NOAA exploring artificial intelligence pilots with Google Cloud

While specific pilots haven't been announced, the series will be designed to give agency employees hands-on training with emerging tech.

The National Oceanic and Atmospheric Administration plans to improve weather forecasting by more effectively using satellite and environmental data in a series of pilots with Google Cloud.

Google entered into a three-year other transaction authority (OTA) agreement with the National Environmental Satellite, Data, and Information Service (NESDIS) to explore machine learning and artificial intelligence applications for not only weather but environmental monitoring, climate research and technical innovation, it announced Tuesday.

Together NESDIS and Google will develop small-scale ML and AI systems and use results from those pilots to build full-scale prototypes for operationalization across NOAA.

“Strengthening NOAA’s data processing through the use of big data, artificial intelligence, machine learning, and other advanced analytical approaches is critical for maintaining and enhancing the performance of our systems in support of public safety and the economy,” said Neil Jacobs, acting NOAA administrator, in the announcement. “I am excited to utilize new authorities granted to NOAA to pursue cutting-edge technologies that will enhance our mission and better protect lives and property.”


Like most agencies, NOAA has experienced an uptick in the volume of its datasets, in this case geared toward the environment. ML and AI systems could help better predict extreme weather events like tornadoes and hurricanes.

The number of pilots is to be determined, but they’ll offer NOAA employees hands-on training to improve ML and AI skills.  NOAA released an AI strategy in February that emphasized applying the emerging technology to its mission priorities.

Google engineers and data scientists have already explored weather prediction including hyperlocal precipitation forecasting, flood forecasting in India and Bangladesh, and related computational methods.

Latest Podcasts