The US National Oceanic and Atmospheric Administration (NOAA) has selected Google Cloud as its primary high-performance computing provider for the Weather and Climate Operational Supercomputing System (WCOSS).

The move is part of a wider shift as NOAA moves from traditional on-premises infrastructure to a cloud-first approach.

Google Cloud's H4D VMs with fifth-generation AMD Epyc processors will serve as the primary computing backbone for NOAA, acting as a cloud-based supercomputer.

Google and NOAA have a long-standing relationship, having previously worked together to share environmental data, track wildfires in real time, and work on marine conservation efforts.

NOAA also previously used Google DeepMind and the cloud company's WeatherNext model to predict the landfall of Hurricane Melissa, five days before it actually arrived.

WCOSS includes the supercomputing, storage resources, WAN, and developmental computing used by NOAA to run daily weather, ocean, and climate forecast models.

Previously, this was typically done using on-prem HPC systems, which were regularly upgraded.

“Cloud-based high-performance computing will accelerate the transition of research into operations by eliminating traditional bottlenecks of on-premise systems,” said NOAA administrator Neil Jacobs, Ph.D. “Not only will this new approach provide access to the latest chips, it will advance weather forecasting by aligning operational and research compute and provide capabilities for elastic on-demand model development.”

“We are charting a course to global leadership in cloud-based numerical weather prediction,” added Ken Graham, director, NOAA’s National Weather Service. “This is a significant achievement for NOAA; one that will ensure our critical modeling operations can seamlessly adapt to emerging science, and strengthen our mission to protect life and property.”

NOAA completed an upgrade of its Weather and Climate Operational Supercomputing System (WCOSS) in the summer of 2023, giving it twin supercomputers each with 14.5 petaflops of computing capacity, an increase of 20 percent compared to the previous solution.

In September 2024, NOAA announced a $100 million grant from the Bipartisan Infrastructure Law and Inflation Reduction Act to acquire the supercomputer dubbed Rhea. Including GPUs, Rhea was designed to “strengthen NOAA’s exploration and application of artificial intelligence and machine learning capabilities.”

The organization, in March 2026, revealed it had awarded two contracts for its National Weather Service to move its data and applications services to the cloud as part of a modernization initiative.

NOAA is not the first global meteorology service to move to the cloud.

The UK's Met Office signed an agreement with Microsoft in 2021 under which the two partnered on a supercomputer. The HPC system is not “based in the public cloud,” but is housed in a dedicated supercomputing facility within a Microsoft cloud data center in the UK. The Met Office officially adopted the Microsoft supercomputer in May 2025.

“Microsoft is hosting the multiple supercomputers underlying this service in dedicated halls within Microsoft data centers that have been designed and optimized for these supercomputers, rather than generic cloud hosting,” Microsoft told DCD in 2022.

“This includes power, cooling, and networking configurations tuned to the needs of the program, including energy efficiency and operational resilience. Thus, the supercomputers are hosted within a ‘dedicated’ Microsoft supercomputing facility for this project.”

The solution holds its own storage capabilities, but can also leverage offerings available from Microsoft cloud.