Hybrid Deep Learning Time-Lagged Precipitation-Runoff Model
Publication: Journal of Hydrologic Engineering
Volume 29, Issue 6
Abstract
Hydrological models are pivotal tools for comprehending and managing water resources in various applications, including urban and hydrological planning. Nevertheless, these models often grapple with challenges due to the unavailability and sensitivity of specific data required for calibration. This paper aims to explore machine learning algorithms as a potential alternative to traditional hydrological models for flow estimation, focusing on the case study of the dam Três Marias-MG in Brazil. Hybrid models merging spatial data processing with deep learning were investigated to determine the optimal data configuration for enhanced learning. The study area was partitioned into 91 quadrants, with distances from each quadrant’s centroid to the flow point calculated. With an estimated velocity of , the lag time, denoting the time each quadrant takes to contribute to the flow, was established. This information facilitated the adjustment of the input precipitation data vector to align with the flow contribution output. The model achieved an average error of approximately 4.4% and a relative peak flow of 19.7% compared with 5.1% and 40% with the regular model, making it a robust approach to flow estimation.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some data, models, or code generated or used during the study are available in a repository online in accordance with funder data retention policies: Operador Nacional do Sistema elétrico. “Arquitetura Aberta.” Accessed September 10, 2021. https://www.ons.org.br/Paginas/topo/arquitetura-aberta.aspx. National Aeronautics and Space Administration (NASA). “Goddard Earth Sciences Data and Information Services Center Database.” Accessed: February 2, 2022. https://disc.gsfc.nasa.gov/. Some data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request: Python code with LSTM and GRU networks.
Acknowledgments
The authors would like to express sincere gratitude to Professor Celso Augusto Guimarães Santos from Federal University of Paraiba (UFPA) who contributed to the success of this research. The authors would also like to extend appreciation to Intel for its generous support and provision of resources that enabled the execution of this project. Their commitment to advancing technology and innovation has been instrumental in the development of the research. Additionally, the authors wish to acknowledge the Coordination for the Improvement of Higher Education Personnel (CAPES) for its financial assistance and scholarships, which have been pivotal in facilitating the authors’ studies and research endeavors. Furthermore, the authors extend appreciation to Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro (FAPERJ) for funding this study under Grant SEI-260003/000537/2023. Its financial support has been integral in driving forward this investigation. The collective contributions of Professor Celso Augusto, Intel, CAPES, and FAPERJ have played a crucial role in the successful completion of this work, and the authors express heartfelt gratitude for their unwavering support and guidance.
References
Ayzel, G., and M. Heistermann. 2021. “The effect of calibration data length on the performance of a conceptual hydrological model versus LSTM and GRU: A case study for six basins from the CAMELS dataset.” Comput. Geosci. 149 (Apr): 104708. https://doi.org/10.1016/j.cageo.2021.104708.
Bahdanau, D., K. Cho, and Y. Bengio. 2014. “Neural machine translation by jointly learning to align and translate.” Preprint, submitted September 1, 2014. https://arxiv.org/abs/1409.0473.
Cho, K., B. Van Merrienboer, Ç. Gülçehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio. 2014. “Learning phrase representations using RNN encoder-decoder for statistical machine translation.” Preprint, submitted June 3, 2014. https://arxiv.org/abs/1406.1078.
da Silva Cruz, J. 2018. “Modelo vazão-velocidade para avaliação de potencial hidrocinético.” Accessed January 15, 2023. https://ppgec.propesp.ufpa.br/ARQUIVOS/dissertacoes/2018/josias.pdf.pdf.
de Macedo Machado Freire, P. K. 2019. “Modelos robustos de previsão de vazão baseados em wavelet e redes neurais artificiais.” Ph.D. thesis, Dept. of Environmental Civil Engineering, Universidade Federal da Paraíba.
De Paiva, L. F. G., S. M. Montenegro, and M. Cataldi. 2020. “Prediction of monthly flows for Três Marias Reservoir (São Francisco River basin) using the CFS climate forecast model.” RBRH 25 (Apr): e16. https://doi.org/10.1590/2318-0331.252020190067.
Diez-Sierra, J., and M. del Jesus. 2020. “Long-term rainfall prediction using atmospheric synoptic patterns in semi-arid climates with statistical and machine learning methods.” J. Hydrol. 586 (Jul): 124789. https://doi.org/10.1016/j.jhydrol.2020.124789.
Frame, J. M., F. Kratzert, D. Klotz, M. Gauch, G. Shalev, O. Gilon, L. M. Qualls, H. V. Gupta, and G. S. Nearing. 2022. “Deep learning rainfall–runoff predictions of extreme events.” Hydrol. Earth Syst. Sci. 26 (13): 3377–3392. https://doi.org/10.5194/hess-26-3377-2022.
Gao, S., Y. Huang, S. Zhang, J. Han, G. Wang, M. Zhang, and Q. Lin. 2020. “Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation.” J. Hydrol. 589 (Oct): 125188. https://doi.org/10.1016/j.jhydrol.2020.125188.
Goodfellow, I., Y. Bengio, and A. Courville. 2016. Deep learning. Cambridge, MA: MIT Press.
Haykin, S. 2007. Redes neurais: Princćpios e prática. 2nd ed. Porto Alegre, Brazil: Bookman.
Hochreiter, S., and J. Schmidhuber. 1997. “Long short-term memory.” Neural Comput. 9 (8): 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735.
