Nvidia announced three new AI weather tools today. Together, they promise to improve the accuracy of weather forecasts while also making them accessible to more users.

TechCrunch (TC) is a leading technology news and media site that covers the latest trends, startups, and innovations in the tech industry. With breaking news,  analysis, and expert commentary, TechCrunch provides  insights into the world of technology and entrepreneurship. Developers can learn about emerging technologies, funding opportunities, and market trends by following TechCrunch's coverage of the tech industry.

TechCrunch

Nvidia announced three new AI weather forecasting models called Earth-2 that promise faster and more accurate predictions. The Medium Range model reportedly outperforms Google DeepMind's GenCast on over 70 variables for 15-day forecasts. The suite includes Nowcasting for short-term predictions (0-6 hours), Global Data Assimilation for creating weather snapshots in minutes instead of hours, and uses transformer architectures. These GPU-based models aim to democratize weather forecasting by reducing computational costs, making advanced forecasting accessible to smaller countries and organizations that previously couldn't afford supercomputer time.

Nvidia’s new AI weather models probably saw this storm coming weeks ago