Google on Wednesday shared an update on its Flood Forecasting Initiative in India. The company said its systems now extend to the whole of India. It added that Google systems can now help protect more than 200 million people across more than 250,000 square kilometres, which is more than 20 times to the area it covered last year. So far, Google has sent about 30 million notifications to people in flood-hit areas.
Apart from expanding its coverage in India, Google has partnered with the Bangladesh Water Development Board to bring its alerts systems to Bangladesh. The company said it covers more than 40 million people in Bangladesh. Google plans to expand the coverage of its Flood Forecasting Initiative to the whole country in the future.
Google further said that it introduced a new forecasting model this year. The technology helped the company to double the lead time for many of its alerts. Google also helped alert governments and give people in the country an extra day or so to prepare for the flooding.
Google’s flood forecasting system now also provides more insights such as flood depth, timing and volume of water rise, and a more accurate depth maps of flood-hit areas.
Another improvement the company has made is overhauling the alerts to help users make the most of the information. Google’s flood warning system is now available in Hindi, Bengali, and seven other local languages in order to make the alerts more localised and accurate. It now also allows users to easily change language or location to help their friends and families.
“Of course, for all the progress we’ve made with alert technology, there are still a lot of challenges to overcome. With the flood season still in full swing in India and Bangladesh, COVID-19 has delayed critical infrastructure work, added to the immense pressure on first responders and medical authorities, and disrupted the in-person networks that many people still rely on for advance notice when a flood is on the way,” wrote Yossi Matias, VP Engineering & Crisis Response Lead, in a blog post.
