Comparative Performance Assessment of Physical-Based and Data-Driven Machine-Learning Models for Simulating Streamflow: A Case Study in Three Catchments across the US
Publication: Journal of Hydrologic Engineering
Volume 29, Issue 2
Abstract
Recent developments in computational techniques and data-driven machine-learning models (MLMs) have shown great potential in capturing the rainfall-runoff relationship. However, whether MLMs outperform the classical physical-based models (PBMs) in streamflow simulation is still controversial. In this study, we chose three representative catchments across the continental United States for a comparative analysis of these two model categories, including two PBMs, i.e., a conceptual hydrological model (EXP-HYDRO) and a classical semidistributed hydrological model (SWAT), and three MLMs, i.e., support vector regression (SVR), backpropagation artificial neural networks (BP-ANN), and a deep learning model, termed long short-term memory (LSTM). Results indicate that the bias of SVR and BP-ANN models is greater than PBMs under the baseline input scenario, while LSTM outperforms other models for the rainfall-runoff relationship. For delayed input scenarios, MLMs have great potential and perform satisfactorily. In addition, MLMs show better performance in the high-flow regime, while PBMs perform better in the low-flow regime, implying that both PBMs and MLMs have their own merits and should be jointly employed holistically to analyze the streamflow. Our comparison analysis demonstrates that the performance of MLMs and PBMs is variable under different seasonal, climatic, and topographic conditions, and conclude that MLMs can better capture the rainfall-runoff relationship than PBMs, when the coefficient of variation (COV) is large.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Daily precipitation, potential evapotranspiration, temperature, and streamflow data used in this study are available on the United States Geological Survey (https://www.usgs.gov). The source code of the EXP-HYDRO model is available at https://github.com/sopanpatil/exp-hydro. MLMs and optimization algorithms were built using Python 3.11 software.
Acknowledgments
This research was partially supported by Programs of the National Key Research and Development Program of China (No. 2021YFA0715900); the National Natural Science Foundation of China (Nos. 42222704 and 41972250); the Natural Science Foundation of Hubei Province (No. 2021CFA089); and the 111 Program (State Administration of Foreign Experts Affairs and the Ministry of Education of China, No. B18049). We thank the associate editor and three anonymous reviewers for their critical and constructive comments, which help us improve the quality of the manuscript.
Author contributions: Aohan Jin: methodology, software, visualization, and writing of the original draft; Quanrong Wang: conceptualization, writing, review, editing, funding acquisition, and project administration; Hongbin Zhan: validation, writing, review, and editing; and Renjie Zhou: validation, writing, review, and editing.
References
Abbasi, M., A. Farokhnia, M. Bahreinimotlagh, and R. Roozbahani. 2021. “A hybrid of Random Forest and deep auto-encoder with support vector regression methods for accuracy improvement and uncertainty reduction of long-term streamflow prediction.” J. Hydrol. 597 (Jun): 125717. https://doi.org/10.1016/j.jhydrol.2020.125717.
Abdelkader, M., M. Temimi, and T. B. M. J. Ouarda. 2023. “Assessing the national water model’s streamflow estimates using a multi-decade retrospective dataset across the contiguous united states.” Water 15 (13): 2319. https://doi.org/10.3390/w15132319.
Adnan, R. M., Z. Liang, S. Trajkovic, M. Zounemat-Kermani, B. Li, and O. Kisi. 2019. “Daily streamflow prediction using optimally pruned extreme learning machine.” J. Hydrol. 577 (Oct): 123981. https://doi.org/10.1016/j.jhydrol.2019.123981.
Alizadeh, B., A. Ghaderi Bafti, H. Kamangir, Y. Zhang, D. B. Wright, and K. J. Franz. 2021. “A novel attention-based LSTM cell post-processor coupled with bayesian optimization for streamflow prediction.” J. Hydrol. 601 (Oct): 126526. https://doi.org/10.1016/j.jhydrol.2021.126526.
Allen, H. E., and E. A. Cowan. 1985. Low-flow characteristics of streams in the Kishwaukee River basin, Illinois. Reston, VA: USGS. https://doi.org/10.3133/WRI844311.
