Land Cover result (2011) from 1d-CNN on CONUS

The document is the land cover results from the paper:

Hankui K. Zhang, David P. Roy, Dong Luo, Demonstration of large area land cover classification with a one dimensional convolutional neural network applied to single pixel temporal metric percentiles. Remote sensing of environment. (revision)

There is total 482 files and the name of each file is:

Landsatard2011.hxxvxx.7p.cnnnlcd.tif

The “hxx” and “vxx” are the unique horizontal and vertical number that aligning with the Conterminous U.S. Landsat Analysis Ready Data (ARD) Tiles https://www.usgs.gov/media/images/conterminous-us-landsat-analysis-ready-data-ard-tiles.

Total 15 classes:

11: Open water

21: Developed, open-space

22: Developed, low-intensity

23: Developed, medium-intensity

24: Developed, high-intensity

31: Barren land

41: Deciduous forest

42: Evergreen forest

43: Mixed forest

52: Shrub/scrub

71: Grassland/herbaceous

81: Pasture/hay

82: Cultivated crops

90: Woody wetlands

95: Emergent herbaceous wetland

The data format is GEOTIFF files with unit8 data type.

It has "cnn1d_landcover_result_readme" and zip file "cnn1d.7p.result.u8".