Articles | Volume 26, issue 15
https://doi.org/10.5194/hess-26-4013-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-26-4013-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
05 Aug 2022
Research article |
| 05 Aug 2022
| 05 Aug 2022
Flood forecasting with machine learning models in an operational framework
Sella Nevo
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Hebrew University of Jerusalem, Institute of Earth Sciences, Safra Campus, Jerusalem 91904, Israel
Adi Gerzi Rosenthal
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Asher Metzger
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Chen Barshai
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Dana Weitzner
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Dafi Voloshin
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Frederik Kratzert
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Gal Elidan
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Hebrew University of Jerusalem, Department of Statistics, Mount Scopus Campus, Jerusalem 91905, Israel
Gideon Dror
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Gregory Begelman
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Grey Nearing
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Guy Shalev
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Hila Noga
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Ira Shavitt
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Liora Yuklea
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Moriah Royz
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Niv Giladi
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Nofar Peled Levi
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Ofir Reich
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Oren Gilon
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Ronnie Maor
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Shahar Timnat
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Tal Shechter
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Vladimir Anisimov
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Yotam Gigi
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Yuval Levin
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Zach Moshe
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Zvika Ben-Haim
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Avinatan Hassidim
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Yossi Matias
Google Research, Yigal Alon 96, Tel Aviv 6789141, Israel
Related authors
Grey S. Nearing, Daniel Klotz, Jonathan M. Frame, Martin Gauch, Oren Gilon, Frederik Kratzert, Alden Keefe Sampson, Guy Shalev, and Sella Nevo
Hydrol. Earth Syst. Sci., 26, 5493–5513, https://doi.org/10.5194/hess-26-5493-2022, https://doi.org/10.5194/hess-26-5493-2022, 2022
Short summary
Short summary
When designing flood forecasting models, it is necessary to use all available data to achieve the most accurate predictions possible. This manuscript explores two basic ways of ingesting near-real-time streamflow data into machine learning streamflow models. The point we want to make is that when working in the context of machine learning (instead of traditional hydrology models that are based on
bio-geophysics), it is not necessary to use complex statistical methods for injecting sparse data.
Claudia Färber, Henning Plessow, Simon A. Mischel, Frederik Kratzert, Nans Addor, Guy Shalev, and Ulrich Looser
Earth Syst. Sci. Data, 17, 4613–4625, https://doi.org/10.5194/essd-17-4613-2025, https://doi.org/10.5194/essd-17-4613-2025, 2025
Short summary
Short summary
Large-sample datasets are essential in hydrological science to support modelling studies and advance process understanding. Caravan is a community initiative to create a large-sample hydrology dataset of meteorological forcing data, catchment attributes and discharge data for catchments around the world. This dataset is a subset of hydrological discharge data and station-based watersheds from the Global Runoff Data Centre (GRDC), which are covered by an open data policy.
Martin Gauch, Frederik Kratzert, Daniel Klotz, Grey Nearing, Deborah Cohen, and Oren Gilon
EGUsphere, https://doi.org/10.5194/egusphere-2025-1224, https://doi.org/10.5194/egusphere-2025-1224, 2025
Short summary
Short summary
Missing input data are one of the most common challenges when building deep learning hydrological models. We present and analyze different methods that can produce predictions when certain inputs are missing during training or inference. Our proposed strategies provide high accuracy while allowing for more flexible data handling and being robust to outages in operational scenarios.
Eduardo Acuña Espinoza, Frederik Kratzert, Daniel Klotz, Martin Gauch, Manuel Álvarez Chaves, Ralf Loritz, and Uwe Ehret
Hydrol. Earth Syst. Sci., 29, 1749–1758, https://doi.org/10.5194/hess-29-1749-2025, https://doi.org/10.5194/hess-29-1749-2025, 2025
Short summary
Short summary
Long short-term memory (LSTM) networks have demonstrated state-of-the-art performance for rainfall-runoff hydrological modelling. However, most studies focus on predictions at a daily scale, limiting the benefits of sub-daily (e.g. hourly) predictions in applications like flood forecasting. In this study, we introduce a new architecture, multi-frequency LSTM (MF-LSTM), designed to use inputs of various temporal frequencies to produce sub-daily (e.g. hourly) predictions at a moderate computational cost.
