At NSF Unidata, we have successfully implemented and re-used weights from several global AI-NWP (Artificial Intelligence-Numerical Weather Prediction) models (FourCastNet, Pangu) using the NVIDIA earth2mip package. We can confirm that these models are open source and can be reused on high-end, but increasingly standard, HPC hardware. While traditional numerical weather prediction requires massive supercomputing resources, these AI models can potentially deliver similar or better results using standard GPU hardware for inference.

Announcing a new eLearning series available now on Unidata eLearning: Supervised Machine Learning Readiness. This learning series is a self-paced, beginner-friendly program designed for Earth systems scientists to explore the core principles of supervised machine learning. This series uses a combination of step-by-step frameworks, exploratory widgets, and low-code exercises in Jupyter Notebooks, to explore the full cycle of machine learning model development. No programming experience is required. By the end of the series, you will be able to recognize when machine learning is an appropriate tool and critically evaluate machine learning in Earth systems science contexts.