hello,
i have 2 raster images that i would like to compare numerically. for the
time being, a simple linear regression would suffice.
these rasters are basically 84 selected points from a much larger raster
image - therefore there should only be 84 pixels that are not NODATA.
i have tried dumping the rasters as ascii, removing the NODATA values, and
setting up a table as follows:
raster1_values | raster2_values
-------------------------------
v1 | v1
v2 | v2
... | ...
however, when i plot the values i am getting very unusual results. it could
be that my plots are valid, but could i be doing something strange here?
thanks in advance,
Dylan
--
"The world is a dangerous place to live; not because of the people who are
evil, but because of the people who don't do anything about it."
-Albert Einstein
What about create a difference raster?
you can do with
r.mapcalc diff=rast1-rast2
So you can see in a moment where difference are.....
dylan wrote:
hello,
i have 2 raster images that i would like to compare numerically. for the
time being, a simple linear regression would suffice.
these rasters are basically 84 selected points from a much larger raster
image - therefore there should only be 84 pixels that are not NODATA.
i have tried dumping the rasters as ascii, removing the NODATA values, and
setting up a table as follows:
raster1_values | raster2_values
-------------------------------
v1 | v1
v2 | v2
... | ...
however, when i plot the values i am getting very unusual results. it could
be that my plots are valid, but could i be doing something strange here?
thanks in advance,
Dylan
--
-------------
note: change my e-mail reference to massimiliano.cannata@supsi.ch
because the old one will be deleted soon.
-------------
Ing. Massimiliano Cannata
Istituto di Scienze della Terra - SUPSI
C.P. 72 - CH-6952 Canobbio (Ticino, Switzerland)
Tel +41 91 /935 12 25 - Fax +41 91 /935 12 09
eMail: massimiliano.cannata@supsi.ch
Internet: http://www.ist.supsi.ch