Eduardo Acuña Espinoza, Ralf Loritz, Frederik Kratzert, Daniel Klotz, Martin Gauch, Manuel Álvarez Chaves, and Uwe Ehret
Hydrol. Earth Syst. Sci., 29, 1277–1294, https://doi.org/10.5194/hess-29-1277-2025, https://doi.org/10.5194/hess-29-1277-2025, 2025
Short summary
Short summary
Data-driven techniques have shown the potential to outperform process-based models in rainfall–runoff simulations. Hybrid models, combining both approaches, aim to enhance accuracy and maintain interpretability. Expanding the set of test cases to evaluate hybrid models under different conditions, we test their generalization capabilities for extreme hydrological events.
Gab Abramowitz, Anna Ukkola, Sanaa Hobeichi, Jon Cranko Page, Mathew Lipson, Martin G. De Kauwe, Samuel Green, Claire Brenner, Jonathan Frame, Grey Nearing, Martyn Clark, Martin Best, Peter Anthoni, Gabriele Arduini, Souhail Boussetta, Silvia Caldararu, Kyeungwoo Cho, Matthias Cuntz, David Fairbairn, Craig R. Ferguson, Hyungjun Kim, Yeonjoo Kim, Jürgen Knauer, David Lawrence, Xiangzhong Luo, Sergey Malyshev, Tomoko Nitta, Jerome Ogee, Keith Oleson, Catherine Ottlé, Phillipe Peylin, Patricia de Rosnay, Heather Rumbold, Bob Su, Nicolas Vuichard, Anthony P. Walker, Xiaoni Wang-Faivre, Yunfei Wang, and Yijian Zeng
Biogeosciences, 21, 5517–5538, https://doi.org/10.5194/bg-21-5517-2024, https://doi.org/10.5194/bg-21-5517-2024, 2024
Short summary
Short summary
This paper evaluates land models – computer-based models that simulate ecosystem dynamics; land carbon, water, and energy cycles; and the role of land in the climate system. It uses machine learning and AI approaches to show that, despite the complexity of land models, they do not perform nearly as well as they could given the amount of information they are provided with about the prediction problem.
Frederik Kratzert, Martin Gauch, Daniel Klotz, and Grey Nearing
Hydrol. Earth Syst. Sci., 28, 4187–4201, https://doi.org/10.5194/hess-28-4187-2024, https://doi.org/10.5194/hess-28-4187-2024, 2024
Short summary
Short summary
Recently, a special type of neural-network architecture became increasingly popular in hydrology literature. However, in most applications, this model was applied as a one-to-one replacement for hydrology models without adapting or rethinking the experimental setup. In this opinion paper, we show how this is almost always a bad decision and how using these kinds of models requires the use of large-sample hydrology data sets.
Andreas Auer, Martin Gauch, Frederik Kratzert, Grey Nearing, Sepp Hochreiter, and Daniel Klotz
Hydrol. Earth Syst. Sci., 28, 4099–4126, https://doi.org/10.5194/hess-28-4099-2024, https://doi.org/10.5194/hess-28-4099-2024, 2024
Short summary
Short summary
This work examines the impact of temporal and spatial information on the uncertainty estimation of streamflow forecasts. The study emphasizes the importance of data updates and global information for precise uncertainty estimates. We use conformal prediction to show that recent data enhance the estimates, even if only available infrequently. Local data yield reasonable average estimations but fall short for peak-flow events. The use of global data significantly improves these predictions.
Daniel Klotz, Martin Gauch, Frederik Kratzert, Grey Nearing, and Jakob Zscheischler
Hydrol. Earth Syst. Sci., 28, 3665–3673, https://doi.org/10.5194/hess-28-3665-2024, https://doi.org/10.5194/hess-28-3665-2024, 2024
Short summary
Short summary
The evaluation of model performance is essential for hydrological modeling. Using performance criteria requires a deep understanding of their properties. We focus on a counterintuitive aspect of the Nash–Sutcliffe efficiency (NSE) and show that if we divide the data into multiple parts, the overall performance can be higher than all the evaluations of the subsets. Although this follows from the definition of the NSE, the resulting behavior can have unintended consequences in practice.
Talia Rosin, Francesco Marra, and Efrat Morin
Hydrol. Earth Syst. Sci., 28, 3549–3566, https://doi.org/10.5194/hess-28-3549-2024, https://doi.org/10.5194/hess-28-3549-2024, 2024
Short summary
Short summary
Knowledge of extreme precipitation probability at various spatial–temporal scales is crucial. We estimate extreme precipitation return levels at multiple scales (10 min–24 h, 0.25–500 km2) in the eastern Mediterranean using radar data. We show our estimates are comparable to those derived from averaged daily rain gauges. We then explore multi-scale extreme precipitation across coastal, mountainous, and desert regions.
