Deep learning for cross-region streamflow and flood forecasting at a global scale

Binlan Zhang; Chaojun Ouyang; Peng Cui; Qingsong Xu; Dongpo Wang; Fei Zhang; Zhong Li; Linfeng Fan; Marco Lovati; Yanling Liu; Qianqian Zhang

doi:10.1016/j.xinn.2024.100617

The Innovation > 2024 Vol. 5 > No. 3

Next Article Previous Article

Article Open Access

Cite PDF

Deep learning for cross-region streamflow and flood forecasting at a global scale

1.
State Key Laboratory of Mountain Hazards and Engineering Resilience, Institute of Mountain Hazards and Environment, Chinese Academy of Sciences, Chengdu 610299, China
2.
State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, China
3.
Data Science in Earth Observation, Technical University of Munich, 80333 Munich, Germany
4.
State Key Laboratory of Loess and Quaternary Geology, Institute of Earth Environment, Chinese Academy of Sciences, Xi'an 710061, China
5.
Department of Civil Engineering, McMaster University, Hamilton, ON L8S 4L8, Canada
6.
Chengdu University of Information Technology, Chengdu 610225, China

Show all affliationsShow less

More Information

⁷These authors contributed equally
Corresponding author: cjouyang@imde.ac.cn
Received Date: December 19, 2023

Accepted Date: March 24, 2024

Published Online: March 26, 2024

The Innovation 5(3), https://doi.org/10.1016/j.xinn.2024.100617 | Cite this article

GRAPHICAL ABSTRACT

GRAPHICAL ABSTRACT

DownLoad: Full size image

PUBLIC SUMMARY

PUBLIC SUMMARY
1. ■ An end-to-end model called ED-DLSTM with superior flood forecasting in gauged and ungauged catchments was proposed.
2. ■ For the first time, multiple hydrological AI models were trained and provided comparative analyses at a global-scale.
3. ■ The time-series forecasting capacities were apparently improved by the encoding of spatial attributes and transferability ability was well explained.

ABSTRACT

ABSTRACT

Streamflow and flood forecasting remains one of the long-standing challenges in hydrology. Traditional physically based models are hampered by sparse parameters and complex calibration procedures particularly in ungauged catchments. We propose a novel hybrid deep learning model termed encoder-decoder double-layer long short-term memory (ED-DLSTM) to address streamflow forecasting at global scale for all (gauged and ungauged) catchments. Using historical datasets, ED-DLSTM yields a mean Nash-Sutcliffe efficiency coefficient (NSE) of 0.75 across more than 2, 000 catchments from the United States, Canada, Central Europe, and the United Kingdom, highlighting improvements by the state-of-the-art machine learning over traditional hydrologic models. Moreover, ED-DLSTM is applied to 160 ungauged catchments in Chile and 76.9% of catchments obtain NSE > 0 in the best situation. The interpretability of cross-region capacities of ED-DLSTM are established through the cell state induced by adding a spatial attribute encoding module, which can spontaneously form hydrological regionalization effects after performing spatial coding for different catchments. The study demonstrates the potential of deep leaning methods to overcome the ubiquitous lack of hydrologic information and deficiencies in physical model structure and parameterization.

FullText(HTML)

