Articles | Volume 30, issue 12
https://doi.org/10.5194/hess-30-4095-2026
© Author(s) 2026. 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-30-4095-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Identifying dominant parameters in SWAT across subbasin and HRU scales using a two-step deep learning-assisted spatial sensitivity analysis
Jing Yang
School of Land Engineering, Key Laboratory of Degraded and Unused Land Consolidation Engineering of the Ministry of Natural Resources, Shaanxi Key Laboratory of Land Consolidation, and Shaanxi Province Land Consolidation Engineering Technology Research Center, Chang'an University, Xi'an 710054, China
Key Laboratory of Environmental Simulation and Ecological Health in the Yellow River Basin, College of Urban and Environmental Sciences, Northwest University, Xi'an 710127, China
Jiangjiang Zhang
State Key Laboratory of Water Disaster Prevention, Hohai University, Nanjing 210098, China
Yangtze Institute for Conservation and Development, Hohai University, Nanjing 210098, China
Tian Jiao
CORRESPONDING AUTHOR
Key Laboratory of Environmental Simulation and Ecological Health in the Yellow River Basin, College of Urban and Environmental Sciences, Northwest University, Xi'an 710127, China
Yonghua Zhao
CORRESPONDING AUTHOR
School of Land Engineering, Key Laboratory of Degraded and Unused Land Consolidation Engineering of the Ministry of Natural Resources, Shaanxi Key Laboratory of Land Consolidation, and Shaanxi Province Land Consolidation Engineering Technology Research Center, Chang'an University, Xi'an 710054, China
Manya Luo
School of Land Engineering, Key Laboratory of Degraded and Unused Land Consolidation Engineering of the Ministry of Natural Resources, Shaanxi Key Laboratory of Land Consolidation, and Shaanxi Province Land Consolidation Engineering Technology Research Center, Chang'an University, Xi'an 710054, China
Lei Wu
College of Water Resources and Architectural Engineering, Northwest A&F University, Yangling 712100, China
Ming Ye
Department of Earth, Ocean, and Atmosphere Science and Department of Scientific Computing, Florida State University, Tallahassee, FL 32306, USA
Jinxi Song
Key Laboratory of Environmental Simulation and Ecological Health in the Yellow River Basin, College of Urban and Environmental Sciences, Northwest University, Xi'an 710127, China
Related authors
Wanli Ren, Yue Fan, Anwen Pan, Heng Dai, Jing Yang, Mohamad Reza Soltanian, and Zhenxue Dai
Hydrol. Earth Syst. Sci., 30, 2759–2774, https://doi.org/10.5194/hess-30-2759-2026, https://doi.org/10.5194/hess-30-2759-2026, 2026
Short summary
Short summary
Using reconstructed 3D basin-scale sedimentary architectures, this study quantifies how hierarchical heterogeneity controls solute dispersion. Results show that macroform-scale lithofacies geometry and connectivity dominate macro-dispersion. Basin systems display a prolonged pre-asymptotic and strongly non-ergodic regime, with a buffering effect that reduces realization variability. The study establishes a transferable framework linking hierarchical architecture to multi-scale dispersion.
Wanli Ren, Yue Fan, Anwen Pan, Heng Dai, Jing Yang, Mohamad Reza Soltanian, and Zhenxue Dai
Hydrol. Earth Syst. Sci., 30, 2759–2774, https://doi.org/10.5194/hess-30-2759-2026, https://doi.org/10.5194/hess-30-2759-2026, 2026
Short summary
Short summary
Using reconstructed 3D basin-scale sedimentary architectures, this study quantifies how hierarchical heterogeneity controls solute dispersion. Results show that macroform-scale lithofacies geometry and connectivity dominate macro-dispersion. Basin systems display a prolonged pre-asymptotic and strongly non-ergodic regime, with a buffering effect that reduces realization variability. The study establishes a transferable framework linking hierarchical architecture to multi-scale dispersion.
Cited articles
Acero Triana, J. S., Ajami, H., and Razavi, S.: The dilemma of objective function selection for sensitivity and uncertainty analyses of semi-distributed hydrologic models across spatial and temporal scales, J. Hydrol., 650, 132482, https://doi.org/10.1016/j.jhydrol.2024.132482, 2025.
