The A-Train Cloud Segmentation Dataset

ATCS is a dataset designed to train deep learning models to volumetrically segment clouds from multi-angle satellite imagery. The dataset consists of spatiotemporally aligned patches of multi-angle polarimetry from the POLDER sensor aboard the PARASOL mission and vertical cloud profiles from the 2B-CLDCLASS product using the cloud profiling radar (CPR) aboard CloudSat.

Data and Resources

Additional Info

Field Value
Maintainer Earthdata Forum
Last Updated September 11, 2025, 04:22 (UTC)
Created April 1, 2025, 19:29 (UTC)
accessLevel public
bureauCode {026:00}
catalog_conformsTo https://project-open-data.cio.gov/v1.1/schema
harvest_object_id 261415d0-c661-4a4c-af0c-87c3c0b541fd
harvest_source_id b99e41c6-fe79-4c19-bbc3-9b6c8111bfac
harvest_source_title Science Discovery Engine
identifier 10.5067/SeaBASS/ATCS/DATA001
landingPage https://seabass.gsfc.nasa.gov/experiment/ATCS/
modified 2025-09-10
programCode {026:000}
publisher NASA/GSFC/SED/ESD/GCDC/OB.DAAC;NASA/GSFC/SED/ESD/GCDC/SeaBASS
resource-type Dataset
source_datajson_identifier true
source_hash 5bcd4b29ef7d8bb2e9077ea1580a333e09aa36eabbb35857d3fcba5cc7ad817d
source_schema_version 1.1
spatial [[{"EastBoundingCoordinate":180.0,"NorthBoundingCoordinate":90.0,"SouthBoundingCoordinate":-90.0,"WestBoundingCoordinate":-180.0}],"CARTESIAN"]
temporal 2007-11-27/2007-11-27
theme {"Earth Science"}