The ORNL DAAC recently released a new Arctic-Boreal Vulnerability Experiment (ABoVE) dataset by Wang, C. et al. (2022):
This dataset contains land cover classification focused on water and wetland vegetation communities over the Peace-Athabasca Delta, Canada. Four classification maps with 5-m resolution were derived various combinations of Airborne Visible/Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) and Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) acquired in July and September 2019, and a historical LiDAR archive data. The maps include 10 land cover classes, including open water, emergent aquatic vegetation types, terrestrial vegetation, and forest. Based on field data, the best performing model, which combined all three data sources, achieved an overall accuracy of 93.5%. The land cover maps are provided in GeoTIFF format along with polygons of AVIRIS-NG, UAVSAR, and LiDAR footprints in shapefile and KML formats.
The ABoVE is a NASA Terrestrial Ecology Program field campaign being conducted in Alaska and western Canada, for 8 to 10 years, starting in 2015. Research for ABoVE links field-based, process-level studies with geospatial data products derived from airborne and satellite sensors, providing a foundation for improving the analysis, and modeling capabilities needed to understand and predict ecosystem responses to, and societal implications of, climate change in the Arctic and Boreal regions.
Additional data from ABoVE and other relevant links can be found on the ORNL DAAC's ABoVE Project Page.
Citation: Wang, C., T.M. Pavelsky, E.D. Kyzivat, F. Garcia-Tigreros, F. Yao, X. Yang, S. Zhang, C. Song, T. Langhorst, W. Dolan, M. Kurek, M.E. Harlan, L.C. Smith, D. Butman, R.G.M. Spencer, C.J. Gleason, and D.L. Peters. 2022. ABoVE: Wetland Vegetation Classification for Peace-Athabasca Delta, Canada, 2019. ORNL DAAC, Oak Ridge, Tennessee, USA. https://doi.org/10.3334/ORNLDAAC/2069