Abstract
Simulation of watershed streamflow is essential for the prevention and control of flood and drought disasters. To improve streamflow simulation, a coupled SWAT-LSTM model was constructed by combining a conceptual process-based hydrological model—Soil and Water Assessment Tool (SWAT)—with a machine learning model—Long Short-Term Memory (LSTM). The coupled model was applied to simulate the daily streamflow of the upper Huaihe River above the Xixian station from 1962 to 2010, which identified the optimal explanatory variables of the model and reduced streamflow simulation errors. Furthermore, four machine learning models, back propagation (BP) neural network, gated recurrent unit (GRU), support vector regression (SVR) and extreme gradient boosting (XGBoost), were chosen to assess the effectiveness of coupling SWAT with LSTM in streamflow simulation. Results showed that the coupled SWAT-LSTM model performed satisfactorily in streamflow simulation in the study area, with NSE reaching 0.90 and 0.85 in calibration and validation periods, respectively. The coupled model showed a significant improvement in simulating flood peak and average streamflow in each period, with mean NSE increasing by 0.24 compared to the standalone SWAT model. In comparison to other coupled models (i.e., SWAT-BP, SWAT-GRU, SWAT-SVR, and SWAT-XGB), the mean NSE of SWAT-LSTM exhibited an improvement of 0.02–0.16 during validation period. Furthermore, the coupled model effectively avoided the overfitting problem and had better generalization performance. The findings of this study offer new ideas for streamflow simulation of watersheds and provide references for water resources management and planning.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data Availability
Data will be made available on request.
References
Arsenault R, Martel JL, Brunet F, Brissette F, Mai J (2023) Continuous streamflow prediction in ungauged basins: long short-term memory neural networks clearly outperform traditional hydrological models. Hydrol Earth Syst Sci 27(1):139–157. https://doi.org/10.5194/hess-27-139-2023
Awchi TA (2014) River discharges forecasting in northern Iraq using different ANN techniques. Water Resour Manag 28(3):801–814. https://doi.org/10.1007/s11269-014-0516-3
Bennett A, Nijssen B (2021) Deep learned process parameterizations provide better representations of turbulent heat fluxes in hydrologic models. Water Resour Res 57(5):e2020WR029328. https://doi.org/10.1029/2020WR029328
Bergström S, Lindström G (2015) Interpretation of runoff processes in hydrological modelling-experience from the HBV approach. Hydrol Process 29(16):3535–3545. https://doi.org/10.1002/hyp.10510
Beven K, Binley A (1992) The future of distributed models: model calibration and uncertainty prediction. Hydrol Process 6:79–298. https://doi.org/10.1002/hyp.3360060305
Beven KJ, Kirkby MJ, Freer JE, Lamb R (2021) A history of TOPMODEL. Hydrol Earth Syst Sci 25(2):527–549. https://doi.org/10.5194/hess-25-527-2021
Boucher MA, Quilty J, Adamowski J (2020) Data assimilation for streamflow forecasting using extreme learning machines and multilayer perceptrons. Water Resour Res 56(6):e2019WR026226. https://doi.org/10.1029/2019WR026226
Breiman L (2001) Random forests. Mach Learn 45(1):5–32. https://doi.org/10.1023/A:1010933404324
Chadalawada J, Herath HMVV, Babovic V (2020) Hydrologically informed machine learning for rainfall-runoff modeling: a genetic programming-based toolkit for automatic model induction. Water Resour Res 56(4):e2019WR026933. https://doi.org/10.1029/2019WR026933
Chen S, Huang J, Huang J-C (2023) Improving daily streamflow simulations for data-scarce watersheds using the coupled SWAT-LSTM approach. J Hydrol 622:129734. https://doi.org/10.1016/j.jhydrol.2023.129734
Chen T, Guestrin C (2016) XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 785–794. https://doi.org/10.1145/2939672.2939785
Cho K, Kim Y (2022) Improving streamflow prediction in the WRF-Hydro model with LSTM networks. J Hydrol 605:127297. https://doi.org/10.1016/j.jhydrol.2021.127297
Clark MP, Bierkens MFP, Samaniego L, Woods RA, Uijlenhoet R, Bennett KE, Pauwels VRN, Cai X, Wood AW, Peters-Lidard CD (2017) The evolution of process-based hydrologic models: historical challenges and the collective quest for physical realism. Hydrol Earth Syst Sci 21(7):3427–3440. https://doi.org/10.5194/hess-21-3427-2017
Dasari I, Vema VK (2024) Spatial variability of rainfall: deciphering flood characteristics and model precision. Hydrol Sci J 69(10):1317–1334. https://doi.org/10.1080/02626667.2024.2371876
