Articles | Volume 29, issue 17
https://doi.org/10.5194/hess-29-4251-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-29-4251-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
10 Sep 2025
Research article |
| 10 Sep 2025
| 10 Sep 2025
Enhancing inverse modeling in groundwater systems through machine learning: a comprehensive comparative study
Junjun Chen
National and Local Joint Engineering Laboratory of Internet Application Technology on Mine, China University of Mining and Technology, Xuzhou, 221008, China
College of Construction Engineering, Jilin University, Changchun, 130026, China
Zhenxue Dai
CORRESPONDING AUTHOR
College of Construction Engineering, Jilin University, Changchun, 130026, China
School of Environmental and Municipal Engineering, Qingdao University of Technology, Qingdao, 273400, China
Shangxian Yin
CORRESPONDING AUTHOR
College of Safety Engineering, North China Institute of Science and Technology, Langfang, 065201, China
Mingkun Zhang
Shandong Ruyi Technology Group Co., Ltd., Jinan, 250000, China
Mohamad Reza Soltanian
Departments of Geosciences and Environmental Engineering, University of Cincinnati, Cincinnati, OH 45220, USA
Related authors
No articles found.
Xiaoying Zhang, Fan Dong, Guangquan Chen, and Zhenxue Dai
Hydrol. Earth Syst. Sci., 27, 83–96, https://doi.org/10.5194/hess-27-83-2023, https://doi.org/10.5194/hess-27-83-2023, 2023
Short summary
Short summary
In a data-driven framework, groundwater levels can generally only be calculated 1 time step ahead. We discuss the advance prediction with longer forecast periods rather than single time steps by constructing a model based on a temporal convolutional network. Model accuracy and efficiency were further compared with an LSTM-based model. The two models derived in this study can help people cope with the uncertainty of what might occur in hydrological scenarios under the threat of climate change.
Huijun Li, Lin Zhu, Gaoxuan Guo, Yan Zhang, Zhenxue Dai, Xiaojuan Li, Linzhen Chang, and Pietro Teatini
Nat. Hazards Earth Syst. Sci., 21, 823–835, https://doi.org/10.5194/nhess-21-823-2021, https://doi.org/10.5194/nhess-21-823-2021, 2021
Short summary
Short summary
We propose a method that integrates fuzzy set theory and a weighted Bayesian model to evaluate the hazard probability of land subsidence based on Interferometric Synthetic Aperture Radar technology. The proposed model can represent the uncertainty and ambiguity in the evaluation process, and results can be compared to traditional qualitative methods.
Cited articles
Abbas, S. A., Bailey, R. T., White, J. T., Arnold, J. G., White, M. J., Čerkasova, N., and Gao, J.: A framework for parameter estimation, sensitivity analysis, and uncertainty analysis for holistic hydrologic modeling using SWAT+, Hydrol. Earth Syst. Sci., 28, 21–48, https://doi.org/10.5194/hess-28-21-2024, 2024.
Adler, J. and Öktem, O.: Solving ill-posed inverse problems using iterative deep neural networks, Inverse Probl., 33, 124007, https://doi.org/10.1088/1361-6420/aa9581, 2017.
Arsenault, R. and Brissette, F. P.: Continuous streamflow prediction in ungauged basins: The effects of equifinality and parameter set selection on uncertainty in regionalization approaches, Water Resour. Res., 50, 6135–6153, https://doi.org/10.1002/2013wr014898, 2014.
Bandai, T. and Ghezzehei, T. A.: Forward and inverse modeling of water flow in unsaturated soils with discontinuous hydraulic conductivities using physics-informed neural networks with domain decomposition, Hydrol. Earth Syst. Sci., 26, 4469–4495, https://doi.org/10.5194/hess-26-4469-2022, 2022.
