Integrating process-based and deep learning models for flood simulation in karst basins

Bin-quan Li; Yi-jie Xia; Si-ji Tao; Yun-yao Chen; Jian-fei Zhao; Zhong-min Liang

doi:10.1016/j.wse.2025.11.005

Volume 19 Issue 1

Mar. 2026

Turn off MathJax

Article Contents

Article Navigation > Water Science and Engineering > 2026 > 19(1): 23-34

Bin-quan Li, Yi-jie Xia, Si-ji Tao, Yun-yao Chen, Jian-fei Zhao, Zhong-min Liang. 2026: Integrating process-based and deep learning models for flood simulation in karst basins. Water Science and Engineering, 19(1): 23-34. doi: 10.1016/j.wse.2025.11.005

Citation:

Bin-quan Li, Yi-jie Xia, Si-ji Tao, Yun-yao Chen, Jian-fei Zhao, Zhong-min Liang. 2026: Integrating process-based and deep learning models for flood simulation in karst basins. Water Science and Engineering, 19(1): 23-34. doi: 10.1016/j.wse.2025.11.005

Citation:

Bin-quan Li, Yi-jie Xia, Si-ji Tao, Yun-yao Chen, Jian-fei Zhao, Zhong-min Liang. 2026: Integrating process-based and deep learning models for flood simulation in karst basins. Water Science and Engineering, 19(1): 23-34. doi: 10.1016/j.wse.2025.11.005

PDF( 0 KB)

Integrating process-based and deep learning models for flood simulation in karst basins

doi: 10.1016/j.wse.2025.11.005

a. State Key Laboratory of Water Cycle and Water Security in River Basin, Hohai University, Nanjing 210098, China;
b. Key Laboratory of Hydrologic-Cycle and Hydrodynamic-System of Ministry of Water Resources, Hohai University, Nanjing 210098, China;
c. College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China;
d. Guizhou Water & Power Survey-Design Institute Co., Ltd., Guiyang 550002, China

Funds:

This work was supported by the National Natural Science Foundation of China (Grant No. 42471049).

Received Date: 2025-04-23
Accepted Date: 2025-10-30

Available Online: 2026-03-28

Abstract

Abstract

Flood process simulation in karst basins is challenging due to complex runoff generation and concentration mechanisms, often resulting in low accuracy. This study investigated two typical karst basins (the Maiweng and Liudong river basins) in Guizhou Province, China, and developed two hydrological models for flood simulation: the karst-Xin'anjiang (Karst-XAJ) model, a modified Xin'anjiang (XAJ) hydrological model adapted for karst runoff characteristics, and the long short-term memory (LSTM) deep learning model. Their performances were compared, and their results were integrated using Bayesian model averaging (BMA). The Karst-XAJ model accurately simulated flood peak time and runoff depth but showed limited peak flow accuracy. The LSTM model performed well within a 2-h computational window, with accuracy declining for longer computational windows (3-4 h) yet maintaining a Nash—Sutcliffe model efficiency coefficient above 0.7. The BMA approach further enhanced simulation accuracy beyond individual models. Overall, both models effectively captured flood dynamics in karst basins, with the LSTM model achieving superior precision. This study offers a novel framework for simulating flood processes in karst regions with complex runoff processes.
- Karst basin,
- Karst-Xin'anjiang model,
- Long short-term memory neural network,
- Bayesian model averaging,
- Flood simulation

FullText(HTML)

References(29)

References

[1]	Adnan, R.M., Liang, Z.M., Heddam, S., Zounemat-Kermani, M., Kisi, O., Li, B.Q., 2020. Least square support vector machine and multivariate adaptive regression splines for streamflow prediction in mountainous basin using hydro-meteorological data as inputs. Journal of Hydrology 586, 24371. https://doi.org/10.1016/j.jhydrol.2019.124371.
[2]	Basu, B., Morrissey, P., Gill, L.W., 2022. Application of nonlinear time series and machine learning approaches for groundwater flood prediction in lowland karst. Water Resources Research 58(2), e2021WR029576. https://doi.org/10.1029/2021WR029576.
[3]	Cui, Z., Zhou, Y.L., Guo, S.L., Wang, J., Ba, H.H., He, S.K., 2021. A novel hybrid XAJ-LSTM model for multi-step-ahead flood forecasting. Hydrology Research 52(6), 1436-1454. https://doi.org/10.2166/nh.2021.016.
[4]	Department of Emergency Management of Guizhou Province, 2025. Basic Situation of Natural Disasters in the Province in 2024. The Department of Emergency Management of Guizhou Province, Guiyang (in Chinese).
[5]	Guo, X.L., Huang, K., Li, J.W., Kuang, Y., Chen, Y.F., Jiang, C., Luo, M.M., Zhou, H., 2023. Rainfall-runoff process simulation in the karst spring basins using a SAC-Tank Model. Journal of Hydrologic Engineering 28(9), 04023044. https://doi.org/10.1061/JHYEFF.HEENG-5956.
[6]	Guo, Y.X., Xu, Y.P., Yu, X.T., Liu, L., Gu, H.T., 2024. AI-based ensemble flood forecasts and its implementation in multi-objective robust optimization operation for reservoir flood control. Water Resources Research 60(5), e2023WR035693. https://doi.org/10.1029/2023WR035693.
[7]	Harrigan, S., Zsoter, E., Cloke, H., Salamon, P., Prudhomme, C., 2023. Daily ensemble river discharge reforecasts and real-time forecasts from the operational Global Flood Awareness System. Hydrology and Earth System Sciences 27(1), 1-19. https://doi.org/10.5194/hess-27-1-2023.
[8]	Huang, Y.X., Liang, Z.M., Singh, V.P., Hu, Y.M., Li, B.Q., Wang, J., 2022. A coupled dynamic system inversion model for higher accuracy in flood forecasting. Water Resources Research 58(2), e2021WR030531. https://doi.org/10.1029/2021WR030531.
[9]	Hunt, K.M.R., Matthews, G.R., Pappenberger, F., Prudhomme, C., 2022. Using a long short-term memory (LSTM) neural network to boost river streamflow forecasts over the western United States. Hydrology and Earth System Sciences 26(21), 5449-5472. https://doi.org/10.5194/hess-26-5449-2022.
[10]	Li, J., Yuan, D., Liu, J., Jiang, Y., Chen, Y., Hsu, K.L., Sorooshian, S., 2019. Predicting floods in a large karst river basin by coupling PERSIANN-CCS QPEs with a physically based distributed hydrological model. Hydrology and Earth System Sciences 23(3), 1505-1532. https://doi.org/10.5194/hess-23-1505-2019.
[11]	Li, J., Hong, A.H., Yuan, D.X., Jiang, Y.J., Zhang, Y.Z., Deng, S.J., Cao, C., Liu, J., Chen, Y.B., 2021. Elaborate simulations and forecasting of the effects of urbanization on karst flood events using the improved karst-Liuxihe model. Catena 197, 104990. https://doi.org/10.1016/j.catena.2020.104990.
[12]	Li, J., Yuan, D.X., Ma, M.G., Liu, J., 2022. Simulation of karst floods with a hydrological model improved by meteorological model coupling. Journal of Hydrometeorology 23(2), 185-207. http://doi.org/10.1175/JHM-D-21-0088.1.
[13]	Li, X., Li, J., 2023. Data-driven models for flood prediction in an ungauged karst wetland: Napahai wetland, Yunnan, China. PeerJ 11, e14940. http://doi.org/10.7717/peerj.14940.
[14]	Liang, X., Lettenmaier, D.P., Wood, E.F., Burges, S.J., 1994. A simple hydrologically based model of land surface water and energy fluxes for general circulation models. Journal of Geophysical Research 99(D7), 14415-14428. https://doi.org/10.1029/94JD00483.
[15]	Mosavi, A., Ozturk, P., Chau, K.-W., 2018. Flood prediction using machine learning models: Literature review. Water 10(11), 1536. https://doi.org/10.3390/w10111536.
