Abstract
NVIDIA Earth 2 creates open source software and open science to help developers apply AI to understanding weather and climate. These open technologies — including pretrained models, frameworks, customization recipes and inference libraries — accelerate all forecasting stages, from processing initial observation data to generating 15-day global forecasts or local storm forecasts. Historically, weather forecasting has relied on powerful supercomputers running physics-based models. AI-powered weather forecasting saves significant computational time and costs, allowing more nations, weather enterprises and businesses to run application-specific forecasting systems. Making production-ready weather AI fully accessible for organizations to run, fine-tune and deploy on their own infrastructure, NVIDIA Earth-2 is the first open, accelerated set of models and tools that enables developers to bring disparate weather and climate AI capabilities together. It’s pioneering work to speed weather prediction, enhance forecasting accuracy, foster collaboration and advance scientists’ overall understanding of the planet’s atmospheric conditions. Developers will gain an understanding of how to setup various types of weather forecast using OSS, with further information available in Developers will gain an understanding of how AI is changing weather forecasting and how they can set up an AI forecast using OSS. They can dive deeper through NVIDIA training courses, cookbooks, and blog posts.
Speaker Bio
Niall Robinson
Niall Robinson is the Product Lead for NVIDIA Earth 2, where he makes tools which empower others to apply AI to weather and climate. He started his career as a climate scientist, before spending a decade hacking in the Informatics Lab at the UK Meteorological Office. He joined NVIDIA in 2025.