Grey Nearing is a Senior Research Scientist at Google. He holds a PhD in Hydrology from the University of Arizona and has worked on large-scale hydrological modeling teams at NASA, the National Center for Atmospheric Research, and NOAA. Before joining Google he was a professor at the University of California Davis and the University of Alabama.
AI/ML for Flood Forecasting
Abstract: Flooding is one of the most common and costly types of natural disaster, with disproportionate human impacts in developing communities. One of the main challenges in providing accurate and actionable flood warnings is the problem of out-of-sample prediction -- this is a named problem in the hydrological sciences called "Prediction in Ungauged Basins." We've developed AI/ML approaches that significantly reduce this problem. Building on that, Google Research has developed an operational global flood forecast and flood alerting system that currently covers more than 1B people worldwide. This talk will cover the background and science behind the technical developments that support the Google FloodHub (g.co/floodhub), as well as our experience operationalizing AI/ML technology for global-scale adoption including partnership efforts with national and international governments agencies, NGOs, and individual communities through information channels like Google Maps, Search, and Android Alerts.