Apaydin, H., and M. Sibtain. 2021. “A multivariate streamflow forecasting model by integrating improved complete ensemble empirical mode decomposition with additive noise, sample entropy, Gini index and sequence-to-sequence approaches.” J. Hydrol. 603 (Oct): 126831. https://doi.org/10.1016/j.jhydrol.2021.126831.
Archfield, S. A., R. M. Hirsch, A. Viglione, and G. Blöschl. 2016. “Fragmented patterns of flood change across the United States.” Geophys. Res. Lett. 43 (19): 10–232. https://doi.org/10.1002/2016GL070590.
Brunner, M. I., E. Gilleland, A. Wood, D. L. Swain, and M. Clark. 2020. “Spatial dependence of floods shaped by spatiotemporal variations in meteorological and land-surface processes.” Geophys. Res. Lett. 47 (13): e2020GL088000. https://doi.org/10.1029/2020GL088000.
Chen, Y., J. Niu, Y. Sun, Q. Liu, and Q. Li. 2020. “Study on streamflow response to land use change over the upper reaches of Zhanghe Reservoir in the Yangtze River basin.” Geosci. Lett. 7 (1): 1–2. https://doi.org/10.1186/s40562-020-00155-7.
Cho, K. H., Y. A. Pachepsky, J. H. Kim, J.-W. Kim, and M.-H. Park. 2012. “The modified SWAT model for predicting fecal coliforms in the Wachusett Reservoir Watershed, USA.” Water Res. 46 (15): 4750–4760. https://doi.org/10.1016/j.watres.2012.05.057.
Choi, W., and B. M. Deal. 2008. “Assessing hydrological impact of potential land use change through hydrological and land use change modeling for the Kishwaukee River basin (USA)” J. Environ. Manage. 88 (4): 1119–1130. https://doi.org/10.1016/j.jenvman.2007.06.001.
Criss, R. E., E. M. Stein, and D. L. Nelson. 2022. “Generation and propagation of an urban flash flood and our collective responsibilities.” J. Earth Sci. 33 (6): 1624–1628. https://doi.org/10.1007/s12583-022-1314-0.
Cui, K., and X. Jing. 2019. “Research on prediction model of geotechnical parameters based on BP neural network.” Neural Comput. Appl. 31 (12): 8205–8215. https://doi.org/10.1007/s00521-018-3902-6.
Ding, S., C. Su, and J. Yu. 2011. “An optimizing BP neural network algorithm based on genetic algorithm.” Artif. Intell. Rev. 36 (2): 153–162. https://doi.org/10.1007/s10462-011-9208-z.
Fang, K., and C. Shen. 2017. “Full-flow-regime storage: Treamflow correlation patterns provide insights into hydrologic functioning over the continental US.” Water Resour. Res. 53 (9): 8064–8083. https://doi.org/10.1002/2016WR020283.
Feng, D., K. Fang, and C. Shen. 2020. “Enhancing streamflow forecast and extracting insights using long-short term memory networks with data integration at continental scales.” Water Resour. Res. 56 (9): e2019WR026793. https://doi.org/10.1029/2019WR026793.
Ficklin, D. L., Y. Luo, I. T. Stewart, and E. P. Maurer. 2012. “Development and application of a hydroclimatological stream temperature model within the soil and water assessment tool.” Water Resour. Res. 48 (1): 308–316. https://doi.org/10.1029/2011WR011256.
Flanagan, C., and M. Laituri. 2004. “Local cultural knowledge and water resource management: The Wind River Indian Reservation.” Environ. Manage. 33 (2): 262–270. https://doi.org/10.1007/s00267-003-2894-9.
Ghorbani, M. A., H. A. Zadeh, M. Isazadeh, and O. Terzi. 2016. “A comparative study of artificial neural network (MLP, RBF) and support vector machine models for river flow prediction.” Environ. Earth Sci. 75 (6): 1–14. https://doi.org/10.1007/s12665-015-5096-x.
Gurrieri, J. 1998. “Distribution of metals in water and sediment and effects on aquatic biota in the upper Stillwater River basin, Montana.” J. Geochem. Explor. 64 (1–3): 83–100. https://doi.org/10.1016/S0375-6742(98)00022-3.
Han, J., J. Xu, L. Yi, Z. Chang, J. Wang, H. Ma, B. Zhang, and H. Jiang. 2022. “Seasonal interaction of river water-groundwater-salt lake brine and its influence on water-salt balance in the Nalenggele River catchment in Qaidam Basin, NW China.” J. Earth Sci. 33 (5): 1298–1308. https://doi.org/10.1007/s12583-022-1731-0.
Huang, P., Z. Li, J. Chen, Q. Li, and C. Yao. 2016. “Event-based hydrological modeling for detecting dominant hydrological process and suitable model strategy for semi-arid catchments.” J. Hydrol. 542 (Mar): 292–303. https://doi.org/10.1016/j.jhydrol.2016.09.001.
Jiang, S., Y. Zheng, and D. Solomatine. 2020. “Improving AI system awareness of geoscience knowledge: Symbiotic integration of physical approaches and deep learning.” Geophys. Res. Lett. 47 (13): 733–745. https://doi.org/10.1029/2020GL088229.
Jiang, S., Y. Zheng, C. Wang, and V. Babovic. 2021. “Uncovering flooding mechanisms across the contiguous United States through interpretive deep learning on representative catchments.” Water Resour. Res. 58 (1): e2021WR030185. https://doi.org/10.1029/2021WR030185.
Kan, G., X. He, L. Ding, J. Li, K. Liang, and Y. Hong. 2017. “Study on applicability of conceptual hydrological models for flood forecasting in humid, semi-humid semi-arid and arid basins in China.” Water 9 (10): 719. https://doi.org/10.3390/w9100719.
Kim, T., T. Yang, S. Gao, L. Zhang, Z. Ding, X. Wen, J. J. Gourley, and Y. Hong. 2021. “Can artificial intelligence and data-driven machine learning models match or even replace process-driven hydrologic models for streamflow simulation?: A case study of four watersheds with different hydro-climatic regions across the CONUS.” J. Hydrol. 598 (Mar): 126423. https://doi.org/10.1016/j.jhydrol.2021.126423.
Kumari, N., A. Srivastava, B. Sahoo, N. S. Raghuwanshi, and D. Bretreger. 2021. “Identification of suitable hydrological models for streamflow assessment in the Kangsabati River basin, India, by using different model selection scores.” Nat. Resour. Res. 30 (6): 4187–4205. https://doi.org/10.1007/s11053-021-09919-0.
Kuzara, S. 2011. “Groundwater surface-water interaction in the alluvial aquifer of the Middle Stillwater River Valley, Absarokee, Montana.” Ph.D. thesis, Montana Tech of Univ. of Montana.
Li, P., Y. Zha, L. Shi, C.-H. M. Tso, Y. Zhang, and W. Zeng. 2020. “Comparison of the use of a physical-based model with data assimilation and machine learning methods for simulating soil water dynamics.” J. Hydrol. 584 (May): 124692. https://doi.org/10.1016/j.jhydrol.2020.124692.
Liu, Z., P. Zhou, G. Chen, and L. Guo. 2014. “Evaluating a coupled discrete wavelet transform and support vector regression for daily and monthly streamflow forecasting.” J. Hydrol. 519 (Nov): 2822–2831. https://doi.org/10.1016/j.jhydrol.2014.06.050.
Mallakpour, I., and G. Villarini. 2015. “The changing nature of flooding across the central United States.” Nat. Clim. Change 5 (3): 250–254. https://doi.org/10.1038/nclimate2516.
Mangini, W., A. Viglione, J. Hall, Y. Hundecha, and J. Parajka. 2018. “Detection of trends in magnitude and frequency of flood peaks across Europe.” Hydrol. Sci. J. 63 (4): 493–512. https://doi.org/10.1080/02626667.2018.1444766.
