Articles | Volume 29, issue 20
https://doi.org/10.5194/hess-29-5719-2025
© 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-29-5719-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
24 Oct 2025
Research article |
| 24 Oct 2025
| 24 Oct 2025
Synergistic identification of hydrogeological parameters and pollution source information for groundwater point and areal source contamination based on machine learning surrogate–artificial hummingbird algorithm
Chengming Luo
College of Civil Engineering, Tongji University, 1239 Siping Road, Shanghai 200092, China
College of Civil Engineering, Tongji University, 1239 Siping Road, Shanghai 200092, China
Department of Earth and Environmental Sciences, University of Waterloo, ON N2L 3G1, Canada
Y. Jun Xu
School of Renewable Natural Resources, Louisiana State University Agricultural Center, Baton Rouge, Louisiana, USA
Shunqing Jia
College of Civil Engineering, Tongji University, 1239 Siping Road, Shanghai 200092, China
Zejun Liu
College of Civil Engineering, Tongji University, 1239 Siping Road, Shanghai 200092, China
Boyang Mao
College of Civil Engineering, Tongji University, 1239 Siping Road, Shanghai 200092, China
Qinya Lv
College of Civil Engineering, Tongji University, 1239 Siping Road, Shanghai 200092, China
Xuming Ji
College of Civil Engineering, Tongji University, 1239 Siping Road, Shanghai 200092, China
Yanxin Rong
College of Civil Engineering, Tongji University, 1239 Siping Road, Shanghai 200092, China
Yan Dai
College of Civil Engineering, Tongji University, 1239 Siping Road, Shanghai 200092, China
Related authors
Chenyi Shi, Xihua Wang, Y. Jun Xu, Chaomeng Dai, Nianqing Zhou, Rongbing Fu, Chengming Luo, Boyang Mao, Shunqing Jia, Qinya Lv, Zejun Liu, Xuming Ji, Yan Dai, and Yanxin Rong
EGUsphere, https://doi.org/10.5194/egusphere-2026-3574, https://doi.org/10.5194/egusphere-2026-3574, 2026
This preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).
Short summary
Short summary
We studied how nitrogen pollution changed in 3,020 lakes across China from 2010 to 2024 using monitoring records, environmental data, and machine learning. We found that lakes with high nitrogen today are not always the ones getting worse over time. Total nitrogen changed slowly and was shaped by both climate and long-term pollution buildup, while ammonia nitrogen responded rapidly to pollution control. These results show lake management should target both current pollution and future change.
Chenyi Shi, Xihua Wang, Y. Jun Xu, Chaomeng Dai, Nianqing Zhou, Rongbing Fu, Chengming Luo, Boyang Mao, Shunqing Jia, Qinya Lv, Zejun Liu, Xuming Ji, Yan Dai, and Yanxin Rong
EGUsphere, https://doi.org/10.5194/egusphere-2026-3574, https://doi.org/10.5194/egusphere-2026-3574, 2026
This preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).
Short summary
Short summary
We studied how nitrogen pollution changed in 3,020 lakes across China from 2010 to 2024 using monitoring records, environmental data, and machine learning. We found that lakes with high nitrogen today are not always the ones getting worse over time. Total nitrogen changed slowly and was shaped by both climate and long-term pollution buildup, while ammonia nitrogen responded rapidly to pollution control. These results show lake management should target both current pollution and future change.
Boting Hu, Liwen Chen, Yanfeng Wu, Jingxuan Sun, Y. Jun Xu, Qingsong Zhang, and Guangxin Zhang
Hydrol. Earth Syst. Sci., 29, 6023–6041, https://doi.org/10.5194/hess-29-6023-2025, https://doi.org/10.5194/hess-29-6023-2025, 2025
Short summary
Short summary
This study presents a novel framework for accurately quantifying wetland depression water storage capacity. The framework and its concept are transferable to other wetland areas in the world where field measurements or high-resolution terrain data are unavailable. Moreover, the framework provides accurate distributions and depth–area relations of wetland depressions, which can be incorporated in wetland modules of hydrological models to improve the accuracy of flow and storage predictions.
Yanfeng Wu, Jingxuan Sun, Boting Hu, Y. Jun Xu, Alain N. Rousseau, and Guangxin Zhang
Hydrol. Earth Syst. Sci., 27, 2725–2745, https://doi.org/10.5194/hess-27-2725-2023, https://doi.org/10.5194/hess-27-2725-2023, 2023
Short summary
Short summary
Reservoirs and wetlands are important regulators of watershed hydrology, which should be considered when projecting floods and droughts. We first coupled wetlands and reservoir operations into a semi-spatially-explicit hydrological model and then applied it in a case study involving a large river basin in northeast China. We found that, overall, the risk of future floods and droughts will increase further even under the combined influence of reservoirs and wetlands.
