google Scholar] [CrossRef]
- Xu, T.; Zhang, W.; Gómez-Hernández, J.J.; Xie, Y.; Yang, J.; Chen, Z.; Lu, C. Non-point contaminant source identification in an aquifer using the ensemble smoother with multiple data assimilation. J. Hydrol. 2022, 606, 127405. [Google Scholar] [CrossRef]
- Wang, Z.; Lu, W.; Chang, Z.; Wang, H. Simultaneous identification of groundwater contaminant source and simulation model parameters based on an ensemble Kalman filter—Adaptive step length ant colony optimization algorithm. J. Hydrol. 2022, 605, 127352. [Google Scholar] [CrossRef]
- Wang, Z.; Lu, W.; Chang, Z.; Luo, J. A combined search method based on a deep learning combined surrogate model for groundwater DNAPL contamination source identification. J. Hydrol. 2023, 616, 128854. [Google Scholar] [CrossRef]
- Hou, Z.; Lao, W.; Wang, Y.; Lu, W. Hybrid homotopy-PSO global searching approach with multi-kernel extreme learning machine for efficient source identification of DNAPL-polluted aquifer. Comput. Geosci. 2021, 155, 104837. [Google Scholar] [CrossRef]
- Jiang, S.; Zhang, Y.; Wang, P.; Zheng, M. An almost-parameter-free harmony search algorithm for groundwater pollution source identification. Water Sci. Technol. 2013, 68, 2359–2366. [Google Scholar] [CrossRef]
- Aral, M.M.; Guan, J.; Maslia, M.L. Identification of contaminant source location and release history in aquifers. J. Hydrol. Eng. 2001, 6, 225–234. [Google Scholar] [CrossRef]
- Chakraborty, A.; Prakash, O. Identification of clandestine groundwater pollution sources using heuristics optimization algorithms: A comparison between simulated annealing and particle swarm optimization. Environ. Monit. Assess. 2020, 192, 791. [Google Scholar] [CrossRef]
- Zhao, Y.; Qu, R.; Xing, Z.; Lu, W. Identifying groundwater contaminant sources based on a KELM surrogate model together with four heuristic optimization algorithms. Adv. Water Resour. 2020, 138, 103540. [Google Scholar] [CrossRef]
- Zhang, Q.; Wang, R.; Yang, J.; Ding, K.; Li, Y.; Hu, J. Collective decision optimization algorithm: A new heuristic optimization method. Neurocomputing 2017, 221, 123–137. [Google Scholar] [CrossRef]
- Li, J.; Lu, W.; Fan, Y. Groundwater pollution sources identification based on hybrid homotopy-genetic algorithm and simulation optimization. Environ. Eng. Sci. 2021, 38, 777–788. [Google Scholar] [CrossRef]
- Ayvaz, M.T. A linked simulation-optimization model for solving the unknown groundwater pollution source identification problems. J. Contam. Hydrol. 2010, 117, 46–59. [Google Scholar] [CrossRef] [PubMed]
- Xu, T.; Gomez-Hernandez, J.J. Joint identification of contaminant source location, initial release time, and initial solute concentration in an aquifer via ensemble Kalman filtering. Water Resour. Res. 2016, 52, 6587–6595. [Google Scholar] [CrossRef]
- Han, K.; Zuo, R.; Ni, P.; Xue, Z.; Xu, D.; Wang, J.; Zhang, D. Application of a genetic algorithm to groundwater pollution source identification. J. Hydrol. 2020, 589, 125343. [Google Scholar] [CrossRef]
- Bai, Y.; Lu, W.; Li, J.; Chang, Z.; Wang, H. Groundwater contamination source identification using improved differential evolution Markov chain algorithm. Environ. Sci. Pollut. Res. 2022, 29, 19679–19692. [Google Scholar] [CrossRef] [PubMed]