Bao, J., Li, L., and Redoloza, F.: Coupling ensemble smoother and deep learning with generative adversarial networks to deal with non-Gaussianity in flow and transport data assimilation, J. Hydrol., 590, 125443, https://doi.org/10.1016/j.jhydrol.2020.125443, 2020.
Bentivoglio, R., Isufi, E., Jonkman, S. N., and Taormina, R.: Deep learning methods for flood mapping: a review of existing applications and future research directions, Hydrol. Earth Syst. Sci., 26, 4345–4378, https://doi.org/10.5194/hess-26-4345-2022, 2022.
Beven, K. and Binley, A.: The future of distributed models: Model calibration and uncertainty prediction, Hydrol. Process., 6, 279–298, https://doi.org/10.1002/hyp.3360060305, 1992.
Blasone, R.-S., Madsen, H., and Rosbjerg, D.: Parameter estimation in distributed hydrological modelling: comparison of global and local optimisation techniques, Hydrol. Res., 38, 451–476, https://doi.org/10.2166/nh.2007.024, 2007.
Botto, A., Belluco, E., and Camporese, M.: Multi-source data assimilation for physically based hydrological modeling of an experimental hillslope, Hydrol. Earth Syst. Sci., 22, 4251–4266, https://doi.org/10.5194/hess-22-4251-2018, 2018.
Cao, M., Dai, Z., Chen, J., Yin, H., Zhang, X., Wu, J., Thanh, H. V., and Soltanian, M. R.: An integrated framework of deep learning and entropy theory for enhanced high-dimensional permeability field identification in heterogeneous aquifers, Water Res., 268, 122706, https://doi.org/10.1016/j.watres.2024.122706, 2025.
Carrera, J. and Glorioso, L.: On geostatistical formulations of the groundwater flow inverse problem, Adv. Water Resour., 14, 273–283, https://doi.org/10.1016/0309-1708(91)90039-Q, 1991.
Castaings, W., Dartus, D., Le Dimet, F.-X., and Saulnier, G.-M.: Sensitivity analysis and parameter estimation for distributed hydrological modeling: potential of variational methods, Hydrol. Earth Syst. Sci., 13, 503–517, https://doi.org/10.5194/hess-13-503-2009, 2009.
Chang, H. and Zhang, D.: Identification of physical processes via combined data-driven and data-assimilation methods, J. Comput. Phys., 393, 337–350, https://doi.org/10.1016/j.jcp.2019.05.008, 2019.
Chang, Z., Lu, W., and 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., 612, 128109, https://doi.org/10.1016/j.jhydrol.2022.128109, 2022.
Chen, J., Dai, Z., Yang, Z., Pan, Y., Zhang, X., Wu, J., and Reza Soltanian, M.: An improved tandem neural network architecture for inverse modeling of multicomponent reactive transport in porous media, Water Resour. Res., 57, 2021WR030595, https://doi.org/10.1029/2021wr030595, 2021.
Chen, J., Dai, Z., Dong, S., Zhang, X., Sun, G., Wu, J., Ershadnia, R., Yin, S., and Soltanian, M. R.: Integration of deep learning and information theory for designing monitoring networks in heterogeneous aquifer systems, Water Resour. Res., 58, 2022WR032429, https://doi.org/10.1029/2022wr032429, 2022.
Chen, J., Dai, Z., Yin, S., Zhang, M., and Soltanian, M. R.: Enhancing Inverse Modeling in Groundwater Systems through Machine Learning: A Comprehensive Comparative Study, Zenodo [data set], https://doi.org/10.5281/zenodo.10499582, 2024.
Chen, X., Hammond, G. E., Murray, C. J., Rockhold, M. L., Vermeul, V. R., and Zachara, J. M.: Application of ensemble-based data assimilation techniques for aquifer characterization using tracer data at Hanford 300 area, Water Resour. Res., 49, 7064–7076, https://doi.org/10.1002/2012wr013285, 2013.
