Understanding similarities and differences between data-driven AI model-based and physics model-based ensemble forecasts

Du, Jun; Sadeghi Tabas, Sadegh; Wang, Jun; Levit, Jason

doi:10.25923/4pc4-3t39

i

Understanding similarities and differences between data-driven AI model-based and physics model-based ensemble forecasts

Public Domain

2025
By Du, Jun ; Sadeghi Tabas, Sadegh ; Wang, Jun ; ...
Series: Office note (National Centers for Environmental Prediction (U.S.)) 523

File Language:

Details

Personal Author:

Du, Jun ; Sadeghi Tabas, Sadegh ; Wang, Jun ; Levit, Jason
Corporate Authors:

National Centers for Environmental Prediction (U.S.) ; Environmental Modeling Center (U.S.) ; Axiom.
NOAA Program & Office:

NWS (National Weather Service) ; NCEP (National Centers for Environmental Prediction) ; EMC (Environmental Modelling Center)
Description:

At NOAA/NWS/National Centers for Environmental Prediction (NCEP), a Google DeepMind developed machine-learning weather model GraphCast-based global ensemble forecast system (MLGEFS) has been tested. This study compares MLGEFS with the NCEP operational global ensemble forecast system (GEFS).
Keywords:

AI Model Global Ensemble Forecast System (GEFS) Google DeepMind GraphCast Weather Model Physical Model
Series:

Office note (National Centers for Environmental Prediction (U.S.)) ; 523
DOI:

https://doi.org/10.25923/4pc4-3t39
Format:

pdf
Document Type:

Office Note
License:

https://creativecommons.org/publicdomain/zero/1.0/
Rights Information:

CC0 Public Domain
Compliance:

Submitted
Main Document Checksum:

urn:sha-512:1dca7adb469e186bac2ad557b29855e6e57991ab3d7ed05e9a84562325f39829dac4173b77428ceb7ca4e27cdead6fd227dbffbdeeedda39203131f0eb5b2e82
Download URL:

https://repository.library.noaa.gov/view/noaa/70923/noaa_70923_DS1.pdf
File Type:

[PDF - 4.60 MB ]

File Language:

ON THIS PAGE

Details

The NOAA IR serves as an archival repository of NOAA-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by NOAA or funded partners. As a repository, the NOAA IR retains documents in their original published format to ensure public access to scientific information.