[Portugal] Kernel Density

[Giovanni Manghi]

Viva,


> > Estou a precisar construir um raster através da ferramenta de Kernel
> > Density baseada numa layer de pontos e num dos seus atributos. Já
> > estive a experimentar no gvSIG+Sextante e o resultado não me
> > satisfaz uma vez que só me aceita pixel de 1000 metros. Se diminuir
> > este parâmetro tenho problemas com Java Heap Space (memória). Fui ao
> > grass dentro do qgis e vejo la a função gaussian kernel mas não
> > permite seleccionar um atributo do vector. Alguém tem sugestões???
> > 
> > Obrigado.
> > Abraço Viva,



no QGIS poderá usar o plugin
"SDA4PP" (Spatial Data Analysis for Point Pattern) que, entre as outras,
inclui as seguintes ferramentas:


                      * Interactive Identify Tool: returns the value of
                        overlapping raster and vector layers at the same
                        time in one window. It gives more information
                        about feature than the standard identify tool in
                        QGIS.  
                      * Quadrat analysis: A method of point pattern
                        analysis in which the study region is sampled
                        using a set of similar shapes (quadrats) and
                        counting the number of events in each. Analysis
                        of the resulting quadrat counts can help
                        determine whether the pattern is evenly spaced
                        or clustered. 
                      * F function: A function in point pattern analysis
                        based on the cumulative frequency of the
                        shortest distance between events in a point
                        pattern and a set of randomly placed locations
                        in the study area.
                      * G function: A function in point pattern analysis
                        based on the cumulative frequency of the
                        shortest inter- event distances between events
                        in a point pattern. 
                      * K function: A function in point pattern analysis
                        based on all the inter-event distances between
                        events in a point pattern. 
                      * Kernel density estimation: A method of density
                        estimation making use of kernel functions. For
                        each event to be included in the density
                        estimates a kernel function is used to 'spread'
                        its effect across space. 


http://ggit.metu.edu.tr/~volkan/screenshots.html

Para o plugin funcionar é necessario instalar o pacote estatístico "R" e
algumas suas bibliotecas adicionais.

Saluti

-- 
Giovanni Manghi
Faunalia.pt
Sistemas de Informação Geográfica Open Source
Portugal

Web: http://www.faunalia.pt
Email & Jabber: giovanni.manghi at faunalia.pt
PGP Key available
Tel. + 351 96 7058216
--