REFERENCES

[1]	Ingraham, J.B., Baranov, M., Costello, Z., et al. (2023). Illuminating protein space with a programmable generative model. Nature *623*(7989): 1070-1078. https://doi.org/10.1038/s41586-023-06728-8. View in Article CrossRef Google Scholar
[2]	Jiang, T.T., Fang, L., and Wang, K. (2023). Deciphering "the language of nature": A transformer-based language model for deleterious mutations in proteins. Innovation 4(5): 100487. https://doi.org/10.1016/j.xinn.2023.100487. View in Article CrossRef Google Scholar
[3]	Yurtsever, E., Lambert, J., Carballo, A., et al. (2020). A Survey of Autonomous Driving: Common Practices and Emerging Technologies. IEEE Access 8: 58443-58469. https://doi.org/10.1109/access.2020.2983149. View in Article CrossRef Google Scholar
[4]	Zhang, Y., Long, M., Chen, K., et al. (2023). Skilful nowcasting of extreme precipitation with NowcastNet. Nature *619*(7970): 526-532. https://doi.org/10.1038/s41586-023-06184-4. View in Article CrossRef Google Scholar
[5]	Epstein, Z., Hertzmann, A., Investigators of Human Creativity, et al. (2023). Art and the science of generative AI. Science *380*(6650): 1110-1111. https://doi.org/10.1126/science.adh4451. View in Article CrossRef Google Scholar
[6]	Bubeck, S., Chandrasekaran, V., Eldan, R., et al. (2023). Sparks of artificial general intelligence: Early experiments with gpt-4. Preprint at arXiv. https://doi.org/10.48550/arXiv.2303.12712. View in Article CrossRef Google Scholar
[7]	Nichol, A., Dhariwal, P., Ramesh, A., et al. (2021). Glide: Towards photorealistic image generation and editing with text-guided diffusion models. Preprint at arXiv. https://doi.org/10.48550/arXiv.2112.10741. View in Article CrossRef Google Scholar
[8]	Huang, T., Xu, H., Wang, H., et al. (2023). Artificial intelligence for medicine: Progress, challenges, and perspectives. Innovat. Med. 1(2): 100030. https://doi.org/10.59717/j.xinn-med.2023.100030. View in Article CrossRef Google Scholar
[9]	Troin, M., Arsenault, R., Wood, A.W., et al. (2021). Generating Ensemble Streamflow Forecasts: A Review of Methods and Approaches Over the Past 40 Years. Water Resour. Res. 57(7): e2020WR028392. https://doi.org/10.1029/2020WR028392. View in Article CrossRef Google Scholar
[10]	Ghimire, S., Yaseen, Z.M., Farooque, A.A., et al. (2021). Streamflow prediction using an integrated methodology based on convolutional neural network and long short-term memory networks. Sci. Rep. 11(1): 17497. https://doi.org/10.1038/s41598-021-96751-4. View in Article CrossRef Google Scholar
[11]	Bi, K., Xie, L., Zhang, H., et al. (2023). Accurate medium-range global weather forecasting with 3D neural networks. Nature *619*(7970): 533-538. https://doi.org/10.1038/s41586-023-06185-3. View in Article CrossRef Google Scholar
[12]	Xu, Y., Liu, X., Cao, X., et al. (2021). Artificial intelligence: A powerful paradigm for scientific research. Innovation 2(4): 100179. https://doi.org/10.1016/j.xinn.2021.100179. View in Article CrossRef Google Scholar
[13]	Hunt, K.M.R., Matthews, G.R., Pappenberger, F., et al. (2022). Using a long short-term memory (LSTM) neural network to boost river streamflow forecasts over the western United States. Hydrol. Earth Syst. Sci. 26(21): 5449-5472. https://doi.org/10.5194/hess-26-5449-2022. View in Article CrossRef Google Scholar
[14]	Rahmani, F., Shen, C., Oliver, S., et al. (2021). Deep learning approaches for improving prediction of daily stream temperature in data-scarce, unmonitored, and dammed basins. Hydrol. Process. 35(11): e14400. https://doi.org/10.1002/hyp.14400. View in Article CrossRef Google Scholar
[15]	Zhi, W., Feng, D., Tsai, W.-P., et al. (2021). From Hydrometeorology to River Water Quality: Can a Deep Learning Model Predict Dissolved Oxygen at the Continental Scale? Environ. Sci. Technol. 55(4): 2357-2368. https://doi.org/10.1021/acs.est.0c06783. View in Article CrossRef Google Scholar
[16]	Girihagama, L., Naveed Khaliq, M., Lamontagne, P., et al. (2022). Streamflow modelling and forecasting for Canadian watersheds using LSTM networks with attention mechanism. Neural Comput. Appl. 34(22): 19995-20015. https://doi.org/10.1007/s00521-022-07523-8. View in Article CrossRef Google Scholar
[17]	Kişi, Ö. (2007). Streamflow Forecasting Using Different Artificial Neural Network Algorithms. J. Hydrol. Eng. 12(5): 532-539. https://doi.org/10.1061/(ASCE)1084-0699(2007)12:5(532). View in Article CrossRef Google Scholar
