Earth Data School
About
Full catalog/NWS FOURCASTNETGFS
NWS FOURCASTNETGFS·dataset

Experimental AI global weather forecast, 10 days out (NOAA)

(EXPERIMENTAL) NOAA FourCastNet Global Forecast System (FourCastNetGFS) (EXPERIMENTAL)
atmosphere NOAA NOAA active
In plain English

What it measures. Global forecasts of temperature, winds, humidity, pressure heights, and surface conditions, produced every six hours out to ten days on a roughly 28 km grid.

How it's made. An experimental NOAA system runs Nvidia's FourCastNet machine-learning model, trained on past weather, starting each run from NOAA's latest global analysis.

How & where you'd use it. This is a research-stage forecast that lets scientists test whether AI models can match traditional weather prediction; it is labeled experimental, not operational.

What's measured

aws-pdsagricultureclimatedisaster responseenvironmentalmeteorologicalweather

Coverage & cadence

  • Time span— → ongoing

What you can do with it

  • Map air pollutants — NO₂, aerosols, ozone
  • Track greenhouse gases and Earth's energy budget
  • Feed weather and air-quality analysis
Official description

The FourCastNet Global Forecast System (FourCastNetGFS) is an experimental system set up by the National Centers for Environmental Prediction (NCEP) to produce medium range global forecasts. The model runs on a 0.25 degree latitude-longitude grid (about 28 km) and 13 pressure levels. The model produces forecasts 4 times a day at 00Z, 06Z, 12Z and 18Z cycles. Major atmospheric and surface fields including temperature, wind components, geopotential height, relative humidity and 2 meter temperature and 10 meter winds are available. The products are 6 hourly forecasts up to 10 days. The data format is GRIB2. The FourCastNetGFS system is an experimental weather forecast model built upon the pre-trained Nvidia’s FourCastNet Machine Learning Weather Prediction (MLWP) model version 2. The FourCastNet (Bonev et al, 2023) was developed by Nvidia using Adaptive Fourier Neural Operators. It uses a Fourier transform-based token-mixing scheme with the vision transformer architecture. This model is pre-trained with ECMWF’s ERA5 reanalysis data. The FourCastNetGFS takes one model state as initial condition from NCEP 0.25 degree GDAS analysis data and runs FourCastNet with weights from the pretrained FourCastNet by Nvidia. Unit conversion to the GDAS data is conducted to match the input data required by FourCastNet and to generate forecast products consistent to GFS. The input data generated from the GDAS data as FourCastNet input is provided under the forecast data directory. Example of file names is: input_2024022000.npy There are 40 files under each directory covering a 10 day forecast.

Get the data

noaa_access.py
# NOAA Open Data on AWS — public S3, no login
import s3fs

fs = s3fs.S3FileSystem(anon=True)
# find this dataset's bucket in the docs link in the sidebar, then:
# files = fs.ls("noaa-<bucket>/...")
# open NetCDF/GRIB with xarray, COGs with rioxarray
NOAA Open Data is on public AWS S3 — no login at all (anonymous access).