[16]	Oddo, P.C., Bolten, J.D., Kumar, S.V., Cleary, B., 2024. Deep convolutional LSTM for improved flash flood prediction. Frontiers in Water 6, 1346104. https://doi.org/10.3389/frwa.2024.1346104.
[17]	Raftery, A.E., Gneiting, T., Balabdaoui, F., Polakowski, M., 2005. Using Bayesian model averaging to calibrate forecast ensembles. Monthly Weather Review 133(5), 1155-1174. https://doi.org/10.1175/MWR2906.1.
[18]	Ren, Z.L., Li, B.Q., Xiao, Y., Li, K., 2024. Investigating spatial heterogeneity of karst water storage capacity and nonclosure of underground watersheds in karst hydrological simulation. Hydrological Processes 38(12), e70012. https://doi.org/10.1002/hyp.70012.
[19]	Rimmer, A., Salingar, Y., 2006. Modelling precipitation-streamflow processes in karst basin: The case of the Jordan River sources, Israel. Journal of Hydrology 331(3), 524-542. https://doi.org/10.1016/j.jhydrol.2006.06.003.
[20]	Santhi, C., Srinivasan, R., Arnold, J.G., Williams, J.R., 2005. A modeling approach to evaluate the impacts of water quality management plans implemented in a watershed in Texas. Environmental Modelling & Software 21(8), 1141-1157. https://doi.org/10.1016/j.envsoft.2005.05.013.
[21]	Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., Woo, W.-C., 2015. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in Neural Information Processing Systems 28, 802-810. https://doi.org/10.5555/2969239.2969329.
[22]	Veress, M., 2020. Karst types and their karstification. Journal of Earth Science 31(3), 621-634. https://doi.org/10.1007/s12583-020-1306-x.
[23]	Vizi, Z., Batki, B., Ratki, L., Fehervary, I., Kozak, P., Kiss, T., 2023. Water level prediction using long short-term memory neural network model for a lowland river: A case study on the Tisza River, Central Europe. Environmental Sciences Europe 35, 92. https://doi.org/10.1186/s12302-023-00796-3.
[24]	Wang, X., Deng, C., Yin, X., Wei, J., Zou, J., 2025a. Assessing climate change impacts on streamflow in upper Han River Basin using deep learning models ensembled with Bayesian model averaging. Water Science and Engineering 18(4), 412-421. https://doi.org/10.1016/j.wse.2025.08.004.
[25]	Wang, X.J., Xia, J.Q., Dong, B.L., 2025b. Spatiotemporal variation of flood disaster losses and future assessment in the middle and lower region of the Yangtze River. International Journal of Disaster Risk Reduction 116, 105122. https://doi.org/10.1016/j.ijdrr.2024.105122.
[26]	Ye, K.J., Liang, Z.M., Chen, H.Y., Qian, M.K., Hu, Y.M., Bi, C.L., Wang, J., Li, B.Q., 2024. Regionalization strategy guided long short-term memory model for improving flood forecasting. Hydrological Processes 38(10), e15296. https://doi.org/10.1002/hyp.15296.
[27]	Zhao, J.F., Li, G.F., Duan, Y.N., Hu, Y.M., Li, B.Q., Liang, Z.M., 2023. A karst runoff generation module based on the near-surface critical zone structure and threshold behaviors. Hydrology Research 54(5), 686-702. https://doi.org/10.2166/nh.2023.135.
[28]	Zhao, R., 1992. The Xinanjiang model applied in China. Journal of Hydrology 135, 371-381. https://doi.org/10.1016/0022-1694(92)90096-E.
[29]	Zhou, L., Long, G., Hu, C., Zhang, K., 2025. Reservoir water level prediction using combined CEEMDAN-FE and RUN-SVM-RBFNN machine learning algorithms. Water Science and Engineering 18(2), 177-186. https://doi.org/10.1016/j.wse.2025.01.002.

Relative Articles

Supplements(0)

Cited By

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(1)

Get Citation

PDF

XML

Article Metrics

Article views (24) PDF downloads(0)

Integrating process-based and deep learning models for flood simulation in karst basins

doi: 10.1016/j.wse.2025.11.005

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Proportional views

Related

Integrating process-based and deep learning models for flood simulation in karst basins

doi: 10.1016/j.wse.2025.11.005

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Proportional views

Related

Export File

Citation

Format

Content