NERSC/sc25-dl-tutorial

Deep Learning at Scale @ SC25

34
/ 100
Emerging

This project helps researchers and scientists train advanced deep learning models for weather forecasting, similar to those used in FourCastNet or Pangu-Weather. It takes atmospheric data, like the ERA5 reanalysis dataset, and outputs a trained vision transformer model capable of predicting future atmospheric states. This tool is designed for computational scientists and climate researchers who need to develop and optimize high-performance weather prediction models.

Use this if you are a researcher or scientist at NERSC looking to train large-scale deep learning models for weather forecasting on the Perlmutter supercomputer.

Not ideal if you are a practitioner looking for an out-of-the-box weather prediction application rather than a tutorial on training large-scale deep learning models.

weather-forecasting climate-modeling atmospheric-science scientific-computing deep-learning-research
No License No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 7 / 25
Community 16 / 25

How are scores calculated?

Stars

13

Forks

7

Language

Python

License

Last pushed

Nov 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NERSC/sc25-dl-tutorial"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.