Neighborhood Greenery as a Predictor of Outdoor Crimes between Low and High-Income Neighborhoods

An AI-based framework for studying visual diversity of urban neighborhoods and its relationship with socio-demographic variables

This study presents a framework to study quantitatively geographical visual diversities of urban neighborhood from a large collection of street-view images using an Artificial Intelligence (AI)-based image segmentation technique. A variety of diversity indices are computed from the extracted visual semantics. They are utilized to discover the relationships between urban visual appearance and socio-demographic variables. This study also validates the reliability of the method with human evaluators. The methodology and results obtained from this study can potentially be used to study urban features, locate houses, establish services, and better operate municipalities.

Is green space associated with reduced crime? A national-scale study from the Global South

Assumptions about the link between green space and crime mitigation are informed by literature that overwhelmingly originates in the Global North. Little is known about the association between green spaces and crime in the Global South. We utilized 10 years of precinct-level crime statistics (n = 1152) over South Africa, a global crime hotspot, to test the hypothesis that green space is associated with reduced crime rates. We found that, after controlling for a number of socio-demographic confounders (unemployment, income, age, education, land use and population density), for every 1% increase in total green space there is a 1.2% (0.7 to 1.7%; 95% confidence interval) decrease in violent crime, and 1.3% (0.8 to 1.8%) decrease in property crime, with no effect on sexual crimes. However, the direction of the association changed for property crimes when exploring the effect of green space characteristics including tree cover and park accessibility. Property crimes increase by 0.4% (0.1 to 0.7%) with a percentage increase in tree cover, and by 0.9% (0.5 to 1.3%) with every kilometer increase in proximity to a public park. Further research, including experimental studies, is needed to better isolate causal mechanisms behind crime-green space associations, especially considering that green space may map to race and income inequality and that there may be more crime reporting in affluent areas. Nevertheless, our results provide a complementary contribution to the evidence from the Global North, highlighting the need for more nuanced definitions of green space and its characteristics when considering links to crime. When viewed in light of the broader suite of ecosystem services provided by green space, our results support urban greening as a major strategy towards achieving just and sustainable cities and towns.