Shai Abir, Hamish A. McGowan, Yonatan Shaked, Hezi Gildor, Efrat Morin, and Nadav G. Lensky
Atmos. Chem. Phys., 24, 6177–6195, https://doi.org/10.5194/acp-24-6177-2024, https://doi.org/10.5194/acp-24-6177-2024, 2024
Short summary
Short summary
Understanding air–sea heat exchange is vital for studying ocean dynamics. Eddy covariance measurements over the Gulf of Eilat revealed a 3.22 m yr-1 evaporation rate, which is inconsistent with bulk formulae estimations in stable atmospheric conditions, requiring bulk formulae to be revisited in these environments. The surface fluxes have a net cooling effect on the gulf water on an annual mean (-79 W m-2), balanced by a strong exchange flux between the Red Sea and the Gulf of Eilat.
Louise J. Slater, Louise Arnal, Marie-Amélie Boucher, Annie Y.-Y. Chang, Simon Moulds, Conor Murphy, Grey Nearing, Guy Shalev, Chaopeng Shen, Linda Speight, Gabriele Villarini, Robert L. Wilby, Andrew Wood, and Massimiliano Zappa
Hydrol. Earth Syst. Sci., 27, 1865–1889, https://doi.org/10.5194/hess-27-1865-2023, https://doi.org/10.5194/hess-27-1865-2023, 2023
Short summary
Short summary
Hybrid forecasting systems combine data-driven methods with physics-based weather and climate models to improve the accuracy of predictions for meteorological and hydroclimatic events such as rainfall, temperature, streamflow, floods, droughts, tropical cyclones, or atmospheric rivers. We review recent developments in hybrid forecasting and outline key challenges and opportunities in the field.
Grey S. Nearing, Daniel Klotz, Jonathan M. Frame, Martin Gauch, Oren Gilon, Frederik Kratzert, Alden Keefe Sampson, Guy Shalev, and Sella Nevo
Hydrol. Earth Syst. Sci., 26, 5493–5513, https://doi.org/10.5194/hess-26-5493-2022, https://doi.org/10.5194/hess-26-5493-2022, 2022
Short summary
Short summary
When designing flood forecasting models, it is necessary to use all available data to achieve the most accurate predictions possible. This manuscript explores two basic ways of ingesting near-real-time streamflow data into machine learning streamflow models. The point we want to make is that when working in the context of machine learning (instead of traditional hydrology models that are based on
bio-geophysics), it is not necessary to use complex statistical methods for injecting sparse data.
Juliane Mai, Hongren Shen, Bryan A. Tolson, Étienne Gaborit, Richard Arsenault, James R. Craig, Vincent Fortin, Lauren M. Fry, Martin Gauch, Daniel Klotz, Frederik Kratzert, Nicole O'Brien, Daniel G. Princz, Sinan Rasiya Koya, Tirthankar Roy, Frank Seglenieks, Narayan K. Shrestha, André G. T. Temgoua, Vincent Vionnet, and Jonathan W. Waddell
Hydrol. Earth Syst. Sci., 26, 3537–3572, https://doi.org/10.5194/hess-26-3537-2022, https://doi.org/10.5194/hess-26-3537-2022, 2022
Short summary
Short summary
Model intercomparison studies are carried out to test various models and compare the quality of their outputs over the same domain. In this study, 13 diverse model setups using the same input data are evaluated over the Great Lakes region. Various model outputs – such as streamflow, evaporation, soil moisture, and amount of snow on the ground – are compared using standardized methods and metrics. The basin-wise model outputs and observations are made available through an interactive website.
Jonathan M. Frame, Frederik Kratzert, Daniel Klotz, Martin Gauch, Guy Shalev, Oren Gilon, Logan M. Qualls, Hoshin V. Gupta, and Grey S. Nearing
Hydrol. Earth Syst. Sci., 26, 3377–3392, https://doi.org/10.5194/hess-26-3377-2022, https://doi.org/10.5194/hess-26-3377-2022, 2022
Short summary
Short summary
The most accurate rainfall–runoff predictions are currently based on deep learning. There is a concern among hydrologists that deep learning models may not be reliable in extrapolation or for predicting extreme events. This study tests that hypothesis. The deep learning models remained relatively accurate in predicting extreme events compared with traditional models, even when extreme events were not included in the training set.
