[R-sig-Geo] Raster comparrison

[Rainer M. Krug]

Ivailo <ubuntero.9161 at gmail.com> writes:

> On Mon, May 13, 2013 at 8:13 PM, ping yang <pingyang.whu at gmail.com> wrote:
>> Dear Ivailo,
>>
>> Is this method can be used to quantify the spatial variability of two
>> raster grids? Or Is there other measurement will be better to do this?

The earth movers distance might be one option to quantify *differences*
between maps. It is not clear to me, what you mean by "spatial
variability of two raster maps" - do you want to determine the spatial
variability of each raster map and then compare the two afterwards?  

Earth mover distance and e.g. mallow distance are implemented in R -
please see precious email for links to emd implementations in R.

Cheers,

Rainer

>
> Dear Ping,
>
> according to the author of the KappaV package (Vincent Bonhomme),
> rasterizing the vectorial mosaics would be "neither elegant nor exact"
> and that's why he implemented the calculation of the confusion matrix
> (i.e. the matrix quantifying the mismatches in different regions of
> the mosaic)  directly from the vector maps.
>
>> Previously I posted a topic on how to compare two grids regarding to see
>> the difference on spatial variabilities(e.g. two temperature grids). I am
>> still wondering how to do it.
>
> I am not aware of any R code to do such a comparison on raster
> objects, and Cohen’s Kappa just quantifies the degree of agreement
> between the two mosaics of interest. While writing this post I found a
> software package at http://www.riks.nl/mck/ called the "Map Comparison
> Kit" that might lead you further in your efforts.
>
> HTH,
> Ivailo
> --
> UBUNTU: a person is a person through other persons.


-- 
Rainer M. Krug, PhD (Conservation Ecology, SUN), MSc (Conservation Biology, UCT), Dipl. Phys. (Germany)

Centre of Excellence for Invasion Biology
Stellenbosch University
South Africa

Tel :       +33 - (0)9 53 10 27 44
Cell:       +33 - (0)6 85 62 59 98
Fax :       +33 - (0)9 58 10 27 44

Fax (D):    +49 - (0)3 21 21 25 22 44

email:      Rainer at krugs.de

Skype:      RMkrug