Gentrification is multidimensional and complex, but there is general agreement that visible changes to neighbourhoods are a clear manifestation of the process. Recent advances in computer vision and deep learning provide a unique opportunity to support automated mapping or ‘deep mapping’ of perceptual environmental attributes. We present a Siamese convolutional neural network (SCNN) that automatically detects gentrification-like visual changes in temporal sequences of Google Street View (GSV) images. Our SCNN achieves 95.6% test accuracy and is subsequently applied to GSV sequences at 86110 individual properties over a 9-year period in Ottawa, Canada. We use Kernel Density Estimation (KDE) to produce maps that illustrate where the spatial concentration of visual property improvements was highest within the study area at different times from 2007–2016. We find strong concordance between the mapped SCNN results and the spatial distribution of building permits in the City of Ottawa from 2011 to 2016. Our mapped results confirm those urban areas that are known to be undergoing gentrification as well as revealing areas undergoing gentrification that were previously unknown. Our approach differs from previous works because we examine the atomic unit of gentrification, namely, the individual property, for visual property improvements over time and we rely on KDE to describe regions of high spatial intensity that are indicative of gentrification processes.

Income polarization is a pressing issue which is increasingly discussed by academics and policymakers. The present research examines income polarization in Canada’s eight largest Census Metropolitan Areas (CMAs) using data at the census-tract (CT) level between 1971 and 2016. Generally, there are significant decreasing trends in the middle-income population with simultaneously increasing trends in low-income groups. The high-income groups have been relatively stable with fewer significant increasing population trends. Using conventional mapping and cartograms, patterns of the spatial evolution of income inequality are illustrated. Every CMA examined contains an increasing trend of spatial fragmentation at the patch level within each CMA’s landscape mosaic. The results of a spatial autocorrelation analysis at the sub-patch, CT level, exhibit significant spatial clustering of high-income CTs as one process that dominates the increasingly fragmented landscape mosaic.

No abstract