Farfán JF, Palacios K, Ulloa J, Avilés A (2020) A hybrid neural network-based technique to improve the flow forecasting of physical and data-driven models: methodology and case studies in Andean watersheds. J Hydrol Reg Stud 27:100652. https://doi.org/10.1016/j.ejrh.2019.100652
Gao S, Huang Y, Zhang S, Han J, Wang G, Zhang M, Lin Q (2020) Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation. J Hydrol 589:125188. https://doi.org/10.1016/j.jhydrol.2020.125188
Gassman PW, Reyes MR, Green CHM, Arnold JG (2007) The soil and water assessment tool: historical development, applications, and future research directions. Trans ASABE 50:1211–1250. https://doi.org/10.13031/2013.23637
Han H, Morrison RR (2022) Improved runoff forecasting performance through error predictions using a deep-learning approach. J Hydrol 608:127653. https://doi.org/10.1016/j.jhydrol.2022.127653
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Jiang S, Zheng Y, Wang C, Babovic V (2022) Uncovering flooding mechanisms across the contiguous United States through interpretive deep learning on representative catchments. Water Resour Res 58:e2021WR030185. https://doi.org/10.1029/2021WR030185
Konapala G, Kao S-C, Painter SL, Lu D (2020) Machine learning assisted hybrid models can improve streamflow simulation in diverse catchments across the conterminous US. Environ Res Lett 15(10):104022. https://doi.org/10.1088/1748-9326/aba927
Kratzert F, Klotz D, Brenner C, Schulz K, Herrnegger M (2018) Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks. Hydrol Earth Syst Sci 22(11):6005–6022. https://doi.org/10.5194/hess-22-6005-2018
Kwak J, Han H, Kim S, Kim HS (2022) Is the deep-learning technique a completely alternative for the hydrological model?: A case study on Hyeongsan River Basin, Korea. Stoch Environ Res Risk Assess 36(6):1615–1629. https://doi.org/10.1007/s00477-021-02094-x
Latif SD, Ahmed AN (2023) Streamflow prediction utilizing deep learning and machine learning algorithms for sustainable water supply management. Water Resour Manag 37(8):3227–3241. https://doi.org/10.1007/s11269-023-03499-9
Liang X, Lettenmaier DP, Wood EF, Burges SJ (1994) A simple hydrologically based model of land surface water and energy fluxes for general circulation models. J Geophys Res Atmos 99(D7):14415–14428. https://doi.org/10.1029/94JD00483
Lin Y, Wang D, Wang G, Qiu J, Long K, Du Y, Xie H, Wei Z, Shangguan W, Dai Y (2021) A hybrid deep learning algorithm and its application to streamflow prediction. J Hydrol 601:126636. https://doi.org/10.1016/j.jhydrol.2021.126636
Milly PCD, Betancourt J, Falkenmark M, Hirsch RM, Kundzewicz ZW, Lettenmaier DP, Stouffer RJ (2008) Stationarity is dead: whither water management? Science 319(5863):573–574. https://doi.org/10.1126/science.1151915
Moriasi DN, Arnold JG, Liew M, Bingner RL, Harme RD, Veith TL (2007) Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Trans ASABE 50:885–900. https://doi.org/10.13031/2013.23153
Refsgaard JC, Storm B, Clausen T (2010) Systeme Hydrologique Europeen (SHE): review and perspectives after 30 years development in distributed physically-based hydrological modelling. Hydrol Res 41(5):355–377. https://doi.org/10.2166/nh.2010.009
Reichstein M, Camps-Valls G, Stevens B, Jung M, Denzler J, Carvalhais N, Prabhat F (2019) Deep learning and process understanding for data-driven Earth system science. Nature 566:195–204. https://doi.org/10.1038/s41586-019-0912-1
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323(6088):533–536. https://doi.org/10.1038/323533a0
Shah S, Duan Z, Song X, Li R, Mao H, Liu J, Ma T, Wang M (2021) Evaluating the added value of multi-variable calibration of SWAT with remotely sensed evapotranspiration data for improving hydrological modeling. J Hydrol 603:127046. https://doi.org/10.1016/j.jhydrol.2021.127046
Singh D, Vardhan M, Sahu R, Chatterjee D, Chauhan P, Liu S (2023) Machine-learning- and deep-learning-based streamflow prediction in a hilly catchment for future scenarios using CMIP6 GCM data. Hydrol Earth Syst Sci 27(5):1047–1075. https://doi.org/10.5194/hess-27-1047-2023
Slater LJ, Arnal L, Boucher MA, Chang AYY, Moulds S, Murphy C, Nearing G, Shalev G, Shen CP, Speight L, Villarini G, Wilby RL, Wood A, Zappa M (2023) Hybrid forecasting: blending climate predictions with AI models. Hydrol Earth Syst Sci 27(9):1865–1889. https://doi.org/10.5194/hess-27-1865-2023
Sugawara M (1979) Automatic calibration of the tank model. Hydrol Sci Bull 24(3):375–388. https://doi.org/10.1080/02626667909491876
Sun W, Yao X, Cao N, Xu Z, Yu J (2016) Integration of soil hydraulic characteristics derived from pedotransfer functions into hydrological models: evaluation of its effects on simulation uncertainty. Hydrol Res 47(5):964–978. https://doi.org/10.2166/nh.2016.150
