Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Prediction

1 code implementation • 30 Apr 2024 • Jared D. Willard, Peter Harrington, Shashank Subramanian, Ankur Mahesh, Travis A. O'Brien, William D. Collins

The rapid rise of deep learning (DL) in numerical weather prediction (NWP) has led to a proliferation of models which forecast atmospheric variables with comparable or superior skill than traditional physics-based NWP.

A Practical Probabilistic Benchmark for AI Weather Models

no code implementations • 27 Jan 2024 • Noah D. Brenowitz, Yair Cohen, Jaideep Pathak, Ankur Mahesh, Boris Bonev, Thorsten Kurth, Dale R. Durran, Peter Harrington, Michael S. Pritchard

We also reveal how multiple time-step loss functions, which many data-driven weather models have employed, are counter-productive: they improve deterministic metrics at the cost of increased dissipation, deteriorating probabilistic skill.

Weather Forecasting

Exascale Deep Learning for Climate Analytics

3 code implementations • 3 Oct 2018 • Thorsten Kurth, Sean Treichler, Joshua Romero, Mayur Mudigonda, Nathan Luehr, Everett Phillips, Ankur Mahesh, Michael Matheson, Jack Deslippe, Massimiliano Fatica, Prabhat, Michael Houston

The Tiramisu network scales to 5300 P100 GPUs with a sustained throughput of 21. 0 PF/s and parallel efficiency of 79. 0%.

Distributed, Parallel, and Cluster Computing