[18]	Kratzert, F., Klotz, D., Brenner, C., et al. (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. View in Article CrossRef Google Scholar
[19]	Barzegar, R., Aalami, M.T., and Adamowski, J. (2021). Coupling a hybrid CNN-LSTM deep learning model with a Boundary Corrected Maximal Overlap Discrete Wavelet Transform for multiscale Lake water level forecasting. J. Hydrol. *598*: 126196. https://doi.org/10.1016/j.jhydrol.2021.126196. View in Article CrossRef Google Scholar
[20]	Yin, H., Guo, Z., Zhang, X., et al. (2022). RR-Former: Rainfall-runoff modeling based on Transformer. J. Hydrol. *609*: 127781. https://doi.org/10.1016/j.jhydrol.2022.127781. View in Article CrossRef Google Scholar
[21]	Dar, Y., Muthukumar, V., and Baraniuk, R.G. (2021). A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning. Preprint at arXiv. https://doi.org/10.48550/arXiv.2109.02355. View in Article CrossRef Google Scholar
[22]	He, K., Zhang, X., Ren, S., et al (2016). Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). DOI: https://doi.org/10.1109/CVPR.2016.90. View in Article Google Scholar
[23]	He, K., Zhang, X., Ren, S., et al (2014). Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. In D. Fleet, T. Pajdla, B. Schiele, et al, eds. Computer Vision - ECCV 2014. Springer International Publishing. DOI: https://doi.org/10.1007/978-3-319-10578-9_23. View in Article Google Scholar
[24]	McCuen, R.H., Knight, Z., and Cutter, A.G. (2006). Evaluation of the Nash–Sutcliffe Efficiency Index. J. Hydrol. Eng. 11(6): 597-602. https://doi.org/10.1061/(ASCE)1084-0699(2006)11:6(597). View in Article CrossRef Google Scholar
[25]	Jones, T.R., Roberts, W.H.G., Steig, E.J., et al. (2018). Southern Hemisphere climate variability forced by Northern Hemisphere ice-sheet topography. Nature *554*(7692): 351-355. https://doi.org/10.1038/nature24669. View in Article CrossRef Google Scholar
[26]	Jiang, S., Zheng, Y., Wang, C., et al. (2022). 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. View in Article CrossRef Google Scholar
[27]	Gauch, M., Mai, J., and Lin, J. (2021). The proper care and feeding of CAMELS: How limited training data affects streamflow prediction. Environ. Model. Softw. *135*: 104926. https://doi.org/10.1016/j.envsoft.2020.104926. View in Article CrossRef Google Scholar
[28]	Patil, S., and Stieglitz, M. (2011). Hydrologic similarity among catchments under variable flow conditions. Hydrol. Earth Syst. Sci. 15(3): 989-997. https://doi.org/10.5194/hess-15-989-2011. View in Article CrossRef Google Scholar
[29]	Gong, T., Lee, T., Stephenson, C., et al. (2019). A Comparison of Loss Weighting Strategies for Multi task Learning in Deep Neural Networks. IEEE Access 7: 141627-141632. https://doi.org/10.1109/ACCESS.2019.2943604. View in Article CrossRef Google Scholar
[30]	Florez-Lopez, R., and Ramon-Jeronimo, J.M. (2015). Enhancing accuracy and interpretability of ensemble strategies in credit risk assessment. A correlated-adjusted decision forest proposal. Expert Syst. Appl. 42(13): 5737-5753. https://doi.org/10.1016/j.eswa.2015.02.042. View in Article CrossRef Google Scholar
[31]	Shen, C. (2018). A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists. Water Resour. Res. 54(11): 8558-8593. https://doi.org/10.1029/2018WR022643. View in Article CrossRef Google Scholar
[32]	Li, Z., Feng, Q., Wang, X., et al. (2023). Accelerated multiphase water transformation in global mountain regions since 1990. Innovation Geosci. 1(3): 100033. https://doi.org/10.59717/j.xinn-geo.2023.100033. View in Article CrossRef Google Scholar
[33]	Wang, F., Harindintwali, J.D., Wei, K., et al. (2023). Climate change: Strategies for mitigation and adaptation. Innovation Geosci. 1(1): 100015. https://doi.org/10.59717/j.xinn-geo.2023.100015. View in Article CrossRef Google Scholar
[34]	Wei, K., Ouyang, C., Duan, H., et al. (2020). Reflections on the Catastrophic 2020 Yangtze River Basin Flooding in Southern China. Innovation. 1(2): 100038. https://doi.org/10.1016/j.xinn.2020.100038. View in Article CrossRef Google Scholar
[35]	Kao, I.F., Zhou, Y., Chang, L.-C., et al. (2020). Exploring a Long Short-Term Memory based Encoder-Decoder framework for multi-step-ahead flood forecasting. J. Hydrol. *583*: 124631. https://doi.org/10.1016/j.jhydrol.2020.124631. View in Article CrossRef Google Scholar
[36]	Linke, S., Lehner, B., Ouellet Dallaire, C., 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. View in Article CrossRef Google Scholar