Thomas Lees, Steven Reece, Frederik Kratzert, Daniel Klotz, Martin Gauch, Jens De Bruijn, Reetik Kumar Sahu, Peter Greve, Louise Slater, and Simon J. Dadson
Hydrol. Earth Syst. Sci., 26, 3079–3101, https://doi.org/10.5194/hess-26-3079-2022, https://doi.org/10.5194/hess-26-3079-2022, 2022
Short summary
Short summary
Despite the accuracy of deep learning rainfall-runoff models, we are currently uncertain of what these models have learned. In this study we explore the internals of one deep learning architecture and demonstrate that the model learns about intermediate hydrological stores of soil moisture and snow water, despite never having seen data about these processes during training. Therefore, we find evidence that the deep learning approach learns a physically realistic mapping from inputs to outputs.
Daniel Klotz, Frederik Kratzert, Martin Gauch, Alden Keefe Sampson, Johannes Brandstetter, Günter Klambauer, Sepp Hochreiter, and Grey Nearing
Hydrol. Earth Syst. Sci., 26, 1673–1693, https://doi.org/10.5194/hess-26-1673-2022, https://doi.org/10.5194/hess-26-1673-2022, 2022
Short summary
Short summary
This contribution evaluates distributional runoff predictions from deep-learning-based approaches. We propose a benchmarking setup and establish four strong baselines. The results show that accurate, precise, and reliable uncertainty estimation can be achieved with deep learning.
Francesco Marra, Moshe Armon, and Efrat Morin
Hydrol. Earth Syst. Sci., 26, 1439–1458, https://doi.org/10.5194/hess-26-1439-2022, https://doi.org/10.5194/hess-26-1439-2022, 2022
Short summary
Short summary
We present a new method for quantifying the probability of occurrence of extreme rainfall using radar data, and we use it to examine coastal and orographic effects on extremes. We identify three regimes, directly related to precipitation physical processes, which respond differently to these forcings. The methods and results are of interest for researchers and practitioners using radar for the analysis of extremes, risk managers, water resources managers, and climate change impact studies.
Yoav Ben Dor, Francesco Marra, Moshe Armon, Yehouda Enzel, Achim Brauer, Markus Julius Schwab, and Efrat Morin
Clim. Past, 17, 2653–2677, https://doi.org/10.5194/cp-17-2653-2021, https://doi.org/10.5194/cp-17-2653-2021, 2021
Short summary
Short summary
Laminated sediments from the deepest part of the Dead Sea unravel the hydrological response of the eastern Mediterranean to past climate changes. This study demonstrates the importance of geological archives in complementing modern hydrological measurements that do not fully capture natural hydroclimatic variability, which is crucial to configure for understanding the impact of climate change on the hydrological cycle in subtropical regions.
Frederik Kratzert, Daniel Klotz, Sepp Hochreiter, and Grey S. Nearing
Hydrol. Earth Syst. Sci., 25, 2685–2703, https://doi.org/10.5194/hess-25-2685-2021, https://doi.org/10.5194/hess-25-2685-2021, 2021
Short summary
Short summary
We investigate how deep learning models use different meteorological data sets in the task of (regional) rainfall–runoff modeling. We show that performance can be significantly improved when using different data products as input and further show how the model learns to combine those meteorological input differently across time and space. The results are carefully benchmarked against classical approaches, showing the supremacy of the presented approach.
Martin Gauch, Frederik Kratzert, Daniel Klotz, Grey Nearing, Jimmy Lin, and Sepp Hochreiter
Hydrol. Earth Syst. Sci., 25, 2045–2062, https://doi.org/10.5194/hess-25-2045-2021, https://doi.org/10.5194/hess-25-2045-2021, 2021
Short summary
Short summary
We present multi-timescale Short-Term Memory (MTS-LSTM), a machine learning approach that predicts discharge at multiple timescales within one model. MTS-LSTM is significantly more accurate than the US National Water Model and computationally more efficient than an individual LSTM model per timescale. Further, MTS-LSTM can process different input variables at different timescales, which is important as the lead time of meteorological forecasts often depends on their temporal resolution.
Yair Rinat, Francesco Marra, Moshe Armon, Asher Metzger, Yoav Levi, Pavel Khain, Elyakom Vadislavsky, Marcelo Rosensaft, and Efrat Morin
Nat. Hazards Earth Syst. Sci., 21, 917–939, https://doi.org/10.5194/nhess-21-917-2021, https://doi.org/10.5194/nhess-21-917-2021, 2021
Short summary
Short summary
Flash floods are among the most devastating and lethal natural hazards worldwide. The study of such events is important as flash floods are poorly understood and documented processes, especially in deserts. A small portion of the studied basin (1 %–20 %) experienced extreme rainfall intensities resulting in local flash floods of high magnitudes. Flash floods started and reached their peak within tens of minutes. Forecasts poorly predicted the flash floods mostly due to location inaccuracy.
Cited articles
Addor, N., Jaun, S., Fundel, F., and Zappa, M.: An operational hydrological ensemble prediction system for the city of Zurich (Switzerland): skill, case studies and scenarios, Hydrol. Earth Syst. Sci., 15, 2327–2347, https://doi.org/10.5194/hess-15-2327-2011, 2011.
Alfieri, L., Cohen, S., Galantowicz, J., Schumann, G. J., Trigg, M. A.,
Zsoter, E., Prudhomme, C., Kruczkiewicz, A., de Perez, E. C., Flamig, Z., and
Rudari, R.: A global network for operational flood risk reduction,
Environ. Sci. Policy, 84, 149–158, 2018.
Ben-Haim, Z., Anisimov, V., Yonas, A., Gulshan, V., Shafi, Y., Hoyer, S., and
Nevo, S.: Inundation modeling in data scarce regions. Neural Information
Processing Systems (NeurIPS), Artificial Intelligence for Humanitarian
Assistance and Disaster Response workshop, 30 October 2019, Vancouver, Canada, https://doi.org/10.48550/arXiv.1910.05006, 2019.
Beven, K.: Linking parameters across scales: subgrid parameterizations and
scale dependent hydrological models, Hydrol. Process., 9,
507–525, 1995.
Bhatt, C. M., Rao, G. S., Diwakar, P. G., and Dadhwal, V. K.: Development of flood inundation extent libraries over a range of potential flood levels: a
practical framework for quick flood response, Geomat. Nat. Haz. Risk, 8, 384–401, 2017.
Blöschl, G., Hall, J., Viglione, A., Perdigão, R. A., Parajka, J.,
Merz, B., Lun, D., Arheimer, B., Aronica, G. T., Bilibashi, A., and
Boháč, M.: Changing climate both increases and decreases European
river floods, Nature, 573, 108–111, 2019.
Borga, M., Anagnostou, E. N., Blöschl, G., and Creutin, J. D.: Flash flood forecasting, warning and risk management: the HYDRATE project, Environ. Sci. Policy, 14, 834–844, 2011.
Central Water Commission Official Flood Forecast:
@CWCOfficial_FF, post-date: 27 August 2021, https://twitter.com/CWCOfficial_FF/status/1431190935019294726 (access date: 11 November 2021), 2021.
Chang, L. C., Amin, M. Z. M., Yang, S. N., and Chang, F. J.: Building ANN-based regional multi-step-ahead flood inundation forecast models, Water, 10, 1283, https://doi.org/10.3390/w10091283, 2018.
Chu, H., Wu, W., Wang, Q. J., Nathan, R., and Wei, J.: An ANN-based emulation
modelling framework for flood inundation modelling: Application, challenges
and future directions, Environ. Model. Softw., 124, 104587, https://doi.org/10.1016/j.envsoft.2019.104587, 2020.
de Almeida, G. A., Bates, P., Freer, J. E., and Souvignet, M.: Improving the
stability of a simple formulation of the shallow water equations for 2-D
flood modeling, Water Resour. Res., 48, W05528, https://doi.org/10.1029/2011WR011570, 2012.
Devlin, J., Chang, M. W., Lee, K., and Toutanova, K.: BERT: Pre-training of
deep bidirectional transformers for language understanding, Proceedings of
the 2019 Conference of the North American Chapter of the Association for
Computational Linguistics, 2–7 June 2019, Minneapolis, MN, USA, 1, 4171–4186, https://doi.org/10.48550/arXiv.1810.04805 2019.
EM-DAT: https://www.emdat.be/, last access: 10 October 2021.
Emerton, R. E., Stephens, E. M., Pappenberger, F., Pagano, T. C., Weerts, A. H., Wood, A. W., Salamon, P., Brown, J. D., Hjerdt, N., Donnelly, C., and Baugh, C. A.: Continental and global scale flood forecasting systems, WIRES Water, 3, 391–418, 2016.
Feng, D., Fang, K., and Shen, C.: Enhancing streamflow forecast and extracting insights using long-short term memory networks with data integration at continental scales, Water Resour. Res., 56, e2019WR026793, https://doi.org/10.1029/2019WR026793, 2020.
Frame, J. M., Kratzert, F., Klotz, D., Gauch, M., Shelev, G., Gilon, O., Qualls, L. M., Gupta, H. V., and Nearing, G. S.: Deep learning rainfall–runoff predictions of extreme events, Hydrol. Earth Syst. Sci., 26, 3377–3392, https://doi.org/10.5194/hess-26-3377-2022, 2022.
Gauch, M., Kratzert, F., Klotz, D., Nearing, G., Lin, J., and Hochreiter, S.: Rainfall–runoff prediction at multiple timescales with a single Long Short-Term Memory network, Hydrol. Earth Syst. Sci., 25, 2045–2062, https://doi.org/10.5194/hess-25-2045-2021, 2021.
Georgakakos, K. P.: Overview of the Global Flash Flood Guidance System and Its Application Worldwide, WMO Bulletin, 67, 37–42, 2018.
Google-research flood_forecasting: Code excerpts from the flood forecasting inundation models, GitHub [code],
https://github.com/google-research/google-research/tree/master/flood_forecasting, last access: 19 March 2022.
Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D., and Moore, R. Google Earth Engine: Planetary-scale geospatial analysis for everyone, Remote Sens. Environ., 202, 18–27, 2017.
Hallegatte, S.: A cost effective solution to reduce disaster losses in
developing countries: hydro-meteorological services, early warning, and
evacuation, The World Bank, https://doi.org/10.1596/1813-9450-6058, 2012.
He, K., Zhang, X., Ren, S., and Sun, J.: Deep residual learning for image
recognition, Proc. IEEE Conf. on Computer Vision and Pattern Recognition
(CVPR), 27–30 June 2016, Las Vegas, NV, USA, 770–778, https://doi.org/10.1109/CVPR.2016.90, 2016.
Hrachowitz, M., Savenije, H. H. G., Blöschl, G., McDonnell, J. J.,
Sivapalan, M., Pomeroy, J. W., Arheimer, B., Blume, T., Clark, M. P., Ehret,
U., and Fenicia, F.: A decade of Predictions in Ungauged Basins (PUB) – a
review, Hydrolog. Sci. J., 58, 1198–1255, 2013.
Hsu, K. L., Gupta, H. V., and Sorooshian, S.: Artificial neural network modeling of the rainfall-runoff process, Water Resour. Res., 31,
2517–2530, 1995.
Hu, R., Fang, F., Pain, C. C., and Navon, I. M.: Rapid spatio-temporal flood
prediction and uncertainty quantification using a deep learning method,
J. Hydrol., 575, 911–920, 2019.
Huffman, G. J., Stocker, E. F., Bolvin, D. T., Nelkin, E. J., and Tan, J.: GPM IMERG Early Precipitation L3 Half Hourly 0.1 degree x 0.1 degree V06, Greenbelt, MD, Goddard Earth Sciences Data and Information Services Center (GES DISC) [data set], https://doi.org/10.5067/GPM/IMERG/3B-HH-E/06, 2019.
Jian, J., Ryu, D., Costelloe, J. F., and Su, C. H.: Towards hydrological model calibration using river level measurements, J. Hydrol.: Regional Studies, 10, 95–109, 2017.
Jonkman, S. N.: Global perspectives on loss of human life caused by floods,
Nat. Hazards, 34, 151–175, 2005.
Kabir, S., Patidar, S., Xia, X., Liang, Q., Neal, J., and Pender, G.: A deep
convolutional neural network model for rapid prediction of fluvial flood
inundation, J. Hydrol., 590, 125481, https://doi.org/10.1016/j.jhydrol.2020.125481, 2020.
Klotz, D., Kratzert, F., Gauch, M., Keefe Sampson, A., Brandstetter, J., Klambauer, G., Hochreiter, S., and Nearing, G.: Uncertainty estimation with deep learning for rainfall–runoff modeling, Hydrol. Earth Syst. Sci., 26, 1673–1693, https://doi.org/10.5194/hess-26-1673-2022, 2022.
Krajewski, W. F., Ceynar, D., Demir, I., Goska, R., Kruger, A., Langel, C.,
Mantilla, R., Niemeier, J., Quintero, F., Seo, B. C., and Small, S. J.:
Real-time flood forecasting and information system for the state of Iowa,
B. Am. Meteorol. Soc., 98, 539–554, 2017.
Kratzert, F., Klotz, D., Brenner, C., Schulz, K., and Herrnegger, M.: Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks, Hydrol. Earth Syst. Sci., 22, 6005–6022, https://doi.org/10.5194/hess-22-6005-2018, 2018.
