Preprints
https://doi.org/10.5194/hess-2021-554
https://doi.org/10.5194/hess-2021-554

  12 Nov 2021

12 Nov 2021

Review status: this preprint is currently under review for the journal HESS.

Flood forecasting with machine learning models in an operational framework

Sella Nevo1, Efrat Morin2, Adi Gerzi Rosenthal1, Asher Metzger1, Chen Barshai1, Dana Weitzner1, Dafi Voloshin1, Frederik Kratzert1, Gal Elidan1,2, Gideon Dror1, Gregory Begelman1, Grey Nearing1, Guy Shalev1, Hila Noga1, Ira Shavitt1, Liora Yuklea1, Moriah Royz1, Niv Giladi1, Nofar Peled Levi1, Ofir Reich1, Oren Gilon1, Ronnie Maor1, Shahar Timnat1, Tal Shechter1, Vladimir Anisimov1, Yotam Gigi1, Yuval Levin1, Zach Moshe1, Zvika Ben-Haim1, Avinatan Hassidim1, and Yossi Matias1 Sella Nevo et al.
  • 1Google Research, Yigal Alon 96, Tel-Aviv 6789141, Israel
  • 2Hebrew University of Jerusalem, Safra Campus, Jerusalem 91904, Israel

Abstract. Google’s operational flood forecasting system was developed to provide accurate real-time flood warnings to agencies and the public, with a focus on riverine floods in large, gauged rivers. It became operational in 2018 and has since expanded geographically. This forecasting system consists of four subsystems: data validation, stage forecasting, inundation modeling, and alert distribution. Machine learning is used for two of the subsystems. Stage forecasting is modeled with the Long Short-Term Memory (LSTM) networks and the Linear models. Flood inundation is computed with the Thresholding and the Manifold models, where the former computes inundation extent and the latter computes both inundation extent and depth. The Manifold model, presented here for the first time, provides a machine-learning alternative to hydraulic modeling of flood inundation. When evaluated on historical data, all models achieve sufficiently high-performance metrics for operational use. The LSTM showed higher skills than the Linear model, while the Thresholding and Manifold models achieved similar performance metrics for modeling inundation extent. During the 2021 monsoon season, the flood warning system was operational in India and Bangladesh, covering flood-prone regions around rivers with a total area of 287,000 km2, home to more than 350M people. More than 100M flood alerts were sent to affected populations, to relevant authorities, and to emergency organizations. Current and future work on the system includes extending coverage to additional flood-prone locations, as well as improving modeling capabilities and accuracy.

Sella Nevo et al.

Status: open (until 07 Jan 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Sella Nevo et al.

Viewed

Total article views: 611 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
468 139 4 611 21 0 2
  • HTML: 468
  • PDF: 139
  • XML: 4
  • Total: 611
  • Supplement: 21
  • BibTeX: 0
  • EndNote: 2
Views and downloads (calculated since 12 Nov 2021)
Cumulative views and downloads (calculated since 12 Nov 2021)

Viewed (geographical distribution)

Total article views: 601 (including HTML, PDF, and XML) Thereof 601 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 01 Dec 2021
Download
Short summary
Early flood warnings are one of the most effective tools to save lives and goods. Machine learning 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 machine learning models for forecasting river stage and flood inundation maps, and discusses the models’ performances. In 2021 more than 100M flood alerts were sent to people near rivers over an area of 287,000 km2.