Spatial modelling of population concentration using geographically weighted regression method
Apstrakt
This paper presents possibilities of applying the geographically weighted regression method in mapping population change index. During the last decade, this contemporary spatial modeling method has been increasingly used in geographical analyses. On the example of the researched region of Timočka Krajina (defined for the needs of elaborating the Regional Spatial Plan), the possibilities for applying this method in disaggregation of traditional models of population density, which are created using the choropleth maps at the level of statistical spatial units, are shown. The applied method is based on the use of ancillary spatial predictors which are in correlation with a targeted variable, the population change index. For this purpose, spatial databases have been used such as digital terrain model, distances from the network of I and II category state roads, as well as soil sealing databases. Spatial model has been developed in the GIS software environment using commercial GIS applicati...ons, as well as open source GIS software. Population change indexes for the period 1961-2002 have been mapped based on population census data, while the data on planned population forecast have been used for the period 2002-2027.
Ključne reči:
Geographically weighted regression / population change index / dasymetric method / GIS / open source / Timočka KrajinaIzvor:
Zbornik radova Geografskog instituta "Jovan Cvijić", SANU, 2011, 61, 3, 151-167Izdavač:
- Srpska akademija nauka i umetnosti SANU - Geografski institut 'Jovan Cvijić', Beograd
Finansiranje / projekti:
- Prostorni, ekološki, energetski i društveni aspekti razvoja naselja i klimatske promene - međusobni uticaji (RS-36035)
- Uloga i implementacija državnog prostornog plana i regionalnih razvojnih dokumenata u obnovi strateškog istraživanja, mišljenja i upravljanja u Srbiji (RS-47014)