Long-Term Streamflow Prediction Using Hybrid SVR-ANN Based on Bayesian Model Averaging
Publication: Journal of Hydrologic Engineering
Volume 27, Issue 11
Abstract
The Volga River, as the primary supplier of the Caspian Sea, plays a huge role in its ecosystem sustainability. In this study, we analyze its runoff predictability for different monthly forecast horizons. Additionally, the meteorological and hydrological variables affecting runoff in each month are identified. A wide range of the potential variables was first collected and the Boruta variable preprocessing method was employed to select the important ones. Then the hybrid models were created by combining the selected variables and the data-driven models [i.e., support vector regression (SVR), artificial neural network (ANN), and multiple linear regression (MLR)]. To postprocess the predicted data, the Bayesian model averaging (BMA) method was employed using the combination of the Boruta–artificial neural network (B-ANN) and the Boruta–support vector regression (B-SVR) models. Finally, the Kling-Gupta efficiency (KGE) and the continuous ranked probability skill score (CRPSS) probabilistic evaluation criteria were applied to evaluate the hybrid models. The results showed that the streamflow of the previous steps is the most crucial variable in predicting the streamflow of all next horizons, while its significance decreases as the forecast time horizon increases. Moreover, the temperature variables have the unlike effect on the streamflow prediction and the minimum temperature for winter and spring and the maximum and the average temperatures for summer and autumn are the most effective ones. Correspondingly, BMA-B-ANN-SVR presents the best performance among the hybrid models (for example, the median of 0.8 and 0.91 for CRPSS and KGE in the first horizon, respectively); the reliability of its predicted runoff for different forecast horizons is much better than other hybrid models (B-ANN and B-SVR).
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
No original data were created in this study. We used 13 hydrological and meteorological variables (Table S1 ); their descriptions and sources are listed in the Supplemental Materials (there is no restrictions on using the data). All data and R codes of the model are publicly available at https://doi.org/10.5281/zenodo.4678663.
Acknowledgments
This study was supported by the Water Research Institute, Grant No. 320/9906-18.
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.
Ashrafzadeh, A., O. Kişi, P. Aghelpour, S. M. Biazar, and M. A. Masouleh. 2020. “Comparative study of time series models, support vector machines, and GMDH in forecasting long-term evapotranspiration rates in northern Iran.” J. Irrig. Drain. Eng. 146 (6): 04020010. https://doi.org/10.1061/(ASCE)IR.1943-4774.0001471.
Belkin, M., D. Hsu, S. Ma, and S. Mandal. 2019. “Reconciling modern machine-learning practice and the classical bias–variance trade-off.” Proc. Natl. Acad. Sci. U.S.A. 116 (32): 15849–15854. https://doi.org/10.1073/pnas.1903070116.
Bennett, J. C., Q. J. Wang, M. Li, D. E. Robertson, and A. Schepen. 2016. “Reliable long-range ensemble streamflow forecasts: Combining calibrated climate forecasts with a conceptual runoff model and a staged error model.” Water Resour. Res. 52 (10): 8238–8259. https://doi.org/10.1002/2016WR019193.
Bostani, H., and M. Sheikhan. 2017. “Hybrid of binary gravitational search algorithm and mutual information for feature selection in intrusion detection systems.” Soft Comput. 21 (9): 2307–2324. https://doi.org/10.1007/s00500-015-1942-8.
Boucher, M. A., L. Perreault, and F. Anctil. 2009. “Tools for the assessment of hydrological ensemble forecasts obtained by neural networks.” J. Hydroinf. 11 (3–4): 297–307. https://doi.org/10.2166/hydro.2009.037.
Bowden, G. J., H. R. Maier, and G. C. Dandy. 2005. “Input determination for neural network models in water resources applications. Part 2. Case study: Forecasting salinity in a river.” J. Hydrol. 301 (1–4): 93–107. https://doi.org/10.1016/j.jhydrol.2004.06.020.
Bradley, A. A., and S. S. Schwartz. 2011. “Summary verification measures and their interpretation for ensemble forecasts.” Mon. Weather Rev. 139 (9): 3075–3089. https://doi.org/10.1175/2010MWR3305.1.
Bras, R. L. 2015. “Complexity and organization in hydrology: A personal view.” Water Resour. Res. 51 (8): 6532–6548. https://doi.org/10.1002/2015WR016958.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324.
Cortes, C., and V. Vapnik. 1995. “Support-vector networks.” Mach. Learn. 20 (3): 273–297. https://doi.org/10.1007/BF00994018.