Dai, Z. and Samper, J.: Inverse problem of multicomponent reactive chemical transport in porous media: Formulation and applications, Water Resour. Res., 40, W07407, https://doi.org/10.1029/2004wr003248, 2004.
Dai, Z. and Samper, J.: Inverse modeling of water flow and multicomponent reactive transport in coastal aquifer systems, J. Hydrol., 447–461, https://doi.org/10.1016/j.jhydrol.2005.11.052, 2006.
Dragonetti, G., Comegna, A., Ajeel, A., Deidda, G. P., Lamaddalena, N., Rodriguez, G., Vignoli, G., and Coppola, A.: Calibrating electromagnetic induction conductivities with time-domain reflectometry measurements, Hydrol. Earth Syst. Sci., 22, 1509–1523, https://doi.org/10.5194/hess-22-1509-2018, 2018.
Eberhart, R. and Kennedy, J.: Particle swarm optimization, in: Proceedings of the IEEE international conference on neural networks, Perth, Western Australia, Australia, 27 November 1995, 1942–1948, https://doi.org/10.1109/ICNN.1995.488968, 1995.
Elfwing, S., Uchibe, E., and Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning, Neural Networks, 107, 3–11, https://doi.org/10.1016/j.neunet.2017.12.012, 2018.
Epp, R., Schmid, F., and Jenny, P.: Fast convergence strategy for ambiguous inverse problems based on hierarchical regularization, J. Comput. Phys., 489, 112264, https://doi.org/10.1016/j.jcp.2023.112264, 2023.
Ghelichkhan, S., Gibson, A., Davies, D. R., Kramer, S. C., and Ham, D. A.: Automatic adjoint-based inversion schemes for geodynamics: reconstructing the evolution of Earth's mantle in space and time, Geosci. Model Dev., 17, 5057–5086, https://doi.org/10.5194/gmd-17-5057-2024, 2024.
Ginn, T. R. and Cushman, J. H.: Inverse methods for subsurface flow: A critical review of stochastic techniques, Stoch. Hydrol. Hydraul., 4, 1–26, https://doi.org/10.1007/BF01547729, 1990.
Giudici, M.: Some Remarks About Forward and Inverse Modelling in Hydrology, Within a General Conceptual Framework, Hydrology, 11, 189, https://doi.org/10.3390/hydrology11110189, 2024.
Goodfellow, I., Bengio, Y., and Courville, A.: Deep learning, MIT press, Cambridge, MA, USA, 800 pp., ISBN 9780262337373, 2016.
Guo, Q., Liu, M., and Luo, J.: Predictive Deep Learning for High-Dimensional Inverse Modeling of Hydraulic Tomography in Gaussian and Non-Gaussian Fields, Water Resour. Res., 59, 2023WR035408, https://doi.org/10.1029/2023wr035408, 2023.
He, K., Zhang, X., Ren, S., and Sun, J.: Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA, 27-30 June 2016, 770–778, https://doi.org/10.1109/CVPR.2016.90, 2016.
Hinton, G. E. and Salakhutdinov, R. R.: Reducing the dimensionality of data with neural networks, Science, 313, 504–507, https://doi.org/10.1126/science.1127647, 2006.
Holland John, H.: Adaptation in natural and artificial systems, University of Michigan Press, Ann Arbor, ISBN 10 0472084607, 13 978-0472084609, 1975.
Hopmans, J. W., Šimùnek, J., Romano, N., and Durner, W.: 3.6.2. Inverse Methods, in: Methods of Soil Analysis, edited by: Dane, J. H. and Clarke Topp, G., Wiley, 963–1008, https://doi.org/10.2136/sssabookser5.4.c40, 2002.
Ines, A. V. M. and Droogers, P.: Inverse modelling in estimating soil hydraulic functions: a Genetic Algorithm approach, Hydrol. Earth Syst. Sci., 6, 49–66, https://doi.org/10.5194/hess-6-49-2002, 2002.