Aloui, S., Mazzoni, A., Elomri, A., Aouissi, J., Boufekane, A., and Zghibi, A.: A review of Soil and Water Assessment Tool (SWAT) studies of Mediterranean catchments: Applications, feasibility, and future directions, J. Environ. Manage., 326, 116799, https://doi.org/10.1016/j.jenvman.2022.116799, 2023.
Arnold, J., Moriasi, D., Gassman, P., Abbaspour, K., White, M., Srinivasan, R., Santhi, C., Harmel, R., van Griensven, A., Van Liew, M., Kannan, N., and Jha, M.: SWAT: Model Use, Calibration, and Validation, T. ASABE, 55, 1491–1508, https://doi.org/10.13031/2013.42256, 2012.
Bai, J., Zhou, Z., Li, J., Liu, T., Zhu, Q., and Zheng, T.: Predicting soil conservation service in the Jinghe River Basin under climate change, J. Hydrol., 615, 128646, https://doi.org/10.1016/j.jhydrol.2022.128646, 2022.
Bai, T., Liu, X., Liu, D., and Zhou, Y.: Water allocation and irrigation scheme considering runoff forecasting of Ulungur River, Ecol. Indic., 173, 113381, https://doi.org/10.1016/j.ecolind.2025.113381, 2025.
Bhanja, S. N., Coon, E. T., Lu, D., and Painter, S. L.: Evaluation of distributed process-based hydrologic model performance using only a priori information to define model inputs, J. Hydrol., 618, 129176, https://doi.org/10.1016/j.jhydrol.2023.129176, 2023.
Campolongo, F., Cariboni, J., and Saltelli, A.: An effective screening design for sensitivity analysis of large models, Environ. Modell. Softw., 22, 1509–1518, https://doi.org/10.1016/j.envsoft.2006.10.004, 2007.
Chang, J., Zhang, H., Wang, Y., and Zhu, Y.: Assessing the impact of climate variability and human activities on streamflow variation, Hydrol. Earth Syst. Sci., 20, 1547–1560, https://doi.org/10.5194/hess-20-1547-2016, 2016.
Chen, L., Wei, W., Fu, B., and Lü, Y.: Soil and water conservation on the Loess Plateau in China: review and perspective, Prog. Phys. Geog.-Earth Environment, 31, 389–403, https://doi.org/10.1177/0309133307081290, 2007.
Chitsaz, N., Shanafield, M., and Batelaan, O.: Enhanced runoff simulation with improved evapotranspiration accounting for vegetation response to climate variability, J. Hydrol., 662, 133988, https://doi.org/10.1016/j.jhydrol.2025.133988, 2025.
Clark, M. P., Vogel, R. M., Lamontagne, J. R., Mizukami, N., Knoben, W. J. M., Tang, G., Gharari, S., Freer, J. E., Whitfield, P. H., Shook, K. R., and Papalexiou, S. M.: The abuse of popular performance metrics in hydrologic modeling, Water Resour. Res., 57, e2020WR029001, https://doi.org/10.1029/2020WR029001, 2021.
Dai, H., Ju, J., Gui, D., Zhu, Y., Ye, M., Liu, Y., Cui, J., and Hu, B. X.: A two-step Bayesian network-based process sensitivity analysis for complex nitrogen reactive transport modeling, J. Hydrol., 632, 130903, https://doi.org/10.1016/j.jhydrol.2024.130903, 2024.
Dalcin, A. P. and Fernandes Marques, G.: Integrating Water Management Instruments to Reconcile a Hydro-Economic Water Allocation Strategy With Other Water Preferences, Water Resour. Res., 56, e2019WR025558, https://doi.org/10.1029/2019WR025558, 2020.
Fatichi, S., Vivoni, E. R., Ogden, F. L., Ivanov, V. Y., Mirus, B., Gochis, D., Downer, C. W., Camporese, M., Davison, J. H., Ebel, B., Jones, N., Kim, J., Mascaro, G., Niswonger, R., Restrepo, P., Rigon, R., Shen, C., Sulis, M., and Tarboton, D.: An overview of current applications, challenges, and future trends in distributed process-based models in hydrology, J. Hydrol., 537, 45–60, https://doi.org/10.1016/j.jhydrol.2016.03.026, 2016.