Kapoor, A., S. Pathiraja, L. Marshall, and R. Chandra. 2023. “DeepGR4J: A deep learning hybridization approach for conceptual rainfall-runoff modeling.” Environ. Modell. Software 169 (Nov): 105831. https://doi.org/10.1016/j.envsoft.2023.105831.
Kousali, M., M. Salarijazi, and K. Ghorbani. 2022. “Estimation of non-stationary behavior in annual and seasonal surface freshwater volume discharged into the Gorgan Bay, Iran.” Nat. Resour. Res. 31 (2): 835–847. https://doi.org/10.1007/s11053-022-10010-5.
Kratzert, F., D. Klotz, S. Hochreiter, and G. S. Nearing. 2021. “A note on leveraging synergy in multiple meteorological data sets with deep learning for rainfall–runoff modeling.” Hydrol. Earth Syst. Sci. 25 (5): 2685–2703. https://doi.org/10.5194/hess-25-2685-2021.
Le, X.-H., D.-H. Nguyen, S. Jung, M. Yeon, and G. Lee. 2021. “Comparison of deep learning techniques for river streamflow forecasting.” IEEE Access 9 (May): 71805–71820. https://doi.org/10.1109/ACCESS.2021.3077703.
Lee, T., J.-Y. Shin, J.-S. Kim, and V. P. Singh. 2020. “Stochastic simulation on reproducing long-term memory of hydroclimatological variables using deep learning model.” J. Hydrol. 582 (Mar): 124540. https://doi.org/10.1016/j.jhydrol.2019.124540.
Ni, L., D. Wang, V. P. Singh, J. Wu, Y. Wang, Y. Tao, and J. Zhang. 2020. “Streamflow and rainfall forecasting by two long short-term memory-based models.” J. Hydrol. 583 (Apr): 124296. https://doi.org/10.1016/j.jhydrol.2019.124296.
Pham, B. T., L. M. Le, T.-T. Le, K.-T. T. Bui, V. M. Le, H.-B. Ly, and I. Prakash. 2020. “Development of advanced artificial intelligence models for daily rainfall prediction.” Atmos. Res. 237 (Jun): 104845. https://doi.org/10.1016/j.atmosres.2020.104845.
Safari, M. J. S., S. Rahimzadeh Arashloo, and A. Danandeh Mehr. 2020. “Rainfall-runoff modeling through regression in the reproducing kernel Hilbert space algorithm.” J. Hydrol. 587 (Aug): 125014. https://doi.org/10.1016/j.jhydrol.2020.125014.
Santos, C. A. G., P. K. M. M. Freire, G. B. L. Silva, and R. M. Silva. 2014. “Discrete wavelet transform coupled with ANN for daily discharge forecasting into três marias reservoir.” Proc. Int. Assoc. Hydrol. Sci. 364 (Sep): 100–105. https://doi.org/10.5194/piahs-364-100-2014.
Schuster, M., and K. Paliwal. 1997. “Bidirectional recurrent neural networks.” IEEE Trans. Signal Process. 45 (11): 2673–2681. https://doi.org/10.1109/78.650093.
Sit, M. A., B. Z. Demiray, and I. Demir. 2021. “Short-term hourly streamflow prediction with graph convolutional GRU networks.” Preprint, submitted July 7, 2021. https://arxiv.org/abs/2107.07039.
Tucci, C. E. M. 1998. Modelos hidrológicos. Porto Alegre, Brazil: Associação Brasileira de Recursos Hídricos.
Xu, Y., C. Hu, Q. Wu, S. Jian, Z. Li, Y. Chen, G. Zhang, Z. Zhang, and S. Wang. 2022. “Research on particle swarm optimization in lstm neural networks for rainfall-runoff simulation.” J. Hydrol. 608 (May): 127553. https://doi.org/10.1016/j.jhydrol.2022.127553.
Yin, H., X. Zhang, F. Wang, Y. Zhang, R. Xia, and J. Jin. 2021. “Rainfall-runoff modeling using lstm-based multi-state-vector sequence-to-sequence model.” J. Hydrol. 598 (Jul): 126378. https://doi.org/10.1016/j.jhydrol.2021.126378.
Yokoo, K., K. Ishida, A. Ercan, T. Tu, T. Nagasato, M. Kiyama, and M. Amagasaki. 2021. “Capabilities of deep learning models on learning physical relationships: Case of rainfall-runoff modeling with LSTM.” Sci. Total Environ. 802 (Jan): 149876. https://doi.org/10.1016/j.scitotenv.2021.149876.
Zhao, Y., N. Dong, Z. Li, W. Zhang, M. Yang, and H. Wang. 2021. “Future precipitation, hydrology and hydropower generation in the Yalong river basin: Projections and analysis.” J. Hydrol. 602 (Nov): 126738. https://doi.org/10.1016/j.jhydrol.2021.126738.
Zolfaghari, M., and M. R. Golabi. 2021. “Modeling and predicting the electricity production in hydropower using conjunction of wavelet transform, long short-term memory and random forest models.” Renewable Energy 170 (Jun): 1367–1381. https://doi.org/10.1016/j.renene.2021.02.017.
Information & Authors
Information
Published In
Journal of Hydrologic Engineering
Volume 29 • Issue 6 • December 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Dec 5, 2023
Accepted: Jul 17, 2024
Published online: Sep 26, 2024
Published in print: Dec 1, 2024
Discussion open until: Feb 26, 2025
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.