Catchment Area Multi-Streamflow Multiple Hours Ahead Forecast Based on Deep Learning


  • Divas Karimanzira Fraunhofer Institute of Optronics System Technologies and Image Exploitation (IOSB) Am Vogelherd 90, 98693 Ilmenau, Germany
  • Linda Ritzau Fraunhofer Institute of Optronics System Technologies and Image Exploitation (IOSB) Am Vogelherd 90, 98693 Ilmenau, Germany
  • Katharina Emde School 1Fraunhofer Institute of Optronic System Technologies and Image Exploitation (IOSB) Am Vogelherd 90, 98693 Karlsruhe, Germany



Deep Learning, Streamflow prediction, Graph Attention Neural Networks, Sequential model, Rainfall-Runoff Modelling


Modeling of rainfall-runoff is very critical for flood prediction studies in decision making for disaster management. Deep learning methods have proven to be very useful in hydrological prediction. To increase their acceptance in the hydrological community, they must be physic-informed and show some interpretability. They are several ways this can be achieved e.g. by learning from a fully-trained hydrological model which assumes the availability of the hydrological model or to use physic-informed data. In this work we developed a Graph Attention Network (GAT) with learnable Adjacency Matrix coupled with a Bi-directional Gated Temporal Convolutional Neural Network (2DGAT-BiLSTM). Physic-informed data with spatial information from Digital Elevation Model and geographical data is used to train it. Besides, precipitation, evapotranspiration and discharge, the model utilizes the catchment area characteristic information, such as instantaneous slope, soil type, drainage area etc. The method is compared to two different current developments in deep learning structures for streamflow prediction, which also utilize all the spatial and temporal information in an integrated way. One, namely Graph Neural Rainfall-Runoff Models (GNRRM) uses timeseries prediction on each node and a Graph Neural Network (GNN) to route the information to the target node and another one called STA-LSTM is based on Spatial and temporal Attention Mechanism and Long Short Term Memory (LSTM) for prediction. The different methods were compared in their performance in predicting the flow at several points of a pilot catchment area. With an average prediction NSE and KGE of 0.995 and 0.981, respectively for 2DGAT-BiLSTM, it could be shown that graph attention mechanism and learning the adjacency matrix for spatial information can boost the model performance and robustness, and bring interpretability and with the inclusion of domain knowledge the acceptance of the models.


. Löwe, R.; Urich, C.; Domingo, N.D.F.S.; Mark, O.; Deletic, A.; Arnbjerg-Nielsen, K. Assessment of Urban Pluvial Flood Risk and Efficiency of Adaptation Options Through Simulations—A New Generation of Urban Planning Tools. J. Hydrol. 2017, 550, 355–367

. Yildirim, E., & Demir, I. (2021). An Integrated Flood Risk Assessment and Mitigation Framework: A Case Study for Middle Cedar River Basin, Iowa, US. International Journal of Disaster Risk Reduction, 56, 102113.

. Xia, X.; Liang, Q.; Ming, X.; Hou, J. An efficient and stable hydrodynamic model with novel source term discretization schemes for overland flow and flood simulations. Water Resour. Res. 2017, 53, 3730–3759

. Kim, B.; Sanders, B.F.; Famiglietti, J.S.; Guinot, V. Urban flood modeling with porous shallow-water equations: A case study of model errors in the presence of anisotropic porosity. J. Hydrol. 2015, 523, 680–692.

. Cea, L.; Garrido, M.; Puertas, J. Experimental validation of two-dimensional depth-averaged models for forecasting rainfall-runoff from precipitation data in urban areas. J. Hydrol. 2010, 382, 88–102.

. Sit, M., Demiray, B. Z., Xiang, Z., Ewing, G. J., Sermet, Y., & Demir, I. (2020). A comprehensive review of deep learning applications in hydrology and water resources. Water Science and Technology, 82(12), 2635-2670.

. Kratzert, F., Klotz, D., Hochreiter, S., & Nearing, G. S. (2021). A note on leveraging synergy in multiple meteorological data sets with deep learning for rainfall–runoff modeling.Hydrology and Earth System Sciences, 25(5), 2685-2703

. Xiang, Z., Demir, I., Mantilla, R., & Krajewski, W. F. (2021). A Regional Semi-Distributed Streamflow Model Using Deep Learning.EarthArxiv.

. Xu, Y., Hu, C., Wu, Q., Li, Z., Jian, S., & Chen, Y. (2021). Application of temporal convolutional network for flood forecasting.Hydrology Research.

. Lin, K., Sheng, S., Zhou, Y., Liu, F., Li, Z., Chen, H., ... & Guo, S. (2020). The exploration of a Temporal Convolutional Network combined with Encoder-Decoder framework for runoff forecasting.Hydrology Research, 51(5), 1136-1149.

