Published November 9, 2026 | Version 1.0.0

GraphCast_OSSE: truth-insertion OSSE framework for Google DeepMind GraphCast (0.25 deg, 37 levels)

  • 1. University of Maryland, Baltimore County, Baltimore, MD, USA
  • 2. Earth Sciences Division, NASA Ames Research Center, Moffett Field, CA, USA

Description

GraphCast_OSSE: truth-insertion OSSE framework for Google DeepMind GraphCast (0.25 deg, 37 levels).

Code release accompanying the manuscript An AI-Based OSSE Framework to Evaluate Learned Physical Consistency: A Multi-Model Study Using FourCastNet, Aurora, Prithvi WxC, and GraphCast (Diggikar, Halem, and Raman; submitted to AGU Journal of Geophysical Research: Machine Learning and Computation).

Notes

Model weights and input/verification data (ERA5, MERRA-2) are not included; see README for sources.

Files

yashdiggikar/GraphCast_OSSE-v1.0.0.zip

Files (2.1 MB)

Name Size
md5:15e6d09e6304b005f22b532b63b1db72
2.1 MB Preview Download

Additional details

Related works