Jardani, A., Vu, T. M., and Fischer, P.: Use of convolutional neural networks with encoder-decoder structure for predicting the inverse operator in hydraulic tomography, J. Hydrol., 604, 127233, https://doi.org/10.1016/j.jhydrol.2021.127233, 2022.
Jaumann, S. and Roth, K.: Soil hydraulic material properties and layered architecture from time-lapse GPR, Hydrol. Earth Syst. Sci., 22, 2551–2573, https://doi.org/10.5194/hess-22-2551-2018, 2018.
Jose, S. C., Rahman, M. A., and Cirpka, O. A.: Large-scale sandbox experiment on longitudinal effective dispersion in heterogeneous porous media, Water Resour. Res., 40, W12415, https://doi.org/10.1029/2004wr003363, 2004.
Kabala, Z. J. and Skaggs, T. H.: Comment on “Minimum relative entropy inversion: Theory and application to recovering the release history of a groundwater contaminant” by Allan, D. Woodbury and Tadeusz, J. Ulrych, Water Resour. Res., 34, 2077–2079, https://doi.org/10.1029/98WR01337, 1998.
Kapsoulis, D., Tsiakas, K., Trompoukis, X., Asouti, V., and Giannakoglou, K.: A PCA-assisted hybrid algorithm combining EAs and adjoint methods for CFD-based optimization, Appl. Soft Comput., 73, 520–529, https://doi.org/10.1016/j.asoc.2018.09.002, 2018.
Keum, J., Coulibaly, P., Razavi, T., Tapsoba, D., Gobena, A., Weber, F., and Pietroniro, A.: Application of SNODAS and hydrologic models to enhance entropy-based snow monitoring network design, J. Hydrol., 561, 688–701, https://doi.org/10.1016/j.jhydrol.2018.04.037, 2018.
Kirkpatrick, S., Gelatt, C. D., and Vecchi, M. P.: Optimization by Simulated Annealing, Science, 220, 671–680, https://doi.org/10.1126/science.220.4598.671, 1983.
Kool, J. B., Parker, J. C., and van Genuchten, M. T.: Parameter estimation for unsaturated flow and transport models-A review, J. Hydrol., 91, 255–293, https://doi.org/10.1016/0022-1694(87)90207-1, 1987.
Kuang, W., Yuan, C., and Zhang, J.: Real-time determination of earthquake focal mechanism via deep learning, Nat. Commun., 12, 1432, https://doi.org/10.1038/s41467-021-21670-x, 2021.
LeCun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, https://doi.org/10.1038/nature14539, 2015.
Li, E.: An adaptive surrogate assisted differential evolutionary algorithm for high dimensional constrained problems, Appl. Soft Comput., 85, 105752, https://doi.org/10.1016/j.asoc.2019.105752, 2019.
Lindsay, A., McCloskey, J., and Bhloscaidh, M. N.: Using a genetic algorithm to estimate the details of earthquake slip distributions from point surface displacements, J. Geophys. Res.-Sol. Ea., 121, 1796–1820, https://doi.org/10.1002/2015jb012181, 2016.
Liu, D., Tan, Y., Khoram, E., and Yu, Z.: Training deep neural networks for the inverse design of nanophotonic structures, ACS Photonics, 5, 1365–1369, https://doi.org/10.1021/acsphotonics.7b01377, 2018.
Liu, M., Ahmad, R., Cai, W., and Mukerji, T.: Hierarchical Homogenization With Deep-Learning-Based Surrogate Model for Rapid Estimation of Effective Permeability From Digital Rocks, J. Geophys. Res.-Sol. Ea., 128, e2022JB025378, https://doi.org/10.1029/2022jb025378, 2023.
Loève, M.: Probability Theory, Van Nostrand, New York, 1955.
Long, Y., Ren, J., Li, Y., and Chen, H.: Inverse design of photonic topological state via machine learning, Appl. Phys. Lett., 114, 181105, https://doi.org/10.1063/1.5094838, 2019.