Furong, G. and Hossain, S.: Projection of monthly surface flows by an optimized SWAT–MLP: a case study, Water Supply, 24, 341–360, https://doi.org/10.2166/ws.2023.265, 2023.
Gao, L. and Bryan, B. A.: Incorporating deep uncertainty into the elementary effects method for robust global sensitivity analysis, Ecol. Modell., 321, 1–9, https://doi.org/10.1016/j.ecolmodel.2015.10.016, 2016.
Golmohammadi, G., Rudra, R., Dickinson, T., Goel, P., and Veliz, M.: Predicting the temporal variation of flow contributing areas using SWAT, J. Hydrol., 547, 375–386, https://doi.org/10.1016/j.jhydrol.2017.02.008, 2017.
Herman, J. and Usher, W.: SALib: An open-source Python library for Sensitivity Analysis, Journal of Open Source Software, 2, 771–784, https://doi.org/10.21105/joss.00097, 2017.
Herman, J. D., Reed, P. M., and Wagener, T.: Time-varying sensitivity analysis clarifies the effects of watershed model formulation on model behavior, Water Resour. Res., 49, 1400–1414, https://doi.org/10.1002/wrcr.20124, 2013a.
Herman, J. D., Kollat, J. B., Reed, P. M., and Wagener, T.: From maps to movies: high-resolution time-varying sensitivity analysis for spatially distributed watershed models, Hydrol. Earth Syst. Sci., 17, 5109–5125, https://doi.org/10.5194/hess-17-5109-2013, 2013b.
Hou, Y., Guo, H., Yang, Y., and Liu, W.: Global evaluation of runoff simulation from climate, hydrological and land surface models, Water Resour. Res., 59, https://doi.org/10.1029/2021wr031817, 2022.
Jahanshahi, A., Asadi, H., and Gupta, H.: A data fusion approach to enhancing runoff simulation in a semi-arid river basin, Environ. Modell. Softw., 190, 106468, https://doi.org/10.1016/j.envsoft.2025.106468, 2025.
Jeong, H., Lee, B., Kim, D., Qi, J., Lim, K. J., and Lee, S.: Improving estimation capacity of a hybrid model of LSTM and SWAT by reducing parameter uncertainty, J. Hydrol., 633, https://doi.org/10.1016/j.jhydrol.2024.130942, 2024.
Khorashadi Zadeh, F., Nossent, J., Sarrazin, F., Pianosi, F., van Griensven, A., Wagener, T., and Bauwens, W.: Comparison of variance-based and moment-independent global sensitivity analysis approaches by application to the SWAT model, Environ. Modell. Softw., 91, 210–222, https://doi.org/10.1016/j.envsoft.2017.02.001, 2017.
Koo, H., Chen, M., Jakeman, A. J., and Zhang, F.: A global sensitivity analysis approach for identifying critical sources of uncertainty in non-identifiable, spatially distributed environmental models: A holistic analysis applied to SWAT for input datasets and model parameters, Environ. Modell. Softw., 127, https://doi.org/10.1016/j.envsoft.2020.104676, 2020.
Li, M., Di, Z., and Duan, Q.: Effect of sensitivity analysis on parameter optimization: Case study based on streamflow simulations using the SWAT model in China, J. Hydrol., 603, https://doi.org/10.1016/j.jhydrol.2021.126896, 2021.
Li, X., Hu, X., and Wei, X.: Runoff characteristics analysis based on power spectrum method and detrended fluctuation analysis, Journal of Natural Resources, 30, 986–995, https://doi.org/10.11849/zrzyxb.2015.06.009, 2015. (In Chinese).
Liu, Y., Huang, T., Qiu, Z., Guan, Z., and Ma, X.: Effects of precipitation changes on fractional vegetation cover in the Jinghe River basin from 1998 to 2019, Ecol. Inform., 80, https://doi.org/10.1016/j.ecoinf.2024.102505, 2024.
Mao, H., Wang, C., He, Y., Song, X., Ma, R., Li, R., and Duan, Z.: Advancing SWAT model calibration: A U-NSGA-III-based framework for multi-objective optimization, Water, 16, https://doi.org/10.3390/w16213030, 2024.
