Sunday, January 28, 2018

Preliminary comparison of NasaDEM dataset

Some early results from testing preliminary NasaDEM dataset (


Comparison in one of the extremely buggy areas in SRTM 1" (30m), tile s50w075:

Original SRTM 1" (30m) data here:


SRTM1 here contains lots of errors, from artificial narrow peaks to holes and areas clamped to the sea level, as well as some negative heights.

SRTM3 (90m) dataset handles this area slightly better, with fewer holes, but it contains different linear artifacts and the elevations are sometimes dead wrong anyway, or the voids are filled from extremely coarse data:

SRTM 3" (scaled)
This area is full of SRTM voids, places where the radar could not get reliable info due to clouds or other factors, and these holes were filled from various other datasets.

NasaDEM is supposed to be a new reprocessing of raw SRTM data, also using newer sources for void fills. Unfortunately, the preliminary dataset leaves a lot to be desired:

NasaDEM (preliminary)
While it's considerably better than SRTM1 in this area, there are still severe artifacts that show up as very ugly sharp transitions in 3D, and it's basically unusable without extensive corrections.

For these corrections it's possible to use another global dataset that is without (significant) artifacts, Viewfinder Panoramas with a global 3" coverage. This one fills SRTM voids using various local maps.

Viewfinder 3" (scaled)


Comparison in previously OK area - river Amazon delta n00w051

We checked this area only because of a slight mismatch between elevations and the water mask, indicating that perhaps the water mask was acquired at a later date and the terrain changed. To our surprise, NasaDEM filling algorithm introduced a new issue - elevation now goes into negative numbers:

NasaDEM (preliminary)

So far it seems that the new dataset won't solve our existing problems and will introduce some new ones, although this is all preliminary and unofficial.

No comments: