Floods are the most common natural disaster and cause approximately $50 billion in annual financial damages worldwide. The rate of flood-related disasters has more than doubled since 2000, partly due to climate change. Nearly 1.5 billion people, or 19% of the world’s population, face significant risks from severe flood events. Enhancing early warning systems to provide accurate and timely information to these populations can save thousands of lives annually.
Motivated by the impact of reliable flood forecasting on people globally, we initiated our flood forecasting effort in 2017. Throughout this multi-year journey, we advanced research while developing a real-time operational flood forecasting system that provides alerts on Google Search, Maps, Android notifications, and through the Flood Hub. To scale globally, especially in areas lacking accurate local data, further research advances were necessary.
In “Global prediction of extreme floods in ungauged watersheds,” published in Nature, we demonstrate how machine learning (ML) technologies can significantly enhance global-scale flood forecasting compared to the current state-of-the-art in countries with scarce flood-related data. These AI-based technologies extended the reliability of currently-available global nowcasts from zero to five days on average and improved forecasts across regions in Africa and Asia to levels similar to those in Europe. The model evaluations were conducted in collaboration with the European Center for Medium Range Weather Forecasting (ECMWF).
These technologies also enable Flood Hub to provide real-time river forecasts up to seven days in advance, covering river reaches across over 80 countries. This information can be used by individuals, communities, governments, and international organizations to take anticipatory action to help protect vulnerable populations.