[37]	Hersbach, H., Bell, B., Berrisford, P., et al. (2020). The ERA5 global reanalysis. Q. J. R. Meteorol. Soc. *146*(730): 1999-2049. https://doi.org/10.1002/qj.3803. View in Article CrossRef Google Scholar
[38]	Bottou, L. (2012). Stochastic Gradient Descent Tricks. In Neural Networks: Tricks of the Trade: Second Edition, G. Montavon, G.B. Orr, and K. -R. Müller, eds. (Springer Berlin Heidelberg), pp. 421-436. https://doi.org/10.1007/978-3-642-35289-8_25. View in Article Google Scholar
[39]	Kratzert, F., Nearing, G., Addor, N., et al. (2023). Caravan - A global community dataset for large-sample hydrology. Sci. Data 10(1): 61. https://doi.org/10.1038/s41597-023-01975-w. View in Article CrossRef Google Scholar
[40]	Newman, A.J., Clark, M.P., Sampson, K., et al. (2015). Development of a large-sample watershed-scale hydrometeorological data set for the contiguous USA: data set characteristics and assessment of regional variability in hydrologic model performance. Hydrol. Earth Syst. Sci. 19(1): 209-223. https://doi.org/10.5194/hess-19-209-2015. View in Article CrossRef Google Scholar
[41]	Arsenault, R., Brissette, F., Martel, J. -L., et al. (2020). A comprehensive, multisource database for hydrometeorological modeling of 14, 425 North American watersheds. Sci. Data 7(1): 243. https://doi.org/10.1038/s41597-020-00583-2. View in Article CrossRef Google Scholar
[42]	Klingler, C., Schulz, K., and Herrnegger, M. (2021). LamaH-CE: LArge-SaMple DAta for Hydrology and Environmental Sciences for Central Europe. Earth Syst. Sci. Data 13(9): 4529-4565. https://doi.org/10.5194/essd-13-4529-2021. View in Article CrossRef Google Scholar
[43]	Coxon, G., Addor, N., Bloomfield, J.P., et al. (2020). CAMELS-GB: hydrometeorological time series and landscape attributes for 671 catchments in Great Britain. Earth Syst. Sci. Data 12(4): 2459-2483. https://doi.org/10.5194/essd-12-2459-2020. View in Article CrossRef Google Scholar
[44]	Goh, A.T.C. (1995). Back-propagation neural networks for modeling complex systems. Artif. Intell. Eng. 9(3): 143-151. https://doi.org/10.1016/0954-1810(94)00011-S. View in Article CrossRef Google Scholar
[45]	Modarres, R. (2007). Streamflow drought time series forecasting. Stoch. Environ. Res. Risk Assess. 21(3): 223-233. https://doi.org/10.1007/s00477-006-0058-1. View in Article CrossRef Google Scholar
[46]	Wang, H., Reich, B., and Lim, Y.H. (2012). A Bayesian approach to probabilistic streamflow forecasts. J. Hydroinf. 15(2): 381-391. https://doi.org/10.2166/hydro.2012.080. View in Article CrossRef Google Scholar
[47]	Zealand, C.M., Burn, D.H., and Simonovic, S.P. (1999). Short term streamflow forecasting using artificial neural networks. J. Hydrol. *214*(1): 32-48. https://doi.org/10.1016/S0022-1694(98)00242-X. View in Article CrossRef Google Scholar
[48]	Zhang, Z., Koren, V., Reed, S., et al. (2012). SAC-SMA a priori parameter differences and their impact on distributed hydrologic model simulations. J. Hydrol. *420–421*: 216-227. https://doi.org/10.1016/j.jhydrol.2011.12.004. View in Article CrossRef Google Scholar
[49]	Beven, K., and Young, P. (2013). A guide to good practice in modeling semantics for authors and referees. Water Resour. Res. 49(8): 5092-5098. https://doi.org/10.1002/wrcr.20393. View in Article CrossRef Google Scholar
[50]	Gauch, M., and Lin, J.J. (2020). A Data Scientist's Guide to Streamflow Prediction. Preprint at arXiv. https://doi.org/10.48550/arXiv.2006.12975. View in Article CrossRef Google Scholar
[51]	Zhang, Z. (2018). Improved adam optimizer for deep neural networks. 2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS). IEEE. View in Article Google Scholar
[52]	Loshchilov, I., and Hutter, F.J. (2016). Sgdr: Stochastic gradient descent with warm restarts. Preprint at arXiv. https://doi.org/10.48550/arXiv.1608.03983. View in Article CrossRef Google Scholar
[53]	Khalid, S., Khalil, T., and Nasreen, S. (2014). A survey of feature selection and feature extraction techniques in machine learning. 2014 Science and Information Conference. View in Article Google Scholar
[54]	Yilmaz, K.K., Gupta, H.V., and Wagener, T. (2008). A process-based diagnostic approach to model evaluation: Application to the NWS distributed hydrologic model. Water Resour. Res. 44(9). https://doi.org/10.1029/2007WR006716. View in Article CrossRef Google Scholar