Meng, E., S. Huang, Q. Huang, W. Fang, L. Wu, and L. Wang. 2019. “A robust method for non-stationary streamflow prediction based on improved EMD-SVM model.” J. Hydrol. 568 (May): 462–478. https://doi.org/10.1016/j.jhydrol.2018.11.015.
Mengistu, A. G., L. D. van Rensburg, and Y. E. Woyessa. 2019. “Techniques for calibration and validation of SWAT model in data scarce arid and semi-arid catchments in South Africa.” J. Hydrol.: Reg. Stud. 25 (Oct): 100621. https://doi.org/10.1016/j.ejrh.2019.100621.
Mohanty, S., M. K. Jha, A. Kumar, and D. K. Panda. 2013. “Comparative evaluation of numerical model and artificial neural network for simulating groundwater flow in Kathajodi–Surua Inter-basin of Odisha, India.” J. Hydrol. 495 (Jul): 38–51. https://doi.org/10.1016/j.jhydrol.2013.04.041.
Murdoch, W. J., C. Singh, K. Kumbier, R. Abbasi-Asl, and B. Yu. 2019. “Definitions, methods, and applications in interpretable machine learning.” Proc. Natl. Acad. Sci. U.S.A. 116 (44): 22071–22080. https://doi.org/10.1073/pnas.1900654116.
Parisouj, P., H. Mohebzadeh, and T. Lee. 2020. “Employing machine learning algorithms for streamflow prediction: A case study of four river basins with different climatic zones in the United States.” Water Resour. Manage. 34 (13): 4113–4131. https://doi.org/10.1007/s11269-020-02659-5.
Park, J. Y., M. J. Park, H. K. Joh, H. J. Shin, H. J. Kwon, R. Srinivasan, and S. J. Kim. 2011. “Assessment of MIROC3.2 HiRes climate and CLUE-s land use change impacts on watershed hydrology using SWAT.” Trans. ASABE 54 (5): 1713–1724. https://doi.org/10.13031/2013.39842.
Patil, S. D., and M. Stieglitz. 2014. “Modelling daily streamflow at ungauged catchments: What information is necessary?” Hydrol. Processes 28 (3): 1159–1169. https://doi.org/10.1002/hyp.9660.
Patil, S. D., and M. Stieglitz. 2015. “Comparing spatial and temporal transferability of hydrological model parameters.” J. Hydrol. 525 (Jun): 409–417. https://doi.org/10.1016/j.jhydrol.2015.04.003.
Sahay, R. R., and A. Srivastava. 2014. “Predicting monsoon floods in rivers embedding wavelet transform, genetic algorithm and neural network.” Water Resour. Manage. 28 (2): 301–317. https://doi.org/10.1007/s11269-013-0446-5.
Shu, X., W. Ding, Y. Peng, Z. Wang, J. Wu, and M. Li. 2021. “Monthly streamflow forecasting using convolutional neural network.” Water Resour. Manage. 35 (15): 5089–5104. https://doi.org/10.1007/s11269-021-02961-w.
Stonefelt, M. D., T. A. Fontaine, and R. H. Hotchkiss. 2000. “Impacts of climate change on water yield in the upper wind river basin.” JAWRA J. Am. Water Resour. Assoc. 36 (2): 321–336. https://doi.org/10.1111/j.1752-1688.2000.tb04271.x.
Tikhamarine, Y., D. Souag-Gamane, A. N. Ahmed, S. S. Sammen, O. Kisi, Y. F. Huang, and A. El-Shafie. 2020. “Rainfall-runoff modelling using improved machine learning methods: Harris hawks optimizer vs. particle swarm optimization.” J. Hydrol. 589 (Oct): 125133. https://doi.org/10.1016/j.jhydrol.2020.125133.
Vapnik, V., S. E. Golowich, and A. Smola. 1996. “Support vector method for function approximation, regression estimation and signal processing.” In Proc., 9th Int. Conf. on Neural Information Processing Systems, 281–287. Cambridge, UK: MIT Press.
