Landsat Cloud Cover Assessment (CCA) validation datasets are comprised of satellite imagery with accompanying cloud truth masks that specify which Landsat pixels in the scene are cloudy or clear, or have other conditions such as cloud shadow or snow cover. The cloud truth masks were created manually by operators digitizing clouds by hand using image-editing software. These cloud truth masks are essential for validating existing CCA algorithms and can also be used to train new cloud detection algorithms.
Landsat 7 Cloud Cover Assessment Validation Data
The Landsat 7 CCA validation data were created at USGS EROS to validate CCA algorithms for Landsat 7 Enhanced Thematic Mapper Plus (ETM+) and Landsat 4-5 Thematic Mapper (TM) imagery. They were also used to develop new CCA algorithms for the Landsat 8 Operational Land Imager (OLI) instrument prior to launch.
This collection of cloud validation data contains 206 Landsat 7 ETM+ Level-1G scenes in .tif format, with associated manual cloud truth masks also in .tif format. These scenes are stratified by latitude zone, and within each zone, there is one WRS path/row with multiple scenes to allow multiple views over the same area with varying cloud conditions.
Data Citation: U.S. Geological Survey, 2016. L7 Irish Cloud Validation Masks. U.S. Geological Survey data release. doi:10.5066/F7XD0ZWC. Scaramuzza, P.L., Bouchard, M.A. & Dwyer, J.L. (2012). Development of the Landsat data continuity mission cloud-cover assessment algorithms. IEEE Transactions on Geoscience and Remote Sensing, 50(4), 1140-1154. doi:10.1109/TGRS.2011.2164087.
Landsat 8 Cloud Cover Assessment Validation Data
The Landsat 8 CCA validation data were created at USGS Earth Resources Observation and Science (EROS) Center to validate CCA algorithms for Landsat 8 Operational Land Imager (OLI)/Thermal Infrared Sensor (TIRS) imagery.
This collection of cloud validation data contains 96 Landsat 8 OLI/TIRS Level-1T scenes in .tif format, with manual cloud truth masks as flat data files in .img format. These scenes are clustered into biomes using the International Geosphere Biosphere Program (IGBP) dataset.
Data Citation: U.S. Geological Survey, 2016. L8 Biome Cloud Validation Masks. U.S. Geological Survey, data release. doi:10.5066/F7251GDH. Foga, S., Scaramuzza, P.L., Guo, S., Zhu, Z., Dilley, R.D., Beckmann, T., Schmidt, G.L., Dwyer, J.L., Hughes, M.J. & Laue, B. (2017). Cloud detection algorithm comparison and validation for operational Landsat data products. Remote Sensing of Environment, 194, 379-390. doi:10.1016/j.rse.2017.03.026.
Spatial Procedures for Automated Removal of Cloud and Shadow (SPARCS) Validation Data
The Spatial Procedures for Automated Removal of Cloud and Shadow (SPARCS) validation data were created by M. Joseph Hughes, Oregon State University, and were derived manually from Landsat 8 Operational Land Imager (OLI) scenes. Their purpose was to validate cloud and cloud shadow masking derived from the SPARCS algorithm.
This collection of cloud validation data contains 80, 1000 x 1000-pixel, subsets of Landsat 8 OLI/TIRS scenes in .tif format, each with both a manual cloud truth mask and a color composite preview image, in .png format.
Data Citation: U.S. Geological Survey, 2016. L8 SPARCS Cloud Validation Masks. U.S. Geological Survey data release. doi:10.5066/F7FB5146. Hughes M.J. & Hayes, D.J. (2014). Automated detection of cloud and cloud shadow in single-date Landsat imagery using neural networks and spatial post-processing. Remote Sensing, 6(6), 4907–4926. doi:10.3390/rs6064907.