Keywords
urban land use change, sustainable environmental planning, geographically weighted regression modelling
Start Date
1-7-2010 12:00 AM
Abstract
In this study we applied Geographically Weighted Regression (GWR) approach to model urban landuse changes in Penang Island from 1990 to 2005, covering the period during which the Island has experiencedtremendous urban growth due to in migration from adjacent areas. Land use change has potential impacts on thephysical and social environment. We identified spatial variables describing environment, physical and socioeconomicfactors which are hypothesized to influence the change in the land use in the study area. An ordinaryleast squares regression (OLS) model is applied to the variables followed by a GWR model and the results arecompared. The results show that the GWR outputs explained considerably more variance in the relationship ofthe explanatory factors compared to conventional OLS models and provided significantly better results. Inaddition, GWR also provided important insights on location where changes happen and what distance to the citycenter they appear. The information generated will give understanding of spatio-temporal dynamics of land usechanges resulted from different land use policies and can serve as a basis for developing possible growthscenarios which are essential for sustainable urban planning and development. However, more comprehensivestudies are needed to understand long term spatio-temporal patterns and complex inter-related challenges theurban areas of Penang Island facing presently.
Modelling Urban Land Use Change Using Geographically Weighted Regression and the Implications for Sustainable Environmental Planning
In this study we applied Geographically Weighted Regression (GWR) approach to model urban landuse changes in Penang Island from 1990 to 2005, covering the period during which the Island has experiencedtremendous urban growth due to in migration from adjacent areas. Land use change has potential impacts on thephysical and social environment. We identified spatial variables describing environment, physical and socioeconomicfactors which are hypothesized to influence the change in the land use in the study area. An ordinaryleast squares regression (OLS) model is applied to the variables followed by a GWR model and the results arecompared. The results show that the GWR outputs explained considerably more variance in the relationship ofthe explanatory factors compared to conventional OLS models and provided significantly better results. Inaddition, GWR also provided important insights on location where changes happen and what distance to the citycenter they appear. The information generated will give understanding of spatio-temporal dynamics of land usechanges resulted from different land use policies and can serve as a basis for developing possible growthscenarios which are essential for sustainable urban planning and development. However, more comprehensivestudies are needed to understand long term spatio-temporal patterns and complex inter-related challenges theurban areas of Penang Island facing presently.