Cited articles
Asher, M. J., Croke, B. F. W., Jakeman, A. J., and Peeters, L. J. M.: A review of surrogate models and their application to groundwater modeling, Water Resour. Res., 51, 5957–5973, https://doi.org/10.1002/2015wr016967, 2015.
Bai, Y., Lu, W., Li, J., Chang, Z., and Wang, H.: Groundwater contamination source identification using improved differential evolution Markov chain algorithm, Environ. Sci. Pollut. Res., 29, 19679–19692, https://0.1007/s11356-021-17120-2, 2022.
Chen, D., Lu, J., and Shen, Y.: Artificial neural network modelling of concentrations of nitrogen, phosphorus and dissolved oxygen in a non-point source polluted river in Zhejiang Province, southeast China, Hydrol. Process., 24, 290–299, https://10.1002/hyp.7482, 2010.
Chengming, L.: Surrogate model-optimization algorithm, Zenodo [code], https://doi.org/10.5281/zenodo.14568110, 2024.
Chugh, T., Jin, Y., Miettinen, K., Hakanen, J., and Sindhya, K.: A Surrogate-Assisted Reference Vector Guided Evolutionary Algorithm for Computationally Expensive Many-Objective Optimization, IEEE Trans. Evol. Comput., 22, 129–142, https://10.1109/tevc.2016.2622301, 2018.
Daranond, K., Yeh, T.-C. J., Hao, Y., Wen, J.-C., and Wang, W.: Identification of groundwater basin shape and boundary using hydraulic tomography, J. Hydrol., 588, 125099, https://10.1016/j.jhydrol.2020.125099, 2020.
Harbaugh, A. W.: MODFLOW-2005, the U.S. Geological Survey modular ground-water model: the ground-water flow process, U.S. Geological Survey Techniques and Methods, Book 6, Chapter A16, https://doi.org/10.3133/tm6A16, 2005.
Hou, Z., Lao, W., Wang, Y., and Lu, W.: Hybrid homotopy-PSO global searching approach with multi-kernel extreme learning machine for efficient source identification of DNAPL-polluted aquifer, Comput. Geosci., 155, 104837, https://10.1016/j.cageo.2021.104837, 2021.
Jha, M. and Datta, B.: Three-Dimensional Groundwater Contamination Source Identification Using Adaptive Simulated Annealing, J. Hydrol. Eng., 18, 307–317, https://doi10.1061/(ASCE)HE.1943-5584.0000624, 2013.
Jiang, C., Qiu, H. B., Gao, L., Wang, D. P., Yang, Z., and Chen, L. M.: Real-time estimation error-guided active learning Kriging method for time-dependent reliability analysis. Appl. Math. Modell., 77, 82–98, https://doi.org/10.1016/j.apm.2019.06.035, 2020.
Jiang, S., Zhang, Y., Wang, P., and Zheng, M.: An almost-parameter-free harmony search algorithm for groundwater pollution source identification, Water Sci. Technol., 68, 2359–2366, https://doi.org/10.2166/wst.2013.499, 2013.
Jia, S., Wang, X., Xu, Y. J., Liu, Z., and Mao, B.: A New Data-Driven Model to Predict Monthly Runoff at Watershed Scale: Insights from Deep Learning Method Applied in Data-Driven Model, Water Resour. Manage., 38, 5179–5194, https://doi.org/10.1007/s11269-024-03907-8, 2024.
Jiao, J., Zhang, Y., and Wang, L.: A new inverse method for contaminant source identification under unknown solute transport boundary conditions. J. Hydrol., 577, 123911, https://doi.org/10.1016/j.jhydrol.2019.123911, 2019.
Li, J., Lu, W., and Luo, J.: Groundwater contamination sources identification based on the Long-Short Term Memory network, J. Hydrol., 601, 126670, https://doi.org/10.1016/j.jhydrol.2021.126670, 2021.
Li, J., Wu, Z., Lu, W., and He, H.: Simultaneous identification of the number, location and release intensity of groundwater contamination sources based on simulation optimization and ensemble surrogate model, Water Supply, 22, 7671–7689, https://doi.org 10.2166/ws.2022.339, 2022.
Li, W., Englert, A., Cirpka, O. A., and Vereecken, H.: Three-dimensional geostatistical inversion of flowmeter and pumping test data, Ground Water, 46, 193–201, https://doi.org/10.1111/j.1745-6584.2007.00419.x, 2008.
Li, Y., Lu, W., Pan, Z., Wang, Z., and Dong, G.: Simultaneous identification of groundwater contaminant source and hydraulic parameters based on multilayer perceptron and flying foxes optimization, Environ. Sci. Pollut. Res., 30, 78933–78947, https://doi.org/10.1007/s11356-023-27574-1, 2023.
Liu, Y., Luo, J., Xiong, Y., Ji, Y., and Xin, X.: Inversion of hydrogeological parameters based on an adaptive dynamic surrogate model, Hydrogeol. J., 30, 1513–1527, https://doi.org/10.1007/s10040-022-02493-6, 2022.
Liu, Z., Wang, X., Wan, X., Jia, S., and Mao, B.: Evolution origin analysis and health risk assessment of groundwater environment in a typical mining area: Insights from water-rock interaction and anthropogenic activities, Environ. Res., 252, 118792, https://doi.org/10.1016/j.envres.2024.118792, 2024.
Luo, C., Lu, W., Pan, Z., Bai, Y., and Dong, G.: Simultaneous identification of groundwater pollution source and important hydrogeological parameters considering the noise uncertainty of observational data, Environ. Sci. Pollut. Res., 30, 84267–84282, https://doi.org/10.1007/s11356-023-28091-x, 2023.
Mahar, P. S. and Datta, B.: Identification of pollution sources in transient groundwater systems, Water Resour. Manage., 14, 209–227, https://doi.org/10.1023/A:1026527901213, 2000.
Maliva, R. G., Herrmann, R., Coulibaly, K., and Guo, W.: Advanced aquifer characterization for optimization of managed aquifer recharge, Environ. Earth Sci., 73, 7759–7767, https://doi.org/10.1007/s12665-014-3167-z, 2015.
Medici, G., Munn, J. D., and Parker, B. L.: Delineating aquitard characteristics within a Silurian dolostone aquifer using high-density hydraulic head and fracture datasets, Hydrogeol. J., 32, 1663–1691, https://doi.org/10.1007/s10040-024-02824-9, 2024.
ming: PSC data, Zenodo [data set], https://doi.org/10.5281/zenodo.17386323, 2025.
Mirghani, B. Y., Mahinthakumar, K. G., Tryby, M. E., Ranjithan, R. S., and Zechman, E. M.: A parallel evolutionary strategy based simulation-optimization approach for solving groundwater source identification problems, Adv. Water Resour., 32, 1373–1385, https://doi.org/10.1016/j.advwatres.2009.06.001, 2009.
Mirghani, B. Y., Zechman, E. M., Ranjithan, R. S., and Mahinthakumar, G.: Enhanced Simulation-Optimization Approach Using Surrogate Modeling for Solving Inverse Problems, Environ. Forensics, 13, 348–363, https://doi.org/10.1080/15275922.2012.702333, 2012.
Pan, Z., Lu, W., Fan, Y., and Li, J.: Identification of groundwater contamination sources and hydraulic parameters based on bayesian regularization deep neural network, Environ. Sci. Pollut. Res., 28, 16867–16879, https://doi.org/10.1007/s11356-020-11614-1, 2021.
Pan, Z., Lu, W., and Bai, Y.: Groundwater contamination source estimation based on a refined particle filter associated with a deep residual neural network surrogate, Hydrogeol. J., 30, 881–897, https://doi.org/10.1007/s10040-022-02454-z, 2022a.
Pan, Z., Lu, W., Wang, H., and Bai, Y.: Recognition of a linear source contamination based on a mixed-integer stacked chaos gate recurrent unit neural network-hybrid sparrow search algorithm, Environ. Sci. Pollut. Res., 29, 33528–33543, https://doi.org/10.1007/s11356-022-18538-y, 2022b.
Pan, Z., Lu, W., and Bai, Y.: Groundwater contaminated source estimation based on adaptive correction iterative ensemble smoother with an auto lightgbm surrogate, J. Hydrol., 620, 129502, https://doi.org/10.1016/j.jhydrol.2023.129502, 2023.
Rao, S. V. N.: A computationally efficient technique for source identification problems in three-dimensional aquifer systems using neural networks and simulated annealing, Environ. Forensics, 7, 233–240, https://doi.org/10.1080/15275920600840560, 2006.
Sargolzaei, J., Asl, M. H., and Moghaddam, A. H.: Membrane permeate flux and rejection factor prediction using intelligent systems, Desalination, 284, 92–99, https://doi.org/10.1016/j.desal.2011.08.041, 2012.
Singh, R. M., and Datta, B.: Artificial neural network modeling for identification of unknown pollution sources in groundwater with partially missing concentration observation data, Water Resour. Manage., 21, 557–572, https://doi.org/10.1007/s11269-006-9029-z, 2007.
Wang, H., Lu, W., and Chang, Z.: Simultaneous identification of groundwater contamination source and aquifer parameters with a new weighted-average wavelet variable-threshold denoising method, Environ. Sci. Pollut. Res., 28, 38292–38307, https://doi.org/10.1007/s11356-021-12959-x, 2021.