Danielson, J. J., and D. B. Gesch. 2011. Global multi-resolution terrain elevation data 2010 (GMTED2010). Washington, DC: USGS.
Darbandsari, P., and P. Coulibaly. 2019. “Inter-comparison of different Bayesian model averaging modifications in streamflow simulation.” Water 11 (8): 1707. https://doi.org/10.3390/w11081707.
Darbandsari, P., and P. Coulibaly. 2021. “HUP-BMA: An integration of hydrologic uncertainty processor and Bayesian model averaging for streamflow forecasting.” Water Resour. Res. 57 (10): e2020WR029433. https://doi.org/10.1029/2020WR029433.
Degenhardt, F., S. Seifert, and S. Szymczak. 2019. “Evaluation of variable selection methods for random forests and omics data sets.” Brief Bioinf. 20 (2): 492–503. https://doi.org/10.1093/bib/bbx124.
Devia, G. K., B. P. Ganasri, and G. S. Dwarakish. 2015. “A review on hydrological models.” Aquat. Procedia 4 (Jan): 1001–1007. https://doi.org/10.1016/j.aqpro.2015.02.126.
Duan, Q., N. K. Ajami, X. Gao, and S. Sorooshian. 2007. “Multi-model ensemble hydrologic prediction using Bayesian model averaging.” Adv. Water Resour. 30 (5): 1371–1386. https://doi.org/10.1016/j.advwatres.2006.11.014.
Efron, B., and R. J. Tibshirani. 1994. An introduction to the bootstrap. Boca Raton, FL: CRC Press.
Fisher, R. A. 1922. “On the mathematical foundations of theoretical statistics.” Philos. Trans. R. Soc. London, Ser. A 222 (594–604): 309–368. https://doi.org/10.1098/rsta.1922.0009.
Fraley, C., A. E. Raftery, T. Gneiting, and J. M. Sloughter. 2007. EnsembleBMA: An R package for probabilistic forecasting using ensembles and Bayesian model averaging.. Seattle: Dept. of Statistics, Univ. of Washington.
Gizaw, M. S., and T. Y. Gan. 2016. “Regional flood frequency analysis using support vector regression under historical and future climate.” J. Hydrol. 538 (Jul): 387–398. https://doi.org/10.1016/j.jhydrol.2016.04.041.
Gneiting, T., A. E. Raftery, A. H. Westveld, and T. Goldman. 2005. “Calibrated probabilistic forecasting using ensemble model output statistics and minimum CRPS estimation.” Mon. Weather Rev. 133 (5): 1098–1118. https://doi.org/10.1175/MWR2904.1.
Gupta, H. V., H. Kling, K. K. Yilmaz, and G. F. Martinez. 2009. “Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modeling.” J. Hydrol. 377 (1–2): 80–91. https://doi.org/10.1016/j.jhydrol.2009.08.003.
Hamil, T. M. 2001. “Interpretation of rank histograms for verifying ensemble forecasts.” Mon. Weather Rev. 129 (3): 550–560. https://doi.org/10.1175/1520-0493(2001)129%3C0550:IORHFV%3E2.0.CO;2.
Harrigan, S., E. Zsoter, L. Alfieri, C. Prudhomme, P. Salamon, F. Wetterhall, C. Barnard, H. Cloke, and F. Pappenberger. 2020. “GloFAS-ERA5 operational global river discharge reanalysis 1979–present.” Earth Syst. Sci. Data 12 (3): 2043–2060. https://doi.org/10.5194/essd-12-2043-2020.
Hasanabadi, H., M. Bahreinimotlagh, E. Jabbari, K. Kawanisi, H. Alizadeh, and Y. Olfatmiri. 2022. “Improving the accuracy of streamflow data acquired from the acoustic tomography technique using data despiking algorithms.” J. Hydrol. 608 (May): 127587. https://doi.org/10.1016/j.jhydrol.2022.127587.
Hersbach, H. 2000. “Decomposition of the continuous ranked probability score for ensemble prediction systems.” Weather Forecasting 15 (5): 559–570. https://doi.org/10.1175/1520-0434(2000)015%3C0559:DOTCRP%3E2.0.CO;2.
Hoeting, J. A., D. Madigan, A. E. Raftery, and C. T. Volinsky. 1999. “Bayesian model averaging: A tutorial.” Stat. Sci. 14 (4): 382–401. https://doi.org/10.1214/ss/1009212519.