Kratzert, F., Klotz, D., Herrnegger, M., Sampson, A. K., Hochreiter, S., and
Nearing, G. S.: Toward improved predictions in ungauged basins: Exploiting the power of machine learning. Water Resour. Res., 55, 11344–11354,
2019a.
Kratzert, F., Klotz, D., Shalev, G., Klambauer, G., Hochreiter, S., and Nearing, G.: Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets, Hydrol. Earth Syst. Sci., 23, 5089–5110, https://doi.org/10.5194/hess-23-5089-2019, 2019b.
Kuller, M., Schoenholzer, K., and Lienert, J.: Creating effective flood
warnings: A framework from a critical review, J. Hydrol., 602,
126708, https://doi.org/10.1016/j.jhydrol.2021.126708, 2021.
McFeeters, S. K.: Using the normalized difference water index (NDWI) within a
geographic information system to detect swimming pools for mosquito
abatement: a practical approach. Remote Sens., 5, 3544–3561, 2013.
McMillan, H. K. and Westerberg, I. K.: Rating curve estimation under epistemic uncertainty, Hydrol. Process., 29, 1873–1882, 2015.
Mosavi, A., Ozturk, P., and Chau, K. W.: Flood prediction using machine
learning models: Literature review, Water, 10, 1536, https://doi.org/10.3390/w10111536, 2018.
Moshe, Z., Metzger, A., Elidan, G., Kratzert, F., Nevo, S., and El-Yaniv, R.:
Hydronets: Leveraging river structure for hydrologic modeling, arXiv [preprint], arXiv:2007.00595, 1 July 2020.
Nearing, G. S., Kratzert, F., Sampson, A. K., Pelissier, C. S., Klotz, D.,
Frame, J. M., Prieto, C., and Gupta, H. V.: What role does hydrological science play in the age of machine learning?, Water Resour. Res., 57,
e2020WR028091, https://doi.org/https://doi.org/10.1029/2020WR028091, 2020.
Nevo, S., Elidan, G., Hassidim, A., Shalev, G., Gilon, O., Nearing, G., and
Matias, Y.: ML-based flood forecasting: Advances in scale, accuracy and
reach, NeurIPS Artificial Intelligence for Humanitarian Assistance and
Disaster Response Workshop, arXiv [preprint], arXiv:2012.00671, 12–13 December 2020, virtual conference, 2020.
Ocio, D., Le Vine, N., Westerberg, I., Pappenberger, F., and Buytaert, W.: The role of rating curve uncertainty in real-time flood forecasting, Water Resour. Res., 53, 4197–4213, 2017.
OpenCV findContours: [code], https://docs.opencv.org/3.4/d3/dc0/group__imgproc__shape.html#ga17ed9f5d79ae97bd4c7cf18403e1689a, last access: 29 September 2021.
Pagano, T. C., Wood, A. W., Ramos, M. H., Cloke, H. L., Pappenberger, F., Clark, M. P., Cranston, M., Kavetski, D., Mathevet, T., Sorooshian, S., and Verkade, J. S.: Challenges of operational river forecasting, J.
Hydrometeorol., 15, 1692–1707, 2014.
Perera, D., Agnihotri, J., Seidou, O., and Djalante, R.: Identifying societal
challenges in flood early warning systems, Int. J. Disast. Risk Re., 51, 101794, https://doi.org/10.1016/j.ijdrr.2020.101794, 2020.
Rotach, M. W., Ambrosetti, P., Ament, F., Appenzeller, C., Arpagaus, M.,
Bauer, H. S., Behrendt, A., Bouttier, F., Buzzi, A., Corazza, M., and Davolio, S.: MAP D-PHASE: Real-time demonstration of weather forecast quality in the Alpine region, B. Am. Meteorol. Soc., 90, 1321–1336, 2009.
Schumann, G. J. P. and Moller, D. K.: Microwave remote sensing of flood
inundation, Phys. Chem. Earth A/B/C, 83, 84–95, 2015.
Shrestha, M. S., Grabs, W. E., and Khadgi, V. R.: Establishment of a regional
flood information system in the Hindu Kush Himalayas: challenges and
opportunities, Int. J. Water Resour. D., 31, 238–252, 2015.
