Trend analysis of lake dynamics from Landsat time-series 1999-2014, Kobuk-Selawik-Lowlands, Alaska (US)

The dataset was created with a methodology based on machine-learning based classification of robust trends of multi-spectral indices of Landsat data (TM,ETM+, OLI) and object-based lake detection, to analyze and compare the individual, local and regional lake dynamics of four different study sites: Alaska North Slope (NSL), Kobuk-Selawik-Lowlands Western Alaska (AKS), Central Yakutia (CYA) and Kolyma Lowland (KOL) in the northern permafrost zone from the years 1999 to 2014. The data publication provides geospatial polygon and point vector files (ESRI Shapefile or GeoJSON) and raster layer for every study site. The polygon layer contains the boundaries and the point layer the centroid of each detected lake object. The raster layer shows the net lake area change in ha within grid cells of 3 x 3 km.

Detailed information about the methods can be found in the publication to which this dataset is a supplement.