Khosravi, K., A. Golkarian, and J. P. Tiefenbacher. 2022. “Using optimized deep learning to predict daily streamflow: A comparison to common machine learning algorithms.” Water Resour. Manage. 36 (2): 699–716. https://doi.org/10.1007/s11269-021-03051-7.
Khristodulo, O. I., A. F. Atnabaev, J. Leitner, I. Klein, A. J. Dietz, and A. V. Vorobev. 2017. “Snow cover characteristics for the hydrological Volga sub-basins and their influence on spring floods in the Republic of Bashkortostan.” In Proc., Computer Science and Information Technologies (CSIT’2017), 20–37. Moscow, Russia: Scientific Electronic Library.
Kuhn, M. 2008. “Building predictive models in R using the caret package.” J. Stat. Software 28 (5): 1–26. https://doi.org/10.18637/jss.v028.i05.
Kursa, M. B., and W. R. Rudnicki. 2010. “Feature selection with the Boruta package.” J. Stat. Software 36 (11): 1–13. https://doi.org/10.18637/jss.v036.i11.
Linke, S., et al. 2019. “Global hydro-environmental sub-basin and river reach characteristics at high spatial resolution.” Sci. Data 6 (1): 283. https://doi.org/10.1038/s41597-019-0300-6.
Liu, T., Y. Chen, B. Li, Y. Hu, H. Qiu, and Z. Liang. 2019. “Long-term streamflow forecasting for the Cascade Reservoir System of Han River using SWAT with CFS output.” Hydrol. Res. 50 (2): 655–671. https://doi.org/10.2166/nh.2018.114.
Louppe, G. 2014. “Understanding random forests: From theory to practice.” Preprint, submitted July 28, 2014. http://arxiv.org/abs/1407.7502.
Malik, A., Y. Tikhamarine, D. Souag-Gamane, O. Kisi, and Q. B. Pham. 2020. “Support vector regression optimized by meta-heuristic algorithms for daily streamflow prediction.” Stochastic Environ. Res. Risk Assess. 34 (11): 1755–1773. https://doi.org/10.1007/s00477-020-01874-1.
Massoud, E. C., V. Espinoza, B. Guan, and D. E. Waliser. 2019. “Global climate model ensemble approaches for future projections of atmospheric rivers.” Earth’s Future 7 (10): 1136–1151. https://doi.org/10.1029/2019EF001249.
Moon, T. K. 1996. “The expectation-maximization algorithm.” IEEE Signal Process Mag. 13 (6): 47–60. https://doi.org/10.1109/79.543975.
Polonskii, V. F., and L. P. Ostroumova. 2010. “Long-term and intraannual changes in run-off and water levels in the Volga River delta.” Russ. Meteorol. Hydrol. 35 (2): 121–128. https://doi.org/10.3103/S1068373910020068.
Quang, N. H. 2016. “Modelling soil erosion, flash flood prediction and evapotranspiration in northern Vietnam.” Ph.D. thesis, Dept. of Cartography, GIS and Remote Sensing, Institute of Geography, Univ. of Göttingen.
Raftery, A. E., T. Gneiting, F. Balabdaoui, and M. Polakowski. 2005. “Using Bayesian model averaging to calibrate forecast ensembles.” Mon. Weather Rev. 133 (5): 1155–1174. https://doi.org/10.1175/MWR2906.1.
Rathinasamy, M., J. Adamowski, and R. Khosa. 2013. “Multiscale streamflow forecasting using a new Bayesian model average based ensemble multi-wavelet Volterra nonlinear method.” J. Hydrol. 507 (Dec): 186–200. https://doi.org/10.1016/j.jhydrol.2013.09.025.
Ruiz-Aĺvarez, M., F. Gomariz-Castillo, and F. Alonso-Sarría. 2021. “Evapotranspiration response to climate change in semi-arid areas: Using random forest as multi-model ensemble method.” Water 13 (2): 222. https://doi.org/10.3390/w13020222.
Semenov, M. A., and P. Stratonovitch. 2010. “Use of multi-model ensembles from global climate models for assessment of climate change impacts.” Clim. Res. 41 (1): 1–14. https://doi.org/10.3354/cr00836.
Shin, Y., Y. Lee, and J. S. Park. 2020. “A weighting scheme in a multi-model ensemble for bias-corrected climate simulation.” Atmosphere 11 (8): 775. https://doi.org/10.3390/atmos11080775.
