All of Scioteca
Communities & Collections By Issue Date Authors Titles Subjects Country / Region
Profiles
Our Authors
My Account
Login

Exploring the Potential of Machine Learning for Automatic Slum Identification from VHE Imagery

Slum identification in urban settlements is a crucial step in the process of formulation of propoor policies. However, the use of conventional methods for slums detection such as field surveys may result 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 deliver the best performance (over 0.81). We also found that singularities within cities preclude the use of a unified classification model.

Abstract

Description

Subject

Ciudades | Desarrollo urbano | Economía | Equidad e inclusión social | Georreferenciación | Investigación socioeconómica | Pobreza | Políticas públicas | Servicios públicos | Vivienda

País / Región

Argentina
Brasil
Colombia

URI

https://scioteca.caf.com/handle/123456789/975

Date

2016-11-23

Cite from this publication

Collections

6.1 Documentos de trabajo en investigación socioeconómica

Endorsement

Review

Supplemented By

Referenced By

Creative Commons license

CC-BY-NC
Except where otherwised noted, this item's license is described as CC-BY-NC
Thumbnail Image

Files

Duque, Patino & Betancourt (2016).pdf (6.97 MB)

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

CAF

Related Items

Thumbnail Image
Determinants of Slum Formation: The Role of Local Politics and Policies

One-third of the developing world’s population lives in urban slums and the absolute number of slum residents grew from 650 million in 1990 to 863...

Thumbnail Image
Slum Growth in Brazilian Cities

I study slum growth in contemporary urbanization processes by estimating a spatial equilibrium model with houses with and without basic water and sanitation services in...

Thumbnail Image
The Political Economy of Slum Growth: Evidence from Brazil

One-fourth of the world’s urban population lives in slums and the number of slum residents grew from 650 million in 1990 to 1 billion in...

Thumbnail Image
Criminal Dominance and Campaign Concentration

There are many journalistic and anecdotal accounts about the prevalence of electoral corrals in Brazil, geographic areas where brokers, politicians, or community leaders influence residents...

Thumbnail Image
What is the Role of Urban Growth on Inequality, and Segregation? The Case of Urban Argentina´s Urban Agglomerations

We analyze the relationship between urban sprawl and changing patterns of inequality and segregation in metropolitan areas of Argentina. The existing literature has endeavored to...

Thumbnail Image
Measuring the size and growth of cities using nighttime light

This paper uses high-resolution images of nighttime luminosity to estimate a globally comparable measure of the size of metropolitan areas around the world for the...