NLCD data is published in 3x3 degree chunks, as tiff files inside a zip file. For processing this data it's far more convienent if the files are available directly as tiff files without having to unzip.
s3cmd get --skip-existing -r s3://prd-tnm/StagedProducts/NLCD/data/2011/landcover/3x3/
for i in *.zip; do unzip $i '*.tif'; done
mkdir tmp
mkdir clouded
for i in *.tif; do
gdalwarp -srcnodata 0 -dstnodata 0 -co TILED=YES -co BLOCKXSIZE=512 -co BLOCKYSIZE=512 -co COMPRESS=LZW -co ZLEVEL=9 -co TFW=NO $i tmp/$i
gdaladdo -r nearest tmp/$i 2 4 8 16 32
gdal_translate -co TILED=YES -co BLOCKXSIZE=512 -co BLOCKYSIZE=512 -co COMPRESS=LZW -co ZLEVEL=9 -co TFW=NO -co COPY_SRC_OVERVIEWS=YES tmp/$i clouded/$i
rm tmp/$i
done
rmdir tmp
file sizes:
- Original zip files: 3.7 gb
- Unzipped tiff files: 20 gb
- cloud optimized geotiffs: 2.3 gb