Data Information

We provide a set of four large multi-part satellite images, each composed of dozens of individual satellite tiles, covering several hundred thousand km², and encompassing hundreds of lakes. The four images are from four different dates in the summer 2019 melt season, which saw a disproportionately large amount of melt and runoff. All the images cover the same two regions, in southwest and northeast Greenland (see image below, images follow shortly), and contain many surface lakes and other hydrologic features.

Each image will have a corresponding geojson file (.json) as follows:

1. A file containing “regions” outlines over each satellite image. The regions have been identified as two types: “training” regions, where all available lakes have been hand-outlined to assist your algorithms in lake detection, and “test” regions, where your algorithm is tasked to outline lakes within the region.
2. A file containing the vector polygon lake outlines as hand-tagged by reviewers. The field named “region” identifies each training region in which it is contained, and the “image” tag identifies the corresponding image. Data will be made available through the contest website.

Access

The 4 GeoTiff images (.tif) as well as additional geospatial information (.aux.xml) are currently available for download here.

Additional data are provided as Geopackage. GeoPackages are an open, platform-independent, self-describing geospatial database format. GeoPackage files can be easily read and written using open-access geospatial libraries such as GeoPandas.

A GeoPackage file containing the “training” and “test” region outlines in each image is available here: lake_regions.gpkg.

A GeoPackage containing example lakes in the “training” regions is available here: lake_polygons_training.gpkg.

An explanation of the data formats is available here: GISCup_2023_datasets_readme.pdf.

A GeoPackage with your “answers” to the “test” regions should be named “lake_polygons_test.gpkg” and have an identical column format to the “lake_polygons_training.gpkg” file, with each lake polygon specifying the image from which it was derived specified in the “image” column. Your GeoPackage should be in the EPSG:3857 (“WGS 84 / Pseudo-Mercator”) coordinate reference system, the same as the input rasters and all provided GeoPackage files. See Submission Guidelines for all details.