Photo by DeepMind on Unsplash

NOAA National Digital Forecast Database (NDFD) Dataset for Machine Learning

Install DagsHub:

pip install dagshub
Click on copy button to copy content

To stream this data directly on DagsHub

from dagshub.streaming import DagsHubFilesystem

fs = DagsHubFilesystem(".", repo_url="https://test.dagshub.com/DagsHub-Datasets/noaa-ndfd-dataset")

fs.listdir("s3://noaa-ndfd-pds")
Click on copy button to copy content

Description

The National Digital Forecast Database (NDFD) is a suite of gridded forecasts of sensible weather elements (e.g., cloud cover, maximum temperature). Forecasts prepared by NWS field offices working in collaboration with the National Centers for Environmental Prediction (NCEP) are combined in the NDFD to create a seamless mosaic of digital forecasts from which operational NWS products are generated. The most recent data is under the opnl and expr prefixes. A copy is also placed under the wmo prefix. The wmo prefix is structured like so: wmo/<parameter>/<year>/<month>/<day>/<wmo-file-name> The wmo filename codes can be deciphered using the spreadsheet in the root of the bucket.

Additional information

Documentation

https://vlab.noaa.gov/web/mdl/ndfd (For NDFD Product information, instructions, and lookup tables)

Update frequency

As often as once every half hour (varies by forecast element, forecast projection, and domain)

License

Open Data. There are no restrictions on the use of this data.

Related datasets

Atmospheric Models from Météo-France

CAFE60 reanalysis

Coupled Model Intercomparison Project Phase 5 (CMIP5) University of Wisconsin-Madison Probabilistic Downscaling Dataset

Earth Radio Occultation

Launch your ML development to new heights with DagsHub

Back to top