Abstract
Streamflow is a crucial variable for assessing the available water resources for both human and environmental use. Accurate streamflow prediction plays a significant role in water resource management and assessing the impacts of climate change. This study explores the potential of coupling conceptual hydrological models based on physical processes with machine learning algorithms to enhance the performance of streamflow simulations. Four coupled models, namely SWAT-Transformer, SWAT-LSTM, SWAT-GRU, and SWAT-BiLSTM, were constructed in this research. SWAT served as a transfer function to convert four meteorological features, including precipitation, temperature, relative humidity, and wind speed, into six hydrological features: soil water content, lateral flow, percolation, groundwater discharge, surface runoff, and evapotranspiration. Machine learning algorithms were employed to capture the underlying relationships between these ten feature variables and the target variable (streamflow) to predict daily streamflow in the Sandu-River Basin (SRB). Among the four coupled models and the calibrated SWAT model, SWAT-BiLSTM exhibited the best streamflow simulation performance. During the calibration period (training period), it achieved R2 and NSE values of 0.92 and 0.91, respectively, and maintained them at 0.90 during the validation period (testing period). Additionally, the performance of all four coupled models surpassed that of the calibrated SWAT model. Compared to the tendency of the SWAT model to underestimate streamflow, the absolute values of PBIAS for all coupled models are below 10%, which indicates that there is no significant systematic bias evident. SHapley Additive exPlanations (SHAP) were used to analyze the impact of different feature variables on streamflow prediction. The results indicated that precipitation contributed the most to streamflow prediction, with a global importance of 29.7%. Hydrological feature variable output by the SWAT model played a dominant role in the Bi-LSTM’s prediction process. Coupling conceptual hydrological models with machine learning algorithms can significantly enhance the predictive performance of streamflow. The application of SHAP improves the interpretability of the coupled models and enhances researchers’ confidence in the prediction results.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Data availability
The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.
References
Abbass K, Qasim MZ, Song H, Murshed M, Mahmood H, Younis I (2022) A review of the global climate change impacts, adaptation, and sustainable mitigation measures. Environ Sci Pollut Res 29(28):42539–42559
Abbott MB, Bathurst JC, Cunge JA, O’connell PE, Rasmussen J (1986) An introduction to the European Hydrological System—Systeme Hydrologique Europeen, “SHE”, 2: structure of a physically-based, distributed modelling system. J Hydrol 87(1–2):61–77
Aloui S, Mazzoni A, Elomri A, Aouissi J, Boufekane A, Zghibi A (2023) A review of Soil and Water Assessment Tool (SWAT) studies of Mediterranean catchments: applications, feasibility, and future directions. J Environ Manage 326:116799
Anderson RM, Koren VI, Reed SM (2006) Using SSURGO data to improve Sacramento model a priori parameter estimates. J Hydrol 320(1–2):103–116
Ang R, Oeurng C (2018) Simulating streamflow in an ungauged catchment of Tonlesap Lake Basin in Cambodia using Soil and Water Assessment Tool (SWAT) model. Water Sci 32(1):89–101
Bergström S, Lindström G (2015) Interpretation of runoff processes in hydrological modelling—experience from the HBV approach. Hydrol Process 29(16):3535–3545
Bi Y, Xiang D, Ge Z, Li F, Jia C, Song J (2020) An interpretable prediction model for identifying N7-methylguanosine sites based on XGBoost and SHAP. Mol Ther Nucleic Acids 22:362–372
Carvalho DV, Pereira EM, Cardoso JS (2019) Machine learning interpretability: a survey on methods and metrics. Electronics 8(8):832
Chen S, Huang J, & Huang JC (2023) Improving daily streamflow simulations for data-scarce watersheds using the coupled SWAT-LSTM approach J Hydrol 129734
Cho K, Kim Y (2022) Improving streamflow prediction in the WRF-Hydro model with LSTM networks. J Hydrol 605:127297
Dey R, Salem FM (2017) Gate-variants of gated recurrent unit (GRU) neural networks. In 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS) (pp. 1597–1600). IEEE
Donigian AS, Imhoff J (2006) History and evolution of watershed modeling derived from the Stanford Watershed model Watershed models 21–45
Dye PJ, Croke BF (2003) Evaluation of streamflow predictions by the IHACRES rainfall-runoff model in two South African catchments. Environ Model Softw 18(8–9):705–712
Efstratiadis A, Koutsoyiannis D (2010) One decade of multi-objective calibration approaches in hydrological modelling: a review. Hydrolog Sci J 55(1):58–78
Ekanayake IU, Meddage DPP, Rathnayake U (2022) A novel approach to explain the black-box nature of machine learning in compressive strength predictions of concrete using Shapley additive explanations (SHAP). Case Stud Constr Mater 16:e01059
Han K, Xiao A, Wu E, Guo J, Xu C, Wang Y (2021) Transformer in transformer. Adv Neural Inf Process Syst 34:15908–15919
Jiang S, Zheng Y, Babovic V, Tian Y, Han F (2018) A computer vision-based approach to fusing spatiotemporal data for hydrological modeling. J Hydrol 567:25–40