Wang, X., Xu, Y. J., and Zhang, L.: Watershed scale spatiotemporal nitrogen transport and source tracing using dual isotopes among surface water, sediments and groundwater in the Yiluo River Watershed, Middle of China, Sci. Total Environ., 833, 155180, https://doi.org/10.1016/j.scitotenv.2022.155180, 2022.
Wang Z., Lu W., and Chang Z.: Joint inverse estimation of groundwater pollution source characteristics and model parameters based on an intelligent particle filter, J. Hydrol., 625, 129965, https://doi.org/10.1016/j.jhydrol.2023.129965, 2023.
Wang, Z., Yue, C., and Wang, J.: Evaluating parameter inversion efficiency in Heterogeneous Groundwater models using Karhunen-Loève expansion: a comparative study of genetic algorithm, ensemble smoother, and MCMC, Earth Sci. Inf., 17, 3475–3491, https://doi.org/10.1007/s12145-024-01361-z, 2024a.
Wang, X., Ji, X., Xu, Y. J., Mao, B., Jia, S., Wang, C., Liu, Z., and Lv, Q.: Multi-machine learning methods to predict spatial variation characteristics of total nitrogen at watershed scale: evidences from the largest watershed (yangtze river watershed), asian, Sci. Total Environ., 949, 175144, https://doi.org/10.1016/j.scitotenv.2024.175144, 2024b.
Xu, Y., Lu, W., Pan, Z., Luo, C., Bai, Y., and Qiu, S.: Groundwater contaminant source identification considering unknown boundary condition based on an automated machine learning surrogate, Geosci. Front., 15, 101732, https://doi.org/10.1016/j.gsf.2023.101732, 2024a.
Xu, Y., Lu, W., Pan, Z., Wang, Z., Luo, C., and Bai, Y.: Intelligent enhanced particle filter with deep residual network surrogate for accurate groundwater pollution source characterization, J. Hydrol., 642, 131904, https://doi.org/10.1016/j.jhydrol.2024.131904, 2024b.
Yeh, H.-D., Chang, T.-H., and Lin, Y.-C.: Groundwater contaminant source identification by a hybrid heuristic approach, Water Resour. Res., 43, W09420, https://doi.org/10.1029/2005WR004731, 2007.
Zafarmomen, N., Alizadeh, H., Bayat, M., Ehtiat, M., and Moradkhani, H.: Assimilation of Sentinel-Based Leaf Area Index for Modeling Surface-Ground Water Interactions in Irrigation Districts, Water Resour. Res., 60, e2023WR036080, https://doi.org/10.1029/2023WR036080, 2024.
Zhang, P., Cai, Y., and Wang, J.: A simulation-based real-time control system for reducing urban runoff pollution through a stormwater storage tank, J. Cleaner Prod., 183, 641–652, https://doi.org/10.1016/j.jclepro.2018.02.130, 2018.
Zhang, X., Wang, L., Sorensen, J. D.: REIF: A novel active-learning function toward adaptive Kriging surrogate models for structural reliability analysis, Reliab. Eng. Syst. Saf., 185: 440–454, https://doi.org/10.1016/j.ress.2019.01.014, 2019.
Zhang, X., Jiang, S., Zheng, N., Xia, X., Li, Z., Zhang, R., Zhang, J., and Wang, X.: Integration of DDPM and ILUES for Simultaneous Identification of Contaminant Source Parameters and Non-Gaussian Channelized Hydraulic Conductivity Field, Water Resour. Res., 60, e2023WR036893, https://doi.org/10.1029/2023WR036893, 2024.
Zhang, Y., Tang, J., Liao, R., Zhang, M., Zhang, Y., Wang, X., and Su, Z.: Application of an enhanced BP neural network model with water cycle algorithm on landslide prediction, Stochastic Environ. Res. Risk Assess., 35, 1273–1291, https://doi.org/10.1007/s00477-020-01920-y, 2021.
Zhao, Y., Fan, D., Li, Y., and Yang, F.: Application of machine learning in predicting the adsorption capacity of organic compounds onto biochar and resin, Environ. Res., 208, 112694, https://doi.org/10.1016/j.envres.2022.112694, 2022a.
Zhao, W., Wang, L., and Mirjalili, S.: Artificial hummingbird algorithm: A new bio-inspired optimizer with its engineering applications, Comput. Methods Appl. Mech. Eng., 388, 114194, https://doi.org/10.1016/j.cma.2021.114194, 2022b.
Zheng, C., Hill, M. C., Cao, G., and Ma, R.: MT3DMS: Model use, calibration, and validation, Trans. ASABE, 55, 1549–1559, 2012.
Short summary
This study constructed a backpropagation neural network surrogate–artificial hummingbird algorithm inversion framework to accurately and synergistically identify the pollution source information and hydrogeological parameters, which provided a reliable basis for groundwater contamination remediation and management.
This study constructed a backpropagation neural network surrogate–artificial hummingbird...
