Graphcast Hindcast

Sudharsan, Naveen et al.

Experiment
6hrhindcasthindcastingmachine learning
Summary
45-year hindcast dataset (1979 to 2024) created from Google Deepmind's Graphcast-operational model. Developed by researchers at The University of Texas at Austin, this dataset provides daily 15‑day deterministic forecasts at 00 UTC on a 0.25°×0.25° global grid (≈25 km) for a 45-year period. GraphCast is a graph neural network that was trained on ECMWF’s ERA5 reanalysis. It predicts more than a dozen key atmospheric and surface variables on 13 vertical levels, delivering a full medium-range forecast in under one minute on modern hardware.

Hindcast generation: The UT Austin team used the open-source GraphCast model to produce the hindcast. Each hindcast day begins with ERA5 atmospheric analysis fields at 00 UTC as the initial state. GraphCast is then iteratively applied forward in time to produce a 15-day (360 h) forecast, with outputs every 6 hours. By rolling GraphCast’s own predictions forward, a continuous global forecast trajectory is obtained. In practice, this process was automated on high-performance cloud hardware.

Key aspects of the workflow include:
Initialization: Input state (0 h) from ERA5 00 UTC global analysis; also incorporates the 6 h prior state as GraphCast input.

Forecast integration: GraphCast operational advances the state in 6 h increments up to 360 h lead, without further data assimilation.

Output: At each lead time (6 h, 12 h, …, 360 h), the model outputs fields of interest. Results are saved in NetCDF4 format for easy access.
Project
UT Austin Graphcast Hindcast (UT-GraphCast Hindcast Dataset: A Global AI Forecast Archive from UT Austin for Weather and Climate Applications)
Contact
Dr. Naveen Sudharsan (
 naveens@nullutexas.edu
 0000-0002-1328-110X)
Dr. Manmeet Singh (
 manmeet.singh@nullutexas.edu
 0000-0002-3374-7149)
Prof. Dr. Dev Niyogi (
 dev.niyogi@nulljsg.utexas.edu
 0000-0002-1848-5080)
Location(s)
global
Spatial Coverage
Longitude 0 to 360 Latitude -90 to 90 Altitude: 1000 hPa to 50 hPa
Temporal Coverage
1979-01-01 to 2024-12-31 (calendrical)
Use constraints
Creative Commons Attribution 4.0 International (https://creativecommons.org/licenses/by/4.0/)
Data Catalog
World Data Center for Climate
Format
NetCDF
Status
metadata only
Creation Date
Future Review Date
2035-07-21
Find data Export dataset acronyms
Cite as
Sudharsan, Naveen; Singh, Manmeet; Kamath, Harsh; Dashtian, Hassan; Dawson, Clint; Yang, Zong-Liang; Niyogi, Dev (2025). UT-GraphCast Hindcast Dataset (1979–2024): A Global AI Forecast Archive from UT Austin for Weather and Climate Applications. World Data Center for Climate (WDCC) at DKRZ. https://www.wdc-climate.de/ui/entry?acronym=graphcast

BibTeX RIS
Funding
United States Department of Energy
Grant/Award No: DE-SC0022211 - MuSiKAL: Multiphysics Simulations and Knowledge discovery through AI/ML technologies
Contact typePersonORCIDOrganization
Contact
Dr. Naveen Sudharsan
0000-0002-1328-110X
The University of Texas at Austin
Contact
Dr. Manmeet Singh
0000-0002-3374-7149
The University of Texas at Austin
Contact
Prof. Dr. Dev Niyogi
0000-0002-1848-5080
The University of Texas at Austin
Author
Dr. Naveen Sudharsan
0000-0002-1328-110X
The University of Texas at Austin
Author
Dr. Manmeet Singh
0000-0002-3374-7149
The University of Texas at Austin
Author
Harsh Kamath
0000-0002-5210-8369
The University of Texas at Austin
Author
Dr. Hassan Dashtian
0000-0001-6400-1190
The University of Texas at Austin
Author
Dr. Clint Dawson
0000-0001-7273-0684
The University of Texas at Austin
Author
Dr. Zong-Liang Yang
0000-0003-3030-0330
The University of Texas at Austin
Author
Prof. Dr. Dev Niyogi
0000-0002-1848-5080
The University of Texas at Austin
Investigator
Dr. Naveen Sudharsan
0000-0002-1328-110X
The University of Texas at Austin
Funder
-
-
United States Department of Energy

Is compiled by

[1] DOI Lam, Remi; Sanchez-Gonzalez, Alvaro; Willson, Matthew; Wirnsberger, Peter; Fortunato, Meire; Alet, Ferran; Ravuri, Suman; Ewalds, Timo; Eaton-Rosen, Zach; Hu, Weihua; Merose, Alexander; Hoyer, Stephan; Holland, George; Vinyals, Oriol; Stott, Jacklynn; Pritzel, Alexander; Mohamed, Shakir; Battaglia, Peter. (2023). Learning skillful medium-range global weather forecasting. doi:10.1126/science.adi2336

Is derived from

[1] DOI Hersbach, Hans; Bell, Bill; Berrisford, Paul; Hirahara, Shoji; Horányi, András; Muñoz‐Sabater, Joaquín; Nicolas, Julien; Peubey, Carole; Radu, Raluca; Schepers, Dinand; Simmons, Adrian; Soci, Cornel; Abdalla, Saleh; Abellan, Xavier; Balsamo, Gianpaolo; Bechtold, Peter; Biavati, Gionata; Bidlot, Jean; Bonavita, Massimo; Chiara, Giovanna; Dahlgren, Per; Dee, Dick; Diamantakis, Michail; Dragani, Rossana; Flemming, Johannes; Forbes, Richard; Fuentes, Manuel; Geer, Alan; Haimberger, Leo; Healy, Sean; Hogan, Robin J.; Hólm, Elías; Janisková, Marta; Keeley, Sarah; Laloyaux, Patrick; Lopez, Philippe; Lupu, Cristina; Radnoti, Gabor; Rosnay, Patricia; Rozum, Iryna; Vamborg, Freja; Villaume, Sebastien; Thépaut, Jean‐Noël. (2020). The ERA5 global reanalysis. doi:10.1002/qj.3803

Attached Datasets ( 46 )

Details for selected entry

Parent project(s)

UT-GraphCast Hindcast Dataset: A Global AI Forecast Archive from UT Austin for Weather and Climate Applications

[Entry acronym: graphcast] [Entry id: 5285964]