Abstract:The presence of slums in a city is an indicator of poverty and its proper delimitation is a matter of interest for researchers and policy makers. Socio-economic data from surveys and censuses are the primary source of information to identify and quantify slumness within a city or a town. One problem of using survey data for quantifying slumness is that this type of data is usually collected every ten years and is an expensive and time consuming process. Based on the premise that the physical appearance of an u… Show more
“…En el ámbito internacional se han realizado múltiples estudios para varios países utilizando esta metodología (Mason y Fraser, 1998;Hofmann, 2001;Hofmann et al, 2008;Engstrom et al, 2015;Ravshty et al, 2015;Williams et al (2015)). En el caso de Colombia, uno de los más recientes es el trabajo para Medellín realizado por Duque et al (2013). Esta aproximación tiene la ventaja…”
Section: Los Conceptos De Informalidad Laboral Y Urbanaunclassified
“…En el ámbito internacional se han realizado múltiples estudios para varios países utilizando esta metodología (Mason y Fraser, 1998;Hofmann, 2001;Hofmann et al, 2008;Engstrom et al, 2015;Ravshty et al, 2015;Williams et al (2015)). En el caso de Colombia, uno de los más recientes es el trabajo para Medellín realizado por Duque et al (2013). Esta aproximación tiene la ventaja…”
Section: Los Conceptos De Informalidad Laboral Y Urbanaunclassified
“…We extract information on land cover composition using per-pixel classification and on urban texture and structure using an automated tool for texture and structure feature extraction at object level (Ruiz et al, 2011). We use data from Medellin (Colombia), which is the second larger city in the country, and it has been one of the most violent cities in the world in past decades and is still one of the most socioeconomically divergent (Duque et al, 2013a). This city is a useful location for conducting intra-urban variability studies because it has experienced high population growth rates since the 1950s, and the unplanned urban growth in some parts of the city resulted in a high degree of spatial heterogeneity in both the socioeconomic and physical characteristics of its neighborhoods.…”
This work starts by reviewing the potential applications of satellite remote sensing to regional science research in urban settings. Regional science is the study of social problems that have a spatial dimension (Isard, 1975; Isserman, 2004). The availability of satellite remote sensing data has increased significantly in the last two decades, and these data constitute a useful data source for mapping the composition of urban settings and analyzing changes over time (Weng & Quattrochi, 2006). The increasing spatial resolution of commercial satellite imagery has influenced the emergence of new research and applications of regional science in urban settlements because it is now possible to identify individual objects of the urban fabric (Sliuzas et al., 2010).
This paper provides evidence on the usefulness of very high spatial resolution (VHR) imagery in gathering socioeconomic information in urban settlements. We use land cover, spectral, structure and texture features extracted from a Google Earth image of Liverpool (UK) to evaluate their potential to predict Living Environment Deprivation at a small statistical area level. We also contribute to the methodological literature on the estimation of socioeconomic indices with remote-sensing data by introducing elements from modern machine learning. In addition to classical approaches such as Ordinary Least Squares (OLS) regression and a spatial lag model, we explore the potential of the Gradient Boost Regressor and Random Forests to improve predictive performance and accuracy. In addition to novel predicting methods, we also introduce tools for model interpretation and evaluation such as feature importance and partial dependence plots, or cross-validation. Our results show that Random Forest proved to be the best model with an R2 of around 0.54, followed by Gradient Boost Regressor with 0.5. Both the spatial lag model and the OLS fall behind with significantly lower performances of 0.43 and 0.3, respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.