For over two decades, Google Search has been a key provider of information to people, especially in times of crisis where actionable information is crucial. Over the years, Google has evolved its systems to provide more accurate information so that people and authorities can better prepare themselves to be safe when disasters strike. Google has now announced that it is using Artificial Intelligence (AI)-powered systems to forecast floods more accurately. The company has commenced its flood forecasting efforts with India, where 20 percent of global flood-related incidents are said to occur.
“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,” Yossi Matias, Vice President, Engineering, statesin a blog post.
Flood alert shown to users in the Patna region.
Matias adds that Google is partnering with India's Central Water Commission to get the data required for rolling out early flood warnings, starting with the Patna region. According to the company, the first alert went out earlier this month after heavy rains in the region.
“To help improve awareness of impending floods, we're 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,” the executive noted. The company uses a variety of elements like data from historical events and river level readings, to the terrain and elevation of a specific area. This data is then fed into its AI models that generates maps and runs up to thousands of simulations in each location. With this information, Google's AI was able to create river flood forecasting models that are said to more accurately predict when and where a flood might occur, along with the severity of the event.
These images depict a flood simulation of a river in Hyderabad, India. The left side uses publicly available data while the right side uses Google data and technology. Google's models contain higher resolution, accuracy, and up-to-date information. (Courtesy: Google)
“We’re also looking to expand coverage to more countries, to help more people around the world get access to these early warnings, and help keep them informed and safe,” Matias notes. Last year, Google launched SOS Alerts on Search and Maps to make emergency information more accessible. It claims that since then, it 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.