Cited by

ABOUT THIS ARTICLE

Cite this article:

Zhang B., Ouyang C., Cui P., et al., (2024). Deep learning for cross-region streamflow and flood forecasting at a global scale. The Innovation 5(3), 100617. https://doi.org/10.1016/j.xinn.2024.100617

Zhang B., Ouyang C., Cui P., et al., (2024). Deep learning for cross-region streamflow and flood forecasting at a global scale. The Innovation 5(3), 100617. https://doi.org/10.1016/j.xinn.2024.100617

Welcome!

To request copyright permission to republish or share portions of our works, please visit Copyright Clearance Center's (CCC) Marketplace website at marketplace.copyright.com.

PDF

Figures(7) Tables(1)

Article Metrics

Article views(10594) PDF downloads(1768)

Deep learning for cross-region streamflow and flood forecasting at a global scale

GRAPHICAL ABSTRACT

PUBLIC SUMMARY

ABSTRACT

REFERENCES

ABOUT THIS ARTICLE

Cite this article:

Welcome!

Share

Article Metrics

Relative Articles

Cited by

Catalog

{{newsColumn.name}}

Journal links

{{newsColumn.name}}

Collections

Stay connected

Deep learning for cross-region streamflow and flood forecasting at a global scale

GRAPHICAL ABSTRACT

PUBLIC SUMMARY

ABSTRACT

REFERENCES

ABOUT THIS ARTICLE

Cite this article:

Welcome!

Share

Article Metrics

Relative Articles

Cited by

Catalog

Export File

Citation

Format

Content

{{newsColumn.name}}

Journal links

{{newsColumn.name}}

Collections

Stay connected