- Wang, H.; Lu, W.; Chang, Z.; Li, J. Heuristic search strategy based on probabilistic and geostatistical simulation approach for simultaneous identification of groundwater contaminant source and simulation model parameters. Stoch. Environ. Res. Risk Assess. 2020, 34, 891–907. [Google Scholar] [CrossRef]
- Anshuman, A.; Eldho, T.I. A parallel workflow framework using encoder-decoder LSTMs for uncertainty quantification in contaminant source identification in groundwater. J. Hydrol. 2023, 619, 129296. [Google Scholar] [CrossRef]
- Xing, Z.; Qu, R.; Zhao, Y.; Fu, Q.; Ji, Y.; Lu, W. Identifying the release history of a groundwater contaminant source based on an ensemble surrogate model. J. Hydrol. 2019, 572, 501–516. [Google Scholar] [CrossRef]
- Luo, J.; Liu, Y.; Li, X.; Xin, X.; Lu, W. Inversion of groundwater contamination source based on a two-stage adaptive surrogate model-assisted trust region genetic algorithm framework. Appl. Math. Model. 2022, 112, 262–281. [Google Scholar] [CrossRef]
- Yan, X.; Dong, W.; An, Y.; Lu, W. A Bayesian-based integrated approach for identifying groundwater contamination sources. J. Hydrol. 2019, 579, 124160. [Google Scholar] [CrossRef]
- Chang, Z.; Lu, W.; Wang, H.; Li, J.; Luo, J. Simultaneous identification of groundwater contaminant sources and simulation of model parameters based on an improved single-component adaptive Metropolis algorithm. Hydrogeol. J. 2021, 29, 859–873. [Google Scholar] [CrossRef]
- Li, J.; Lu, W.; Wang, H.; Bai, Y.; Fan, Y. Groundwater contamination sources identification based on kernel extreme learning machine and its effect due to wavelet denoising technique. Environ. Sci. Pollut. Res. 2020, 27, 34107–34120. [Google Scholar] [CrossRef] [PubMed]
- Chang, Z.; Lu, W.; Wang, Z. Study on source identification and source-sink relationship of LNAPLs pollution in groundwater by the adaptive cyclic improved iterative process and Monte Carlo stochastic simulation. J. Hydrol. 2022, 612, 128109. [Google Scholar] [CrossRef]
- Pan, Z.; Lu, W.; Bai, Y. Groundwater contamination source estimation based on a refined particle filter associated with a deep residual neural network surrogate. Hydrogeol. J. 2022, 30, 881–897. [Google Scholar] [CrossRef]
- Xia, X.; Jiang, S.; Zhou, N.; Cui, J.; Li, X. Groundwater contamination source identification and high-dimensional parameter inversion using residual dense convolutional neural network. J. Hydrol. 2023, 617, 129013. [Google Scholar] [CrossRef]
- Mo, S.; Zabaras, N.; Shi, X.; Wu, J. Deep autoregressive neural networks for high-dimensional inverse problems in groundwater contaminant source identification. Water Resour. Res. 2019, 55, 3856–3881. [Google Scholar] [CrossRef]
- Müller, J.; Park, J.; Sahu, R.; Varadharajan, C.; Arora, B.; Faybishenko, B.; Agarwal, D. Surrogate optimization of deep neural networks for groundwater predictions. J. Glob. Optim. 2021, 81, 203–231. [Google Scholar] [CrossRef]
- Li, Y.; Lu, W.; Pan, Z.; Wang, Z.; Dong, G. Simultaneous identification of groundwater contaminant source and hydraulic parameters based on multilayer perceptron and flying foxes optimization. Environ. Sci. Pollut. Res. 2023, 30, 78933–78947. [Google Scholar] [CrossRef]
- Huang, G.; Zhu, Q.; Siew, C.K. Extreme learning machine: Theory and applications. Neurocomputing 2006, 70, 489–501. [Google Scholar] [CrossRef]
- Huang, G. An insight into extreme learning machines: Random neurons, random features and kernels. Cogn. Comput. 2014, 6, 376–390. [Google Scholar] [CrossRef]
- Emerick, A.A.; Reynolds, A.C. Ensemble smoother with multiple data assimilation. Comput. Geosci. 2013, 55, 3–15. [Google Scholar] [CrossRef]
- Evensen, G. Analysis of iterative ensemble smoothers for solving inverse problems. Comput. Geosci. 2018, 22, 885–908. [Google Scholar] [CrossRef]
- Wang, Z.; Lu, W.; Chang, Z.; Zhang, T. Joint identification of groundwater pollution source information, model parameters, and boundary conditions based on a novel ES-MDA with a wheel battle strategy. J. Hydrol. 2024, 636, 131320. [Google Scholar] [CrossRef]
- Zhang, J.; Zheng, Q.; Chen, D.; Wu, L.; Zeng, L. Surrogate-Based Bayesian Inverse Modeling of the Hydrological System: An Adaptive Approach Considering Surrogate Approximation Error. Water Resour. Res. 2020, 56, e2019WR025721. [Google Scholar] [CrossRef]
- Zhang, D.; Lu, Z. An efficient, high-order perturbation approach for flow in random porous media via Karhunen-Loeve and polynomial expansions. J. Comput. Phys. 2004, 194, 773–794. [Google Scholar] [CrossRef]
- Li, J.; Lu, W.; Luo, J. Groundwater contamination sources identification based on the Long-Short Term Memory network. J. Hydrol. 2021, 601, 126670. [Google Scholar] [CrossRef]
- Wang, H.; Lu, W. Groundwater contamination source-sink analysis based on random statistical method for a practical case. Stoch. Environ. Res. Risk Assess. 2022, 36, 4157–4174. [Google Scholar] [CrossRef]
Unknown Variable | Reference Value | Initial Range | Only the First-Stage Inversion Process Result | Only the Second-Stage Inversion Process Result | The Two-Stage Inversion Framework Result |
---|---|---|---|---|---|
Sx [L] | 3.99 | U [3, 5] | 3.95 | 3.95 | 3.96 |
Sy [L] | 4.71 | U [4, 6] | 4.72 | 4.72 | 4.71 |
RI1 [MT−1] | 4.90 | U [0, 8] | 4.75 | 4.72 | 4.98 |
RI2 [MT−1] | 3.65 | U [0, 8] | 3.72 | 3.99 | 3.46 |
RI3 [MT−1] | 2.36 | U [0, 8] | 3.16 | 2.66 | 2.67 |
RI4 [MT−1] | 6.70 | U [0, 8] | 5.00 | 5.46 | 6.38 |
RI5 [MT−1] | 2.78 | U [0, 8] | 4.73 | 4.38 | 3.15 |
RI6 [MT−1] | 7.76 | U [0, 8] | 6.41 | 6.68 | 7.50 |
BC [ML−3] | 0.84 | U [0.6, 1.2] | 0.88 | 0.90 | 0.86 |
Indicator | KELM Surrogate Model | MLP Surrogate Model |
---|---|---|
R2 | 0.9577 | 0.9860 |
MRE (%) | 13.07 | 9.72 |
MAE [ML−3] | 0.2379 | 0.1727 |
RMSE [ML−3] | 0.82 | 0.47 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, Z.; Lu, W. Groundwater Contamination Source Recognition Based on a Two-Stage Inversion Framework with a Deep Learning Surrogate. Water 2024, 16, 1907. https://doi.org/10.3390/w16131907
Wang Z, Lu W. Groundwater Contamination Source Recognition Based on a Two-Stage Inversion Framework with a Deep Learning Surrogate. Water. 2024; 16(13):1907. https://doi.org/10.3390/w16131907
Chicago/Turabian StyleWang, Zibo, and Wenxi Lu. 2024. "Groundwater Contamination Source Recognition Based on a Two-Stage Inversion Framework with a Deep Learning Surrogate" Water 16, no. 13: 1907. https://doi.org/10.3390/w16131907
APA StyleWang, Z., & Lu, W. (2024). Groundwater Contamination Source Recognition Based on a Two-Stage Inversion Framework with a Deep Learning Surrogate. Water, 16(13), 1907. https://doi.org/10.3390/w16131907