Elsevier Duque, JC.; Patiño Quinchía, JE.; Ruiz Fernández, LÁ.; Pardo Pascual, JE. (2015). Measuring intra-urban poverty using land cover and texture metrics derived from remote sensing data. Landscape and Urban Planning. 135:11-21.
AbstractThis paper contributes empirical evidence about the usefulness of remote sensing imagery to quantify the degree of poverty at the intra-urban scale. This concept is based on two premises: first, that the physical appearance of an urban settlement is a reflection of the society; and second, that the people who reside in urban areas with similar physical housing conditions have similar social and demographic characteristics. We use a very high spatial resolution (VHR) image from one of the most socioeconomically divergent cities in the world, Medellin (Colombia), to 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. We evaluate the potential of these descriptors to explain a measure of poverty known as the Slum Index. We found that these variables explain up to 59% of the variability in the Slum Index. Similar approaches could be used to lower the cost of socioeconomic surveys by developing an econometric model from a sample and applying that model to the rest of the city and to perform intercensal or intersurvey estimates of intra-urban Slum Index maps.
Slum identification in urban settlements is a crucial step in the process of formulation of pro-poor policies. However, the use of conventional methods for slum detection such as field surveys can be time-consuming and costly. This paper explores the possibility of implementing a low-cost standardized method for slum detection. We use spectral, texture and structural features extracted from very high spatial resolution imagery as input data and evaluate the capability of three machine learning algorithms (Logistic Regression, Support Vector Machine and Random Forest) to classify urban areas as slum or no-slum. Using data from Buenos Aires (Argentina), Medellin (Colombia) and Recife (Brazil), we found that Support Vector Machine with radial basis kernel delivers the best performance (with F2-scores over 0.81). We also found that singularities within cities preclude the use of a unified classification model.
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.