Smola, A. J. 1996. “Regression estimation with support vector learning machines.” Master’s thesis, Physics Dept., Technische Universität München.
Solomatine, D. P., and A. Ostfeld. 2008. “Data-driven modelling: Some past experiences and new approaches.” J. Hydroinf. 10 (1): 3–22. https://doi.org/10.2166/hydro.2008.015.
Sun, H., Y. Yang, R. Wu, D. Gui, J. Xue, Y. Liu, and D. Yan. 2019. “Improving estimation of cropland evapotranspiration by the bayesian model averaging method with surface energy balance models.” Atmosphere 10 (4): 188. https://doi.org/10.3390/atmos10040188.
Talagrand, O. 1999. “Evaluation of probabilistic prediction systems.” In Proc., Workshop proceedings, workshop on predictability. Reading, UK: European Centre for Medium-Range Weather Forecasts.
Tegegne, G., A. M. Melesse, and A. W. Worqlul. 2020. “Development of multi-model ensemble approach for enhanced assessment of impacts of climate change on climate extremes.” Sci. Total Environ. 704 (Feb): 135357. https://doi.org/10.1016/j.scitotenv.2019.135357.
Wang, J., W. Bao, Z. Xiao, and W. Si. 2022. “Multi-model integrated error correction for streamflow simulation based on Bayesian model averaging and dynamic system response curve.” J. Hydrol. 607 (Apr): 127518. https://doi.org/10.1016/j.jhydrol.2022.127518.
Wang, X., Y. Sun, S. Li, and F. Meng. 2020. “Hazard assessment of debris flows based on a PCA-GRNN model: A case study in Liaoning Province, China.” Arabian J. Geosci. 13 (4): 151. https://doi.org/10.1007/s12517-020-5136-z.
Xiang, Y., L. Gou, L. He, S. Xia, and W. Wang. 2018. “A SVR–ANN combined model based on ensemble EMD for rainfall prediction.” Appl. Soft Comput. 73 (Dec): 874–883. https://doi.org/10.1016/j.asoc.2018.09.018.
Xiao, Y., J. Wu, Z. Lin, and X. Zhao. 2018. “A deep learning-based multi-model ensemble method for cancer prediction.” Comput. Methods Programs Biomed. 153 (Jan): 1–9. https://doi.org/10.1016/j.cmpb.2017.09.005.
Yang, Z., Y. Yu, C. You, J. Steinhardt, and Y. Ma. 2020. “Rethinking bias-variance trade-off for generalization of neural networks.” In Proc., Int. Conf. on Machine Learning, 10767–10777. Brookline, MA: Journal of Machine Learning Research.
Yin, W., Z. Fan, N. Tangdamrongsub, L. Hu, and M. Zhang. 2021. “Comparison of physical and data-driven models to forecast groundwater level changes with the inclusion of GRACE–A case study over the state of Victoria, Australia.” J. Hydrol. 602 (Nov): 126735. https://doi.org/10.1016/j.jhydrol.2021.126735.
Zhu, S., X. Luo, Z. Xu, and L. Ye. 2019. “Seasonal streamflow forecasts using mixture-kernel GPR and advanced methods of input variable selection.” Hydrol. Res. 50 (1): 200–214. https://doi.org/10.2166/nh.2018.023.
Information & Authors
Information
Published In
Journal of Hydrologic Engineering
Volume 27 • Issue 11 • November 2022
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Oct 30, 2021
Accepted: Jul 5, 2022
Published online: Sep 15, 2022
Published in print: Nov 1, 2022
Discussion open until: Feb 15, 2023
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.
Cited by
- Shuang Zhu, Maoyu Zhang, Chao Wang, Jun Guo, Xudong Chen, Mengfei Xie, A Probabilistic Runoff Prediction Model Based on Improved Long Short-Term Memory and Interval Correction, Journal of Hydrologic Engineering, 10.1061/JHYEFF.HEENG-6091, 29, 4, (2024).
- Amir Bahramifar, Hassan Afshin, Mehrdad Emami Tabrizi, Optimized simulation of river flow rate using regression-based models, Acta Geophysica, 10.1007/s11600-022-00976-4, (2023).
- T. Singh, R. V. S. Uppaluri, Machine learning tool-based prediction and forecasting of municipal solid waste generation rate: a case study in Guwahati, Assam, India, International Journal of Environmental Science and Technology, 10.1007/s13762-022-04644-4, (2022).