UT-GraphCast Hindcast Dataset: A Global AI Forecast Archive from UT Austin for Weather and Climate Applications
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911016493776896 |
|---|---|
| author | Sudharsan, Naveen Singh, Manmeet Kamath, Harsh Dashtian, Hassan Dawson, Clint Yang, Zong-Liang Niyogi, Dev |
| author_facet | Sudharsan, Naveen Singh, Manmeet Kamath, Harsh Dashtian, Hassan Dawson, Clint Yang, Zong-Liang Niyogi, Dev |
| contents | The UT GraphCast Hindcast Dataset from 1979 to 2024 is a comprehensive global weather forecast archive generated using the Google DeepMind GraphCast Operational model. Developed by researchers at The University of Texas at Austin under the WCRP umbrella, this dataset provides daily 15 day deterministic forecasts at 00UTC on an approximately 25 km global grid for a 45 year period. GraphCast is a physics informed graph neural network that was trained on ECMWF ERA5 reanalysis. It predicts more than a dozen key atmospheric and surface variables on 37 vertical levels, delivering a full medium range forecast in under one minute on modern hardware. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_17453 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UT-GraphCast Hindcast Dataset: A Global AI Forecast Archive from UT Austin for Weather and Climate Applications Sudharsan, Naveen Singh, Manmeet Kamath, Harsh Dashtian, Hassan Dawson, Clint Yang, Zong-Liang Niyogi, Dev Geophysics Machine Learning Atmospheric and Oceanic Physics The UT GraphCast Hindcast Dataset from 1979 to 2024 is a comprehensive global weather forecast archive generated using the Google DeepMind GraphCast Operational model. Developed by researchers at The University of Texas at Austin under the WCRP umbrella, this dataset provides daily 15 day deterministic forecasts at 00UTC on an approximately 25 km global grid for a 45 year period. GraphCast is a physics informed graph neural network that was trained on ECMWF ERA5 reanalysis. It predicts more than a dozen key atmospheric and surface variables on 37 vertical levels, delivering a full medium range forecast in under one minute on modern hardware. |
| title | UT-GraphCast Hindcast Dataset: A Global AI Forecast Archive from UT Austin for Weather and Climate Applications |
| topic | Geophysics Machine Learning Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2506.17453 |