Kim C, Kim CS (2021) Comparison of the performance of a hydrologic model and a deep learning technique for rainfall-runoff analysis. Trop Cyclone Res Rev 10(4):215–222
LeCun Y, Bengio Y, Hinton G (2015) Deep Learning. Nature 521(7553):436–444
Lei X, Liao W, Wang Y, Jiang Y, Wang H, Tian Y (2014) Development and application of a distributed hydrological model: EasyDHM. J Hydrol Eng 19(1):44–59
Liu Z, Todini E (2002) Towards a comprehensive physically-based rainfall-runoff model. Hydrol Earth Syst Sci 6(5):859–881
Liu J, Jiang L, Zhang X, Druce D, Kittel CM, Tøttrup C, Bauer-Gottwein P (2021) Impacts of water resources management on land water storage in the North China Plain: insights from multi-mission earth observations. J Hydrol 603:126933
Marin M, Clinciu I, Tudose NC, Ungurean C, Adorjani A, Mihalache AL, Cacovean H (2020) Assessing the vulnerability of water resources in the context of climate changes in a small forested watershed using SWAT: a review. Environ Res 184:109330
Neitsch SL, Arnold JG, Kiniry JR, Williams JR (2011) Soil and water assessment tool theoretical documentation version 2009. Texas Water Resources Institute
Nohara Y, Matsumoto K, Soejima H, Nakashima N (2022) Explanation of machine learning models using SHapley Additive exPlanation and application for real data in hospital. Comput Methods Programs Biomed 214:106584
Noori N, Kalin L, Isik S (2020) Water quality prediction using SWAT-ANN coupled approach. J Hydrol 590:125220
Nordin N, Zainol Z, Noor MHM, Chan LF (2023) An explainable predictive model for suicide attempt risk using an ensemble learning and Shapley Additive Explanations (SHAP) approach. Asian J Psychiatr 79:103316
Rahman KU, Shang S, Shahid M, Wen Y (2020) Hydrological evaluation of merged satellite precipitation datasets for streamflow simulation using SWAT: a case study of Potohar Plateau. Pak J Hydrol 587:125040
Rossman LA (2010) Storm water management model user’s manual, version 5.0 (p. 276). Cincinnati: National Risk Management Research Laboratory, Office of Research and Development, US Environmental Protection Agency
Siami-Namini S, Tavakoli N, Namin AS (2019) The performance of LSTM and BiLSTM in forecasting time series. In 2019 IEEE International conference on big data (Big Data) (pp. 3285–3292). IEEE
Stott P (2016) How climate change affects extreme weather events. Science 352(6293):1517–1518
Tan ML, Gassman PW, Yang X, Haywood J (2020) A review of SWAT applications, performance and future needs for simulation of hydro-climatic extremes. Adv Water Resour 143:103662
Tsakiris GP, Loucks DP (2023) Adaptive water resources management under climate change: an introduction Water Resour Manag 1–13
Upreti P, Ojha CSP (2021) Comparison of antecedent precipitation based rainfall-runoff models. Water Supply 21(5):2122–2138
Wang X, Dong Z, Xu W, Luo Y, Zhou T, Wang W (2019) Study on spatial and temporal distribution characteristics of coordinated development degree among regional water resources, social economy, and ecological environment systems. Int J Environ Res Public Health 16(21):4213
Wu W, Zhang Q, Singh VP, Wang G, Zhao J, Shen Z, Sun S (2022) A data-driven model on Google Earth Engine for landslide susceptibility assessment in the Hengduan Mountains, the Qinghai-Tibetan Plateau. Remote Sens 14(18):4662
Yen MH, Liu DW, Hsin YC, Lin CE, Chen CC (2019) Application of the deep learning for the prediction of rainfall in Southern Taiwan. Sci Rep 9(1):12774
Yu Y, Si X, Hu C, Zhang J (2019) A review of recurrent neural networks: LSTM cells and network architectures. Neural Comput 31(7):1235–1270
Zeng A, Chen M, Zhang L, Xu Q (2023) Are transformers effective for time series forecasting? In: Proceedings of the AAAI conference on artificial intelligence. 37(9):11121–11128
Zhang X, Qi Y, Li H, Sun S, Yin Q (2023a) Assessing effect of best management practices in unmonitored watersheds using the coupled SWAT-BiLSTM approach. Sci Rep 13(1):17168
Zhang X, Qi Y, Liu F, Li H, Sun S (2023b) Enhancing daily streamflow simulation using the coupled SWAT-BiLSTM approach for climate change impact assessment in Hai-River Basin. Sci Rep 13(1):15169
Zhao P, Lü H, Yang H, Wang W, Fu G (2019) Impacts of climate change on hydrological droughts at basin scale: a case study of the Weihe River Basin, China. Quatern Int 513:37–46
Zhao RJ, Liu XR (1995) The Xinanjiang model. Computer models of Watershed Hydrol 215–232
Funding
No funding was received for conducting this study.
Author information
Authors and Affiliations
Contributions
Feiyun Huang wrote the main manuscript text. Xiuyue Zhang prepared all the figures. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Ethical approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
All authors reviewed the manuscript and consent to publish.
Competing interests
The authors declare no competing interests.
Additional information
Responsible Editor: Marcus Schulz
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
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
Huang, F., Zhang, X. A new interpretable streamflow prediction approach based on SWAT-BiLSTM and SHAP. Environ Sci Pollut Res 31, 23896–23908 (2024). https://doi.org/10.1007/s11356-024-32725-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11356-024-32725-z