Wang, L., G. Jin, and X. Xiong. 2023. “Flood duration estimation based on multisensor, multitemporal remote sensing: The Sardoba reservoir flood.” J. Earth Sci. 34 (3): 868–878. https://doi.org/10.1007/s12583-022-1670-9.
Worsa-Kozak, M., R. Zimroz, A. Michalak, C. Wolkersdorfer, A. Wyłomańska, and M. Kowalczyk. 2020. “Groundwater level fluctuation analysis in a semi-urban area using statistical methods and data mining techniques—A case study in Wrocław, Poland.” Appli. Sci. 10 (10): 3553. https://doi.org/10.5194/hess-24-5491-2020.
Wu, M. C., G. F. Lin, and H. Y. Lin. 2012. “Improving the forecasts of extreme streamflow by support vector regression with the data extracted by self-organizing map.” Hydrol. Processes 28 (2): 386–397. https://doi.org/10.1002/hyp.9584.
Yang, T., F. Sun, P. Gentine, W. Liu, and C. Liu. 2019. “Evaluation and machine learning improvement of global hydrological model-based flood simulations.” Environ. Res. Lett. 14 (11): 114027. https://doi.org/10.1088/1748-9326/ab4d5e.
Yao, C., Z.-J. Li, H.-J. Bao, and Z.-B. Yu. 2009. “Application of a developed Grid-Xinanjiang model to Chinese watersheds for flood forecasting purpose.” J. Hydrol. Eng. 14 (9): 923–934. https://doi.org/10.1061/(ASCE)HE.1943-5584.0000067.
Yaseen, Z. M., O. Jaafar, R. C. Deo, O. Kisi, J. Adamowski, J. Quilty, and A. Elshafie. 2016. “Streamflow forecasting using extreme learning machines: A case study in a semi-arid region in Iraq.” J. Hydrol. 542 (Nov): 603–614. https://doi.org/10.1016/j.jhydrol.2016.09.035.
Yaseen, Z. M., H. Wan, A. Ameen, I. Ebtehaj, S. Razali, H. Bonakdari, S. Q. Salih, N. Al-Ansari, and S. Shahid. 2019. “Implementation of univariate paradigm for streamflow simulation using hybrid data-driven model: Case study in tropical region.” IEEE Access 7 (Jun): 74471–74481. https://doi.org/10.1109/ACCESS.2019.2920916.
Zhang, H., B. Wang, D. Li Liu, M. Zhang, L. M. Leslie, and Q. Yu. 2020. “Using an improved SWAT model to simulate hydrological responses to land use change: A case study of a catchment in tropical Australia.” J. Hydrol. 585 (Jun): 124822. https://doi.org/10.1016/j.jhydrol.2020.124822.
Zhang, J., Y. Zhu, X. Zhang, M. Ye, and J. Yang. 2018. “Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas.” J. Hydrol. 561 (Jun): 918–929. https://doi.org/10.1016/j.jhydrol.2018.04.065.
Zhou, R., and Y. Zhang. 2022. “Reconstruction of missing spring discharge by using deep learning models with ensemble empirical mode decomposition of precipitation.” Environ. Sci. Pollut. Res. 29 (54): 82451–82466. https://doi.org/10.1007/s11356-022-21597-w.
Zhou, R., and Y. Zhang. 2023. “Linear and nonlinear ensemble deep learning models for karst spring discharge forecasting.” J. Hydrol. 627 (Dec): 130394. https://doi.org/10.1016/j.jhydrol.2023.130394.
Zuo, G., J. Luo, N. Wang, Y. Lian, and X. He. 2020. “Two-stage variational mode decomposition and support vector regression for streamflow forecasting.” Hydrol. Earth Syst. Sci. 24 (11): 5491–5518. https://doi.org/10.5194/hess-24-5491-2020.
Information & Authors
Information
Published In
Journal of Hydrologic Engineering
Volume 29 • Issue 2 • April 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Jul 3, 2023
Accepted: Nov 22, 2023
Published online: Feb 8, 2024
Published in print: Apr 1, 2024
Discussion open until: Jul 8, 2024
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.