GraphCast Global Forecast System (GFS GraphCast)

Description

GraphCast Global Forecast System is an experimental global forecast from NOAA/NCEP built on Google DeepMind’s GraphCast machine-learning model. It runs four cycles per day (00, 06, 12, 18 UTC) and produces 6-hourly forecasts of atmosphere and surface fields. The system is designed for medium-range guidance and quick situational awareness at global scale.

The core model is a message-passing graph neural network with an encoder–processor–decoder design. It was pre-trained on ECMWF’s ERA5 reanalysis and in NOAA’s implementation uses two GDAS analysis states, the current time and the one 6 hours earlier, as inputs to step the forecast forward in 6-hour increments. The current operational configuration focuses on a 13-level pressure grid and provides temperature, wind components, geopotential height, specific humidity, vertical velocity, and standard surface variables.

GraphCastGFS is related to GFS through its GDAS initial conditions and is a peer to other AI-based global models such as AIFS. It is not a replacement for numerical weather prediction and is best used alongside physics-based models for validation and risk assessment.

Detail

• Product page: GraphCast GFS documentation
• Resolution: 0.25° global grid
• Vertical levels: 13 pressure levels (the earlier 37-level stream was retired)
• Cycles: 00, 06, 12, 18 UTC
• Forecast cadence and length: 6-hour steps to 16 days
• Inputs: GDAS analyses at t0 and t0-6 h; model pre-trained on ERA5
• Status: Experimental
• Primary uses: Medium-range scenario exploration, ensemble-style risk checks, quick global situational awareness, research and benchmarking

Parameters: