On the opening day of Google I/O 2019, the American-tech giant officially announced that its Artificial Intelligence (AI) driven flood-prediction system will be rolled out in India before Monsoons. The company has been working on the forecasting service since September 2018. Google also mentioned that the algorithm of the flood forecasting service can predict floods that are expected to break out and alert people nearby. It was at the IO 2019 event, where the California-based company confirmed that it will be expanding to new areas in the country before Monsoons hit the Indian soil. Google Assistant Now Gets New Voice-enabled Driving Mode Feature For Android Phones.
The company has also claimed that its flood-prediction tools are becoming more accurate with each day as more data is being collected for precise forecasting. As per Google, its AI forecasting tool is capable of predicting floods with 75 percent precision. This AI flood prediction service from Google is a part of a new program which is referred as AI for Social Good.
For collecting vital data for machine learning, Google has collaborated with Central Water Commission so that it can roll out testing for early flood warnings. Having said that Google has been testing this tool in Patna region since September 2018, the first warning was released by early September post heavy rains. The company is believed to be employing several elements in the machine learning models for predicting floods. This includes data from historical events, river level readings, terrain and elevation of a specific area and more. Google Pixel 3a, Pixel 3a XL Affordable Premium Smartphones Launched in India at Rs 39,999 & Rs 44,999; Online Sale Via Flipkart on May 15.
Yossi Matias, VP, Engineering at Google stated that, "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". Matias further continued, "From there, we generate maps and run up to hundreds of thousands of simulations in each location. With this information, we’ve 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".