Photo by DeepMind on Unsplash

NOAA Global Mosaic of Geostationary Satellite Imagery (GMGSI) 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-gmgsi-dataset")

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

Description

NOAA/NESDIS Global Mosaic of Geostationary Satellite Imagery (GMGSI) visible (VIS), shortwave infrared (SIR), longwave infrared (LIR) imagery, and water vaport imagery (WV) are composited from data from several geostationary satellites orbiting the globe, including the GOES-East and GOES-West Satellites operated by U.S. NOAA/NESDIS, the Meteosat-11 and Meteosat-8 satellites from theMeteosat Second Generation (MSG) series of satellites operated by European Organization for the Exploitation of Meteorological Satellites (EUMETSAT), and the Himawari-8 satellite operated by the Japan Meteorological Agency (JMA). GOES-East is positioned at 75 deg W longitude over the equator. GOES-West is located at 137.2 deg W longitude over the equator. Both satellites cover an area from the eastern Atlantic Ocean to the central Pacific Ocean region. The Meteosat-11 satellite is located at 0 deg E longitude to cover Europe and Africa regions. The Meteosat-8 satellite is located at 41.5 deg E longitude to cover the Indian Ocean region. The Himawari-8 satellite is located at 140.7 deg E longitude to cover the Asia-Oceania region. The visible imagery indicates cloud cover and ice and snow cover. The shortwave, or mid-infrared, indicates cloud cover and fog at night. The longwave, or thermal infrared, depicts cloud cover and land/sea temperature patterns. The water vapor imagery indicates the amount of water vapor contained in the mid to upper levels of the troposphere, with the darker grays indicating drier air and the brighter grays/whites indicating more saturated air. GMGSI composite images have an approximate 8 km (5 mile) horizontal resolution and are updated every hour.

Additional information

Documentation

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