Luo, J., Ma, X., Ji, Y., Li, X., Song, Z., and Lu, W.: Review of machine learning-based surrogate models of groundwater contaminant modeling, Environ. Res., 238, 117268, https://doi.org/10.1016/j.envres.2023.117268, 2023.
Ma, J., Xia, D., Guo, H., Wang, Y., Niu, X., Liu, Z., and Jiang, S.: Metaheuristic-based support vector regression for landslide displacement prediction: a comparative study, Landslides, 19, 2489–2511, https://doi.org/10.1007/s10346-022-01923-6, 2022.
Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., and Frey, B.: Adversarial autoencoders, arXiv [preprint], https://doi.org/10.48550/arXiv.1511.05644, 2015.
Mariethoz, G. and Caers, J.: Multiple-point geostatistics: stochastic modeling with training images, Wiley Blackwell, 364 pp., https://doi.org/10.1002/9781118662953, 2014.
Mariethoz, G., Renard, P., and Straubhaar, J.: The Direct Sampling method to perform multiple-point geostatistical simulations, Water Resour. Res., 46, W11536, https://doi.org/10.1029/2008WR007621, 2010.
McLaughlin, D. and Townley, L. R.: A Reassessment of the Groundwater Inverse Problem, 32, 1131–1161, https://doi.org/10.1029/96WR00160, 1996.
Metropolis, N., Rosenbluth, A. W., Rosenbluth, M. N., Teller, A. H., and Teller, E.: Equation of state calculations by fast computing machines, J. Chem. Phys., 21, 1087–1092, https://doi.org/10.1063/1.1699114, 1953.
Mo, S., Zabaras, N., Shi, X., and Wu, J.: Deep autoregressive neural networks for high-dimensional inverse problems in groundwater contaminant source identification, Water Resour. Res., 55, 3856–3881, https://doi.org/10.1029/2018wr024638, 2019.
Mo, S., Zabaras, N., Shi, X., and Wu, J.: Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non-Gaussian hydraulic conductivities, Water Resour. Res., 56, 2019WR026082, https://doi.org/10.1029/2019WR026082, 2020.
Neupauer, R. M., Borchers, B., and Wilson, J. L.: Comparison of inverse methods for reconstructing the release history of a groundwater contamination source, Water Resour. Res., 36, 2469–2475, https://doi.org/10.1029/2000WR900176, 2000.
Nhu, V. H.: Levenberg–Marquardt method for ill-posed inverse problems with possibly non-smooth forward mappings between Banach spaces, Inverse Probl., 38, 015007, https://doi.org/10.1088/1361-6420/ac38b7, 2022.
Pérez-Cruz, F., Camps-Valls, G., Soria-Olivas, E., Pérez-Ruixo, J. J., Figueiras-Vidal, A. R., and Artés-Rodríguez, A.: Multi-dimensional Function Approximation and Regression Estimation, Artificial Neural Networks – ICANN 2002, Berlin, Heidelberg, 757–762, https://doi.org/10.1007/3-540-46084-5_123, 2002.
Plessix, R.: A review of the adjoint-state method for computing the gradient of a functional with geophysical applications, Geophys. J. Int., 167, 495–503, https://doi.org/10.1111/j.1365-246X.2006.02978.x, 2006.
Qin, Y., Kavetski, D., Kuczera, G., McInerney, D., Yang, T., and Guo, Y.: Can Gauss-Newton Algorithms Outperform Stochastic Optimization Algorithms When Calibrating a Highly Parameterized Hydrological Model? A Case Study Using SWAT, Water Resour. Res., 58, e2021WR031532, https://doi.org/10.1029/2021wr031532, 2022.
Rafiei, V., Nejadhashemi, A. P., Mushtaq, S., Bailey, R. T., and An-Vo, D.-A.: An improved calibration technique to address high dimensionality and non-linearity in integrated groundwater and surface water models, Environ. Modell. Softw., 149, 105312, https://doi.org/10.1016/j.envsoft.2022.105312, 2022.
Razavi, S., Tolson, B. A., and Burn, D. H.: Review of surrogate modeling in water resources, Water Resour. Res., 48, W07401, https://doi.org/10.1029/2011wr011527, 2012.
Sanchez-Fernandez, M., de-Prado-Cumplido, M., Arenas-Garcia, J., and Perez-Cruz, F.: SVM multiregression for nonlinear channel estimation in multiple-input multiple-output systems, IEEE T. Signal Proces., 52, 2298–2307, https://doi.org/10.1109/tsp.2004.831028, 2004.
Sanchez-Vila, X., Donado, L. D., Guadagnini, A., and Carrera, J.: A solution for multicomponent reactive transport under equilibrium and kinetic reactions, Water Resour. Res., 46, W07539, https://doi.org/10.1029/2009wr008439, 2010.
Scharnagl, B., Vrugt, J. A., Vereecken, H., and Herbst, M.: Inverse modelling of in situ soil water dynamics: investigating the effect of different prior distributions of the soil hydraulic parameters, Hydrol. Earth Syst. Sci., 15, 3043–3059, https://doi.org/10.5194/hess-15-3043-2011, 2011.
Schneider-Zapp, K., Ippisch, O., and Roth, K.: Numerical study of the evaporation process and parameter estimation analysis of an evaporation experiment, Hydrol. Earth Syst. Sci., 14, 765–781, https://doi.org/10.5194/hess-14-765-2010, 2010.
Shen, C., Appling, A. P., Gentine, P., Bandai, T., Gupta, H., Tartakovsky, A., Baity-Jesi, M., Fenicia, F., Kifer, D., Li, L., Liu, X., Ren, W., Zheng, Y., Harman, C. J., Clark, M., Farthing, M., Feng, D., Kumar, P., Aboelyazeed, D., Rahmani, F., Song, Y., Beck, H. E., Bindas, T., Dwivedi, D., Fang, K., Höge, M., Rackauckas, C., Mohanty, B., Roy, T., Xu, C., and Lawson, K.: Differentiable modelling to unify machine learning and physical models for geosciences, Nature Reviews Earth and Environment, 4, 552–567, https://doi.org/10.1038/s43017-023-00450-9, 2023.
Sorensen, J. P. R. and Butcher, A. S.: Water Level Monitoring Pressure Transducers – A Need for Industry-Wide Standards, Groundwater Monitoring and Remediation, 31, 56–62, https://doi.org/10.1111/j.1745-6592.2011.01346.x, 2011.
Steefel, C., Depaolo, D., and Lichtner, P.: Reactive transport modeling: An essential tool and a new research approach for the earth sciences, Earth Planet. Sc. Lett., 240, 539–558, https://doi.org/10.1016/j.epsl.2005.09.017, 2005.
Sternagel, A., Loritz, R., Klaus, J., Berkowitz, B., and Zehe, E.: Simulation of reactive solute transport in the critical zone: a Lagrangian model for transient flow and preferential transport, Hydrol. Earth Syst. Sci., 25, 1483–1508, https://doi.org/10.5194/hess-25-1483-2021, 2021.
Storn, R. and Price, K.: Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces, J. Global Optim., 11, 341–359, https://doi.org/10.1023/A:1008202821328, 1997.
Sun, A. Y.: Discovering state-parameter mappings in subsurface models using generative adversarial networks, Geophys. Res. Lett., 45, 11137–11146, https://doi.org/10.1029/2018gl080404, 2018.
Sun, N.: Inverse problems in groundwater modeling, Springer Science and Business Media, 338 pp., https://doi.org/10.1007/978-94-017-1970-4, 2013.
Tran, H.-N., Phan, G. T. T., Do, Q. B., and Tran, V.-P.: Comparative evaluation of the performance of improved genetic algorithms and differential evolution for in-core fuel management of a research reactor, Nucl. Eng. Des., 398, 111953, https://doi.org/10.1016/j.nucengdes.2022.111953, 2022.
Travaš, V., Zaharija, L., Stipanić, D., and Družeta, S.: Estimation of hydraulic conductivity functions in karst regions by particle swarm optimization with application to Lake Vrana, Croatia, Hydrol. Earth Syst. Sci., 27, 1343–1359, https://doi.org/10.5194/hess-27-1343-2023, 2023.
Tsai, F. T. C., Sun, N., and Yeh, W. W. G.: Global-local optimization for parameter structure identification in three-dimensional groundwater modeling, Water Resour. Res., 39, 1043, https://doi.org/10.1029/2001wr001135, 2003.
Tuia, D., Verrelst, J., Alonso, L., Perez-Cruz, F., and Camps-Valls, G.: Multioutput support vector regression for remote sensing biophysical parameter estimation, IEEE Geosci. Remote S., 8, 804–808, https://doi.org/10.1109/lgrs.2011.2109934, 2011.
Vrugt, J. A.: Markov chain Monte Carlo simulation using the DREAM software package: Theory, concepts, and MATLAB implementation, Environ. Modell. Softw., 75, 273–316, https://doi.org/10.1016/j.envsoft.2015.08.013, 2016.
Wang, G. S. and Chen, S. L.: Evaluation of a soil greenhouse gas emission model based on Bayesian inference and MCMC: Parameter identifiability and equifinality, Ecol. Model., 253, 107–116, https://doi.org/10.1016/j.ecolmodel.2012.09.011, 2013.
Wang, N., Chang, H., and Zhang, D.: Deep-learning-based inverse modeling approaches: A subsurface flow example, J. Geophys. Res.-Sol. Ea., 126, 2020JB020549, https://doi.org/10.1029/2020jb020549, 2021.
Wang, Y., Fang, Z., and Hong, H.: Comparison of convolutional neural networks for landslide susceptibility mapping in Yanshan County, China, Sci. Total Environ., 666, 975–993, https://doi.org/10.1016/j.scitotenv.2019.02.263, 2019.
Xia, C.-A., Luo, X., Hu, B. X., Riva, M., and Guadagnini, A.: Data assimilation with multiple types of observation boreholes via the ensemble Kalman filter embedded within stochastic moment equations, Hydrol. Earth Syst. Sci., 25, 1689–1709, https://doi.org/10.5194/hess-25-1689-2021, 2021.
Xiao, C., Deng, Y., and Wang, G.: Deep-Learning-Based Adjoint State Method: Methodology and Preliminary Application to Inverse Modeling, Water Resour. Res., 57, 2020WR027400, https://doi.org/10.1029/2020wr027400, 2021.
Xu, T., Spycher, N., Sonnenthal, E., Zhang, G., Zheng, L., and Pruess, K.: TOUGHREACT Version 2.0: A simulator for subsurface reactive transport under non-isothermal multiphase flow conditions, Comput. Geosci., 37, 763–774, https://doi.org/10.1016/j.cageo.2010.10.007, 2011.
Xu, Z., Serata, R., Wainwright, H., Denham, M., Molins, S., Gonzalez-Raymat, H., Lipnikov, K., Moulton, J. D., and Eddy-Dilek, C.: Reactive transport modeling for supporting climate resilience at groundwater contamination sites, Hydrol. Earth Syst. Sci., 26, 755–773, https://doi.org/10.5194/hess-26-755-2022, 2022.
Yan, Z., Ran, J., Xiao, Y., Xu, Z., Wu, H., Deng, X. L., Du, L., and Zhong, M.: The Temporal Improvement of Earth's Mass Transport Estimated by Coupling GRACE-FO With a Chinese Polar Gravity Satellite Mission, J. Geophys. Res.-Sol. Ea., 128, e2023JB027157, https://doi.org/10.1029/2023jb027157, 2023.
