[GRASS-user] Weights of Evidence in GRASS?

[Nick Jachowski]

Hi Gergely,

I do a lot of predictive modeling, and the approach I take is to export my
data (prepared in GRASS GIS) to an open-source modeling software such WEKA,
and then map the results using GRASS. It takes a little more work than
utilizing built in modeling options often found in GIS software, but you
can do a lot more with it... For GRASS this entails exporting your
variables (rasters I'm guessing) as single column and combining them into a
csv file which you pass to WEKA. Then you map the results of your
predictive modeling in GRASS. If you want more detailed steps I could help
you out, but my suggestion is to just play around with it to see if it'll
work for you. I'm writing a program at the moment which couples GRASS and
WEKA, but it's still in a very beta state.

Best,
Nick

On Wed, Jan 18, 2012 at 6:00 PM, fegyi001 <fegyi001 at gmail.com> wrote:

> Hey Everyone!
>
> Until now I've worked with ArcGIS, but recently changed to GRASS GIS. Enjoy
> it!
> In ArcGIS there is an extension called ArcSDM (Spatial Data Modeler),
> including the Weights of Evidence method which is an excellent way for
> archaeological predictive modeling.
>
> I would like to use this method in GRASS GIS. Does anyone know any similar
> here in GRASS?
>
> Thanks in advance,
>
>          Gergely Padányi-Gulyás
>
> --
> View this message in context:
> http://osgeo-org.1803224.n2.nabble.com/Weights-of-Evidence-in-GRASS-tp7199755p7199755.html
> Sent from the Grass - Users mailing list archive at Nabble.com.
> _______________________________________________
> grass-user mailing list
> grass-user at lists.osgeo.org
> http://lists.osgeo.org/mailman/listinfo/grass-user
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.osgeo.org/pipermail/grass-user/attachments/20120119/ea2b1bc8/attachment.html