Google started using AI to predict floods in India back in 2018, and that program further expanded to Bangladesh in 2020. According to Google, it will now offer flood forecasts for river basins in another 18 countries. Those are Brazil, Colombia, Sri Lanka, Burkina Faso, Cameroon, Malawi, Guinea, Ghana, Ivory Coast, Chad, Democratic Republic of Congo, South Sudan, Namibia, Liberia, Nigeria, Sierra Leone, Angola and South Africa. The alerts go out to every Android phone user or any phone with the installed Google search app. Though, users will need to have an active internet connection and Google location services enabled on their phones to receive alerts. Google is also debuting a new tool called Flood Hub, which will be available worldwide. Flood Hub will display flood forecasts on a map and will show where they might occur. Further, Google announced it is expanding support for wildfire tracking tools in Search and Maps. First introduced in the US, the improved tracking is now available in the US, Mexico, Canada, and parts of Australia.
What is the need for AI-Powered flood and wildfire tracking?
As per a UN report, nearly half of our planet lacks adequate early warning systems for disasters like floods and wildfires. With climate change on the rise, disasters like floods and wildfires have become a regular sight. Flood damage affects 250 million people every year. Therefore, there has to be a system that can predict these life-threatening events and give early warning to residents. This is where Google comes into the picture, with its powerful AI and vast amounts of data. Google hopes its services can fill in some gaps, by providing early warnings to users on their phones. “This expansion in geographic coverage is possible thanks to our recent breakthroughs in AI-based flood forecasting models, and we’re committed to expanding to more countries,” Yossi Matias, Google vice president of engineering and crisis response lead, wrote in a blog post.
How does Google’s AI predict floods and wildfires?
Google relied on water level gauges to predict floods. But in many under-developed countries, the amount of data Google required to predict floods accurately wasn’t available. Therefore, Google switched its model, weather forecast data is now the key driver behind the AI model. This update will allow Google to issue flood warnings up to a week in advance, senior staff engineering manager Sella Nevo told The Verge. As for wildfires, Google uses data from the National Oceanic and Atmospheric Administration (NOAA) and NASA satellites. Google now uses machine learning with satellite imagery to improve wildfire detection and monitoring. This information is used to alert the public and also to assist with firefighting efforts.