Tsai W-P, Feng D, Pan M, Beck H, Lawson K, Yang Y, Liu J, Shen C (2021) From calibration to parameter learning: harnessing the scaling effects of big data in geoscientific modeling. Nat Commun 12(1):5988. https://doi.org/10.1038/s41467-021-26107-z
Wang S, Xu O (2024) Uncertainty forecasting model for mountain flood based on Bayesian deep Learning. IEEE Access 12:47830–47841. https://doi.org/10.1109/ACCESS.2024.3384066
Wang W, Chau K-W, Qiu L, Chen Y (2015) Improving forecasting accuracy of medium and long-term runoff using artificial neural network based on EEMD decomposition. Environ Res 139:46–54. https://doi.org/10.1016/j.envres.2015.02.002
Wang N, Zhang D, Chang H, Li H (2020) Deep learning of subsurface flow via theory-guided neural network. J Hydrol 584:124700. https://doi.org/10.1016/j.jhydrol.2020.124700
Wang Y, Peng T, He Y, Singh VP, Lin Q, Dong X, Fan T, Liu J, Guo J, Wang G (2023) Attribution analysis of non-stationary hydrological drought using the GAMLSS framework and an improved SWAT model. J Hydrol 627:130420. https://doi.org/10.1016/j.jhydrol.2023.130420
Wegayehu EB, Muluneh FB (2022) Short-term daily univariate streamflow forecasting using deep learning models. Adv Meteorol 2022:1860460. https://doi.org/10.1155/2022/1860460
Westerberg IK, McMillan K (2015) Uncertainty in hydrological signatures. Hydrol Earth Syst Sci 19:3951–3968. https://doi.org/10.5194/hess-19-3951-2015
Wu J, Wang Z, Dong J, Cui X, Tao S, Chen X (2023) Robust runoff prediction with explainable artificial intelligence and meteorological variables from deep learning ensemble model. Water Resour Res 59:e2023WR035676. https://doi.org/10.1029/2023WR035676
Yang S, Tan M, Song Q, He J, Yao N, Li X, Yang X (2023) Coupling SWAT and Bi-LSTM for improving daily-scale hydro-climatic simulation and climate change impact assessment in a tropical river basin. J Environ Manag 330:117244. https://doi.org/10.1016/j.jenvman.2023.117244
Yang H, Sun H, Jia C, Yang T, Yang X (2024a) Future climatic projections and hydrological responses with a data driven method: a regional climate model perspective. Water Resour Manage 38:1693–1710. https://doi.org/10.1007/s11269-024-03753-8
Yang X, Zhou J, Zhang Q, Xu Z, Zhang J (2024b) Evaluation and interpretation of runoff forecasting models based on hybrid deep neural networks. Water Resour Manag 38:1987–2013. https://doi.org/10.1007/s11269-023-03731-6
Yu X, Zhang X, Qin H (2018) A data-driven model based on Fourier transform and support vector regression for monthly reservoir inflow forecasting. J Hydro-Environ Res 18:12–24. https://doi.org/10.1016/j.jher.2017.10.005
Zhang Z, Zhang Q, Singh VP (2018a) Univariate streamflow forecasting using commonly used data-driven models: literature review and case study. Hydrol Sci J 63(7):1091–1111. https://doi.org/10.1080/02626667.2018.1469756
Zhang Z, Zhang Q, Singh VP, Shi P (2018b) River flow modelling: comparison of performance and evaluation of uncertainty using data-driven models and conceptual hydrological model. Stoch Environ Res Risk Assess 32(9):2667–2682. https://doi.org/10.1007/s00477-018-1536-y
Zhao W, Gentine P, Reichstein M, Zhang Y, Zhou S, Wen Y, Lin C, Li X, Qiu G (2019) Physics-constrained machine learning of evapotranspiration. Geophys Res Lett 46(24):14496–14507. https://doi.org/10.1029/2019GL085291
Funding
This study was supported by the National Key R&D Program of China (2023YFC3081000, 2021YFC3200400), Hubei Provincial Key Laboratory of Construction and Management in Hydropower Engineering, Three Gorges University, China (2023KSD30) and the Science and Technology Plan Projects of Tibet Autonomous Region (XZ202301YD0044C).
Author information
Authors and Affiliations
Contributions
Methodology: Z. Mei, B. Yi, Z. Leng; Conceptualization: T. Peng, L. Chen; Visualization: Z. Mei, X. Gan, T. Xie; Writing-original draft: Z. Mei; Writing-review & editing: Z. Mei, T. Peng, L. Chen, VP. Singh; Funding acquisition: L. Chen.
Corresponding authors
Ethics declarations
Ethics Approval
Not applicable.
Consent to Participate
The authors agree to participate in this study.
Consent to Publish
The authors agree to publish this study.
Competing Interests
The authors confirm that they have no relevant financial interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Mei, Z., Peng, T., Chen, L. et al. Coupling SWAT and LSTM for Improving Daily Streamflow Simulation in a Humid and Semi-humid River Basin. Water Resour Manage (2024). https://doi.org/10.1007/s11269-024-03975-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11269-024-03975-w