Massmann, C., Wagener, T., and Holzmann, H.: A new approach to visualizing time-varying sensitivity indices for environmental model diagnostics across evaluation time-scales, Environ. Modell. Softw., 51, 190–194, https://doi.org/10.1016/j.envsoft.2013.09.033, 2014.
Morris, M. D.: Factorial Sampling Plans for Preliminary Computational Experiments, Technometrics, 33, 161–174, 1991.
Neitsch, S. L., Arnold, J. G., Kiniry, J. R., and Williams, J. R.: Soil and Water Assessment Tool Theoretical Documentation Version 2009, Texas Water Resources Institute, https://hdl.handle.net/1969.1/128050 (last access: 29 June 2026), 2011.
Ou, Z., Nai, C., Pan, B., Zheng, Y., Shen, C., Jiang, P., Liu, X., Tang, Q., Li, W., and Pan, M.: Probabilistic diffusion models advance extreme flood forecasting, Geophys. Res. Lett., 52, e2025GL115705, https://doi.org/10.1029/2025GL115705, 2025.
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L.: PyTorch: An imperative style, high-performance deep learning library, Adv. Neur. In., 32, 8026–8037, 2019.
Pelletier, A. and Andréassian, V.: On constraining a lumped hydrological model with both piezometry and streamflow: results of a large sample evaluation, Hydrol. Earth Syst. Sci., 26, 2733–2758, https://doi.org/10.5194/hess-26-2733-2022, 2022.
Pianosi, F., Sarrazin, F., and Wagener, T.: A Matlab toolbox for global sensitivity analysis, Environ. Modell. Softw., 70, 80–85, https://doi.org/10.1016/j.envsoft.2015.04.009, 2015.
Razavi, S., Tolson, B. A., and Burn, D. H.: Review of surrogate modeling in water resources, Water Resour. Res., 48, https://doi.org/10.1029/2011wr011527, 2012.
Rouzies, E., Lauvernet, C., Sudret, B., and Vidard, A.: How is a global sensitivity analysis of a catchment-scale, distributed pesticide transfer model performed? Application to the PESHMELBA model, Geosci. Model Dev., 16, 3137–3163, https://doi.org/10.5194/gmd-16-3137-2023, 2023.
Saltelli, A., Ratto, M., Andres, T., Campolongo, F., Cariboni, J., Gatelli, D., Saisana, M., and Tarantola, S.: Global Sensitivity Analysis, The Primer, https://doi.org/10.1002/9780470725184, 2007.
Saint-Geours, N., Bailly, J.-S., Grelot, F., and Lavergne, C.: Multi-scale spatial sensitivity analysis of a model for economic appraisal of flood risk management policies, Environ. Modell. Softw., 60, 153–166, https://doi.org/10.1016/j.envsoft.2014.06.012, 2014.
Sarrazin, F., Pianosi, F., and Wagener, T.: Global Sensitivity Analysis of environmental models: Convergence and validation, Environ. Modell. Softw., 79, 135–152, https://doi.org/10.1016/j.envsoft.2016.02.005, 2016.
Sobol', I. M.: Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates, Math. Comput. Simulat., 55, 271–280, https://doi.org/10.1016/s0378-4754(00)00270-6, 2001.
Sreedevi, S. and Eldho, T. I.: A two-stage sensitivity analysis for parameter identification and calibration of a physically-based distributed model in a river basin, Hydrolog. Sci. J., 64, 701–719, https://doi.org/10.1080/02626667.2019.1602730, 2019.
Su, L., Lettenmaier, D. P., Pan, M., and Bass, B.: Improving runoff simulation in the Western United States with Noah-MP and VIC models, Hydrol. Earth Syst. Sci., 28, 3079–3097, https://doi.org/10.5194/hess-28-3079-2024, 2024.
Tang, Y., Reed, P., van Werkhoven, K., and Wagener, T.: Advancing the identification and evaluation of distributed rainfall-runoff models using global sensitivity analysis, Water Resour. Res., 43, 14, https://doi.org/10.1029/2006wr005813, 2007.