Sivapalan, M., Takeuchi, K., Franks, S. W., Gupta, V. K., Karambiri, H.,
Lakshmi, V., Liang, X., McDonnell, J. J., Mendiondo, E. M., O'connell, P. E., and Oki, T.: IAHS Decade on Predictions in Ungauged Basins (PUB), 2003–2012:
Shaping an exciting future for the hydrological sciences, Hydrolog.
Sci. J., 48, 857–880, 2003.
Sokolova, M., Japkowicz, N., and Szpakowicz, S.: Beyond accuracy, F-score and
ROC: a family of discriminant measures for performance evaluation, in:
Australasian joint conference on artificial intelligence,
4–8 December 2006, Hobart, TAS, Australia, Springer, Berlin, Heidelberg, 1015–1021, https://doi.org/10.1007/11941439_114, 2006.
Teng, J., Jakeman, A. J., Vaze, J., Croke, B. F., Dutta, D., and Kim, S.: Flood inundation modelling: A review of methods, recent advances and uncertainty analysis, Environ. Model. Softw., 90, 201–216, 2017.
Tiwari, M. K. and Chatterjee, C.: Development of an accurate and reliable
hourly flood forecasting model using wavelet–bootstrap–ANN (WBANN) hybrid
approach, J. Hydrol., 394, 458–470, 2010.
Torres, R., Snoeij, P., Geudtner, D., Bibby, D., Davidson, M., Attema, E.,
Potin, P., Rommen, B., Floury, N., Brown, M., Traver, I. N., Deghaye, P.,
Duesmann, B., Rosich, B., Miranda, N., Bruno, C., L'Abbate, M., Croci, R.,
Pietropaolo, A., Huchler, M., and Rostan, F.: GMES Sentinel-1 mission, Remote
Sens. Environ., 120, 9–24, https://doi.org/10.1016/j.rse.2011.05.028, 2012.
United States Nations Office for Disaster Risk Reduction (UNISDR), Centre for Research of the Epidemiology of Disaster (CRED), The human cost of natural disasters: A global perspective, http://repo.floodalliance.net/jspui/handle/44111/1165 (last access: 30 July 2022), 2015.
Welles, E. and Sorooshian, S.: Scientific verification of deterministic river
stage forecasts, J. Hydrometeorol., 10, 507–520, 2009.
Werner, M., Cranston, M., Harrison, T., Whitfield, D., and Schellekens, J.:
Recent developments in operational flood forecasting in England, Wales and
Scotland, Meteorol. Appl., 16, 13–22, 2009.
World Bank: Proceedings of the regional flood early warning system workshop
(English), 23–27 November 2015, Bangkok, Thailand, World Bank Group, Washington, D.C., USA, http://documents.worldbank.org/curated/en/431281468000591916/Proceedings-of-the-regional-flood-early-warning-system-workshop (last access: 30 July 2022), 2015.
World Meteorological Association: The global climate 2001–2010: A decade of
climate extremes, summary report, WMO, Geneva, Switzerland, 16 pp., ISBN 978-92-63-11119-7, 2013.
Xiang, Z. and Demir, I.: Distributed long-term hourly streamflow predictions
using deep learning–A case study for State of Iowa, Environ. Model. Softw., 131, 104761, https://doi.org/10.1016/j.envsoft.2020.104761, 2020.
Xiang, Z., Yan, J., and Demir, I.: A rainfall-runoff model with LSTM-based
sequence-to-sequence learning, Water Resour. Res., 56, e2019WR025326, https://doi.org/10.1029/2019WR025326, 2020.
Zalenski, G., Krajewski, W. F., Quintero, F., Restrepo, P., and Buan, S.:
Analysis of national weather service stage forecast errors, Weather Forecast., 32, 1441–1465, 2017.
Zappa, M., Rotach, M. W., Arpagaus, M., Dorninger, M., Hegg, C., Montani, A.,
Ranzi, R., Ament, F., Germann, U., Grossi, G., and Jaun, S.: MAP D-PHASE:
real-time demonstration of hydrological ensemble prediction systems,
Atmos. Sci. Lett., 9, 80–87, 2008.
Short summary
Early flood warnings are one of the most effective tools to save lives and goods. Machine learning (ML) models can improve flood prediction accuracy but their use in operational frameworks is limited. The paper presents a flood warning system, operational in India and Bangladesh, that uses ML models for forecasting river stage and flood inundation maps and discusses the models' performances. In 2021, more than 100 million flood alerts were sent to people near rivers over an area of 470 000 km2.
Early flood warnings are one of the most effective tools to save lives and goods. Machine...
