STRATA-SCREAM (sdy1)
Global, storm-resolving atmospheric simulation output generated by the SCREAM (Simple Cloud-Resolving E3SM Atmosphere Model) physics model, providing high-resolution global atmospheric state fields for training and evaluating machine-learning weather and climate emulators. The data were produced by the E3SM Project (U.S. Department of Energy) and are publicly available at NERSC under CC BY 4.0; this release is an ML-ready version converted from NetCDF to Zarr and subsampled, with no underlying data values altered. This repository contains the sdy1 simulation store (F2010-SCREAMv1): 1,009 timesteps at 10-minute resolution on the cubed-sphere ne1024pg2 grid (25,165,824 columns, about 4.9 km) with 32 vertical levels and about 34 variables. It is part of a three-part release with the companion STRATA-SCREAM repositories (sdy2, sdecadal). Zarr, 19.6 TB. License: CC BY 4.0.
- Category
- Climate & Weather
- Provider
- E3SM Project (U.S. DOE); ML-ready release by NVIDIA
- License
- cc-by-4.0
- Hosted on
- Hugging Face, bucket nvidia/STRATA-SCREAM-sdy1, us
- Access
- Free and public. No account with the data provider is needed.
- Source
- https://portal.nersc.gov/archive/home/n/ndk/www/STRATA2026
Analyze this dataset without downloading it
On Scigantic, STRATA-SCREAM (sdy1) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.