A new approach to predicting the weather is beginning to take shape as artificial intelligence moves deeper into climate science. Nvidia has introduced a set of open-source AI models aimed at making weather forecasting faster, more affordable, and more precise.
The announcement was made on January 26 at the American Meteorological Society’s annual meeting in Houston. Known as the Earth-2 family, the models are designed to reduce reliance on traditional supercomputer-based simulations and replace them with faster AI-driven systems.
For decades, weather forecasting has depended on large supercomputers running complex physics equations. While effective, this method is costly, slow, and often out of reach for many countries. Nvidia said its new AI toolkit offers a practical alternative.
The Earth-2 models use graphics processing units to speed up the entire forecasting process. According to Nvidia, this shift can cut computing time from hours to just seconds, while also lowering overall costs.
The release includes multiple specialised tools. Earth-2 Medium Range is built on Nvidia’s new Atlas architecture and delivers 15-day global forecasts across 70 variables, including wind, temperature, and humidity.
For short-term and high-risk events, Earth-2 Nowcasting uses generative AI to predict local storm activity at kilometre-scale resolution within a 6-hour timeframe. This capability is especially important for emergency services and insurance providers that depend on fast, accurate data during extreme weather conditions.
Mike Pritchard, Nvidia’s director of climate simulation research and a professor of earth system sciences at the University of California, Irvine, highlighted the performance gains. Once trained, the AI models are “1,000 times faster” than traditional forecasting methods. This speed allows organisations to run thousands of simulations at once, helping them detect rare and high-impact weather risks that were previously too expensive to analyse.
Nvidia has released the models as open-source through GitHub and Hugging Face. This supports what the company calls “sovereign” forecasting, where countries can run and manage climate models on their own local hardware.
Early users, including the Israel Meteorological Service and several energy companies, have reported computing cost reductions of up to 90 percent.
Also read: Viksit Workforce for a Viksit Bharat
Do Follow: The Mainstream formerly known as CIO News LinkedIn Account | The Mainstream formerly known as CIO News Facebook | The Mainstream formerly known as CIO News Youtube | The Mainstream formerly known as CIO News Twitter
About us:
The Mainstream is a premier platform delivering the latest updates and informed perspectives across the technology business and cyber landscape. Built on research-driven, thought leadership and original intellectual property, The Mainstream also curates summits & conferences that convene decision makers to explore how technology reshapes industries and leadership. With a growing presence in India and globally across the Middle East, Africa, ASEAN, the USA, the UK and Australia, The Mainstream carries a vision to bring the latest happenings and insights to 8.2 billion people and to place technology at the centre of conversation for leaders navigating the future.