Tuo, Y., Marcolini, G., Disse, M., and Chiogna, G.: A multi-objective approach to improve SWAT model calibration in alpine catchments, J. Hydrol., 559, 347–360, https://doi.org/10.1016/j.jhydrol.2018.02.055, 2018.
van Werkhoven, K., Wagener, T., Reed, P., and Tang, Y.: Rainfall characteristics define the value of streamflow observations for distributed watershed model identification, Geophys. Res. Lett., 35, https://doi.org/10.1029/2008gl034162, 2008.
Wu, S., Tetzlaff, D., Yang, X., and Soulsby, C.: Identifying dominant processes in time and space: Time-varying spatial sensitivity analysis for a grid-based nitrate model, Water Resour. Res., 58, https://doi.org/10.1029/2021wr031149, 2022.
Xu, C., Jiang, Y., Su, Z., Liu, Y., and Lyu, J.: Assessing the impacts of Grain-for-Green Programme on ecosystem services in Jinghe River basin, China, Ecol. Indic., 137, https://doi.org/10.1016/j.ecolind.2022.108757, 2022.
Yang, J.: Code and Data for Deep Learning-Assisted Spatial Sensitivity Analysis of the SWAT Model in the Jinghe River Basin, Zenodo [data set], https://doi.org/10.5281/zenodo.20440148, 2026.
Yang, J. and Ye, M.: A new multi-model absolute difference-based sensitivity (MMADS) analysis method to screen non-influential processes under process model and parametric uncertainty, J. Hydrol., 608, 127609, https://doi.org/10.1016/j.jhydrol.2022.127609, 2022.
Yang, J., Ye, M., Chen, X., Dai, H., and Walker, A. P.: Process interactions can change process ranking in a coupled complex system under process model and parametric uncertainty, Water Resour. Res., 58, https://doi.org/10.1029/2021wr029812, 2022.
Yang, J., Liu, Y., Dai, H., Yuan, S., Jiao, T., Wen, Z., and Ye, M.: Development of an integrated global sensitivity analysis strategy for evaluating process sensitivities across single- and multi-models, J. Hydrol., 643, 132014, https://doi.org/10.1016/j.jhydrol.2024.132014, 2024.
Yu, D., Xie, P., Dong, X., Hu, X., Liu, J., Li, Y., Peng, T., Ma, H., Wang, K., and Xu, S.: Improvement of the SWAT model for event-based flood simulation on a sub-daily timescale, Hydrol. Earth Syst. Sci., 22, 5001–5019, https://doi.org/10.5194/hess-22-5001-2018, 2018.
Yu, Z., Dai, H., Yang, J., Zhu, Y., and Yuan, S.: Global sensitivity analysis with deep learning-based surrogate models for unraveling key parameters and processes governing redox zonation in riparian zone, J. Hydrol., 638, 131442, https://doi.org/10.1016/j.jhydrol.2024.131442, 2024.
Zhang, C., Chu, J., and Fu, G.: Sobol's sensitivity analysis for a distributed hydrological model of Yichun River Basin, China, J. Hydrol., 480, 58–68, https://doi.org/10.1016/j.jhydrol.2012.12.005, 2013.
Zhang, X., Xu, Y.-P., and Fu, G.: Uncertainties in SWAT extreme flow simulation under climate change, J. Hydrol., 515, 205–222, https://doi.org/10.1016/j.jhydrol.2014.04.064, 2014.
Zheng, Y. and Han, F.: Markov Chain Monte Carlo (MCMC) uncertainty analysis for watershed water quality modeling and management, Stoch. Env. Res. Risk A., 30, 293–308, https://doi.org/10.1007/s00477-015-1091-8, 2015.
Zhou, S., Yu, B., Lintner, B. R., Findell, K. L., and Zhang, Y.: Projected increase in global runoff dominated by land surface changes, Nat. Clim. Change, 13, 442–449, https://doi.org/10.1038/s41558-023-01659-8, 2023.
Short summary
Understanding how rainfall becomes river flow is essential for effective water management, yet complex computer models are often difficult to interpret. This study developed an efficient approach, supported by artificial intelligence, to identify where and how key model parameters influence river flow across different scales. The results reveal clear spatial differences and highlight critical areas controlling runoff, improving model reliability and supporting better water management decisions.
Understanding how rainfall becomes river flow is essential for effective water management, yet...