Forecasting floods, now a reality (all thanks to Google’s AI)

Fri, 2019-01-04 13:10 -- SCC India Staff


Floods are devastating natural disasters worldwide – it is estimated that every year, 250 million people around the world are affected by floods, also costing billions of dollars in damages. Flood forecasting can help individuals and authorities better prepare to keep people safe, but accurate forecasting isn’t currently available in many areas. And the warning systems that do exist can be imprecise and non-actionable, resulting in far too many people being underprepared and under- informed before a flood happens.

To help improve awareness of impending floods, Google is using AI and significant computational power to create better forecasting models that predict when and where floods will occur and incorporating that information into Google Public Alerts. A variety of elements—from historical events to river level readings, to the terrain and elevation of a specific area—feed into our models.

From there, it generates maps and runs up to hundreds of thousands of simulations in each location. With this information, Google has created river flood forecasting models that can more accurately predict not only when and where a flood might occur, but the severity of the event as well.

In India, Google’s presence is blessing in disguise. The company recently started these flood forecasting efforts in India, where 20 per cent of global flood-related fatalities occurs. Here, Google is has partnered with India’s Central Water Commission to get the data to roll out early flood warnings, in the Patna region. The first alert went out in September as part of the pilot project in eastern India.

Taking this pilot project forward, the California-based company is now expanding it ahead of the monsoon season to cover many more parts of the country. In the pilot, implemented in partnership with the Central Water Commission in India, Google showed, via Public Alerts, a map that included areas designated as ‘high risk’ ‘medium risk’ and ‘low risk’. The pilot used an operational hydro-dynamic model, with the explicit goal of preparing the ground for integrating Machine Learning (ML) models into the process. Alerts were then sent out to individuals in the catchment area in the form of maps and Android notifications.

For 20 years, Google Search has provided people with the information they need, and in times of crisis, access to timely, actionable information is often crucial. Last year Google launched SOS Alerts on Search and Maps to make emergency information more accessible. Since then, the company has activated SOS alerts in more than 200 crisis situations, in addition to tens of thousands of Google Public Alerts, which have been viewed more than 1.5 billion times.