ML-based Flood Forecasting: Advances in Scale, Accuracy and Reach

2020/11/29 by Sella Nevo, Nevo, Sella, Gal Elidan +11
Computer Science · Earth and Planetary Sciences · Environmental Science · Physics and Astronomy · #Flood Risk Assessment and Management #Hydrological Forecasting Using AI #Meteorological Phenomena and Simulations #cs.LG #physics.ao-ph

paper · pdf · doi:10.48550/arxiv.2012.00671

Submitted/accepted to NeurIPS HADR workshop: https://www.hadr.ai/home

arxiv created 2020/12/06 · arxiv updated 2020/12/08

Abstract

Floods are among the most common and deadly natural disasters in the world, and flood warning systems have been shown to be effective in reducing harm. Yet the majority of the world's vulnerable population does not have access to reliable and actionable warning systems, due to core challenges in scalability, computational costs, and data availability. In this paper we present two components of flood forecasting systems which were developed over the past year, providing access to these critical systems to 75 million people who didn't have this access before.

Related

• AI Increases Global Access to Reliable Flood Forecasts
• Flood forecasting with machine learning models in an operational framework
• ML for Flood Forecasting at Scale
• Fine Flood Forecasts: Incorporating local data into global models through fine-tuning
• Global Flood Prediction: a Multimodal Machine Learning Approach