Yang, X., Chen, X., and Smith, M. M.: Deep learning inversion of gravity data for detection of CO2 plumes in overlying aquifers, J. Appl. Geophys., 196, 104507, https://doi.org/10.1016/j.jappgeo.2021.104507, 2022.
Yeh, W. W.-G.: Review of Parameter Identification Procedures in Groundwater Hydrology: The Inverse Problem, Water Resour. Res., 22, 95–108, https://doi.org/10.1029/WR022i002p00095, 1986.
Yeung, C., Tsai, J.-M., King, B., Pham, B., Ho, D., Liang, J., Knight, M. W., and Raman, A. P.: Multiplexed supercell metasurface design and optimization with tandem residual networks, Nanophotonics, 10, 1133–1143, https://doi.org/10.1515/nanoph-2020-0549, 2021.
Yu, S. and Ma, J.: Deep Learning for Geophysics: Current and Future Trends, Rev. Geophys., 59, e2021RG000742, https://doi.org/10.1029/2021rg000742, 2021.
Zhan, C., Dai, Z., Soltanian, M. R., and Zhang, X.: Stage-wise stochastic deep learning inversion framework for subsurface sedimentary structure identification, Geophys. Res. Lett., 49, 2021GL095823, https://doi.org/10.1029/2021gl095823, 2021.
Zhan, C., Dai, Z., Yang, Z., Zhang, X., Ma, Z., Thanh, H. V., and Soltanian, M. R.: Subsurface sedimentary structure identification using deep learning: A review, Earth-Sci. Rev., 239, 104370, https://doi.org/10.1016/j.earscirev.2023.104370, 2023.
Zhang, D. X. and Lu, Z. M.: An efficient, high-order perturbation approach for flow in random porous media via Karhunen–Loeve and polynomial expansions, J. Comput. Phys., 194, 773–794, https://doi.org/10.1016/j.jcp.2003.09.015, 2004.
Zhang, J., Zeng, L., Chen, C., Chen, D., and Wu, L.: Efficient Bayesian experimental design for contaminant source identification, Water Resour. Res., 51, 576–598, https://doi.org/10.1002/2014wr015740, 2015.
Zhang, J., Lin, G., Li, W., Wu, L., and Zeng, L.: An iterative local updating ensemble smoother for estimation and uncertainty assessment of hydrologic model parameters with multimodal distributions, Water Resour. Res., 54, 1716–1733, https://doi.org/10.1002/2017wr020906, 2018.
Zhang, J., Cao, C., Nan, T., Ju, L., Zhou, H., and Zeng, L.: A Novel Deep Learning Approach for Data Assimilation of Complex Hydrological Systems, Water Resour. Res., 60, e2023WR035389, https://doi.org/10.1029/2023WR035389, 2024.
Zheng, L. and Samper, J.: Formulation of the inverse problem of non-isothermal multiphase flow and reactive transport in porous media, in: Developments in Water Science, edited by: Miller, C. T. and Pinder, G. F., Elsevier, 1317–1327, https://doi.org/10.1016/S0167-5648(04)80146-1, 2004.
Zhou, H., Gómez-Hernández, J. J., and Li, L.: Inverse methods in hydrogeology: Evolution and recent trends, Adv. Water Resour., 63, 22–37, https://doi.org/10.1016/j.advwatres.2013.10.014, 2014.
Short summary
Balancing exploration and exploitation in conventional inversion algorithms is challenging. We evaluated the effectiveness of tandem neural network architecture (TNNA) in addressing this challenge. Inversion problems with different heterogeneous scenarios were designed to compare TNNA with four metaheuristic algorithms. Results show that TNNA significantly improves computational efficiency and accuracy, offering a promising framework for developing robust inversion algorithms.
Balancing exploration and exploitation in conventional inversion algorithms is challenging. We...