. Van, S. P., Le, H. M., Thanh, D. V., Dang, T. D., Loc, H. H., & Anh, D. T. (2020). Deep learning convolutional neural network in rainfall–runoff modelling. Journal of Hydroinformatics, 22(3), 541-561.

. Zhao, Q., Zhu, Y., Shu, K., Wan, D., Yu, Y., Zhou, X., & Liu, H. (2020). Joint Spatial and Temporal Modeling for Hydrological Prediction.IEEE Access,8, 78492-78503.

. Zhou, J., Cui, G., Zhang, Z., Yang, C., Liu, Z., & Sun, M. (2018). Graph neural networks: A review of methods and applications. arXiv preprint arXiv: 1812.08434.

. Zhongrun & Demir, Ibrahim. (2022). Fully distributed rainfall-runoff modeling using spatial-temporal graph neural network. 10.31223/X57P74.

. Yukai Ding, Yuelong Zhu, Jun Feng, et al. Interpretable spatio-temporal attention LSTM model for flood forecasting. Neurocomputing 2020(403): 348-359.

. S. Song, C. Lan, J. Xing, W. Zeng, J. Liu, An end-to-end spatio-temporal attention model for human action recognition from skeleton data, in: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4–9, 2017, San Francisco, California, USA, 2017, pp. 4263–4270. URL:

. Nash, J. E. and Sutcliffe, J. V.: River flow forecasting through conceptual models part I — A discussion of principles, J. Hydrol., 10(3), 282–290, doi:10.1016/0022-1694(70)90255-6, 1970.

. Gupta, H. V., Kling, H., Yilmaz, K. K. and Martinez, G. F.: Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling, J. Hydrol., 377(1-2), 80–91, doi:10.1016/j.jhydrol.2009.08.003, 2009.

. Shelef, E., & Hilley, G. E. (2013). Impact of flow routing on catchment area calculations, slope estimates, and numerical simulations of landscape development.Journal of Geophysical Research: Earth Surface,118(4), 2105-2123.

. P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, andY. Bengio, “Graph attention networks,” 2017.

. Fang, K., Shen, C., Kifer, D., & Yang, X. (2017). Prolongation of SMAP to spatiotemporally seamless coverage of continental US using a deep learning neural network.Geophysical Research Letters,44(21), 11-030.

. Kong, X., Xing, W., Wei, X., Bao, P., Zhang, J., & Lu, W. (2020). STGAT: Spatial-Temporal Graph Attention Networks for Traffic Flow Forecasting.IEEE Access,8, 134363-134372.

. Kang H, Yang S, Huang J, Oh J. Time series prediction of wastewater flow rate by bidirectional LSTM deep learning. International Journal of Control, Automation and Systems. 2020 Dec;18(12):3023-30.

. Lees, T., Buechel, M., Anderson, B., Slater, L., Reece, S., Coxon, G., & Dadson, S. J. (2021). Benchmarking Data-Driven Rainfall-Runoff Models in Great Britain: A comparison of LSTM-based models with four lumped conceptual models. Hydrology and Earth System Sciences Discussions, 1-41.

. T. Stańczyk and S. Mehrkanoon, “Deep graph convolutional networks for wind speed prediction,”Accepted for publication in Proc. of the 29th European Symposium on Artificial Neural Networks (ESANN), Oct. 2021, Bruges, Belgium, 2021.

. Castaneda-Gonzalez, M., Poulin, A., Romero-Lopez, R., Arsenault, R., Chaumont, D., Paquin, D. and Brissette, F.: Impacts of Regional Climate Model Spatial Resolution on Summer Flood Simulation, in HIC 2018. 13th International Conference on Hydroinformatics, vol. 3, pp. 372–362., 2018.

. Gelati, E., Decharme, B., Calvet, J. C., Minvielle, M., Polcher, J., Fairbairn, D. and Weedon, G. P.: Hydrological assessment of atmospheric forcing uncertainty in the Euro-Mediterranean area using a land surface model, Hydrol. Earth Syst. Sci., 22(4), 15 2091–2115, doi:10.5194/hess-22-2091-2018, 2018.

. Mosier, T. M., Hill, D. F. and Sharp, K. V.: How much cryosphere model complexity is just right? Exploration using the conceptual cryosphere hydrology framework, Cryosph., 10(5), 2147–2171, doi:10.5194/tc-10-2147-2016, 2016.

. Kling, H., Fuchs, M. and Paulin, M.: Runoff conditions in the upper Danube basin under an ensemble of climate changescenarios, J. Hydrol., 424-425, 264–277, doi:10.1016/j.jhydrol.2012.01.011, 2012.




How to Cite

Karimanzira, D., Ritzau, L., & Emde, K. (2022). Catchment Area Multi-Streamflow Multiple Hours Ahead Forecast Based on Deep Learning. Transactions on Engineering and Computing Sciences, 10(5), 15–29.