Corpus ID: 220056268

Case study: Mapping potential informal settlements areas in Tegucigalpa with machine learning to plan ground survey

  title={Case study: Mapping potential informal settlements areas in Tegucigalpa with machine learning to plan ground survey},
  author={F. Bayl{\'e} and Damian E. Silvani},
Data collection through censuses is conducted every 10 years on average in Latin America, making it difficult to monitor the growth and support needed by communities living in these settlements. Conducting a field survey requires logistical resources to be able to do it exhaustively. The increasing availability of open data, high-resolution satellite images, and free software to process them allow us to be able to do so in a scalable way based on the analysis of these sources of information… Expand
1 Citations
Mapping Slums with Medium Resolution Satellite Imagery: a Comparative Analysis of Multi-Spectral Data and Grey-level Co-occurrence Matrix Techniques
Evaluating two techniques on an openaccess dataset consisting of labelled Sentinel-2 images with a spatial resolution of 10 meters indicates that open-access satellite imagery with a resolution of at least 10 meters may be suitable for keeping track of development goals such as the detection of slums in cities. Expand


Assessing the Utility of Satellite Imagery with Differing Spatial Resolutions for Deriving Proxy Measures of Slum Presence in Accra, Ghana
Assessing the correlation between satellite-derived land cover and census-derived socioeconomic variables in Accra, Ghana to determine whether the relationship between these variables is altered with a change in spatial resolution or scale finds that SMA productsderived from ASTER are a sufficient substitute for classification products derived from higher spatial resolution QB data when using land cover fractions as a proxy for slum presence. Expand
Integration of Remote Sensing and GIS to Detect Pockets of Urban Poverty: The Case of Rosario, Argentina
This paper incorporates analysis of Canadian RADARSAT-1 and American Landsat TM satellite imagery and ground-based GIS data to identify known pockets of urban poverty and suggests that the approach used is reasonable and that, with future refinement, it offers planners and decision makers a timely and cost effective means to locate and monitor poverty pockets in urban areas. Expand
Slums from Space - 15 Years of Slum Mapping Using Remote Sensing
Establishing a more systematic relationship between higher-level image elements and slum characteristics is essential to train algorithms able to analyze variations in slum morphologies to facilitate global slum monitoring. Expand
Object‐based classification of residential land use within Accra, Ghana based on QuickBird satellite data
A segmentation and hierarchical classification approach applied to QuickBird multispectral satellite data was implemented, with the goal of delineating residential land use polygons and identifyingExpand
Remote sensing-based measurement of Living Environment Deprivation: Improving classical approaches with machine learning
Evidence on the usefulness of very high spatial resolution (VHR) imagery in gathering socioeconomic information in urban settlements is provided and the potential of the Gradient Boost Regressor and Random Forests to improve predictive performance and accuracy is explored. Expand
Combining satellite imagery and machine learning to predict poverty
This work shows how a convolutional neural network can be trained to identify image features that can explain up to 75% of the variation in local-level economic outcomes, and could transform efforts to track and target poverty in developing countries. Expand
A review of regional science applications of satellite remote sensing in urban settings
The potential applications of satellite remote sensing to regional science research in urban settings are reviewed, finding the detection of urban deprivation hot spots, quality of life index assessment, urban growth analysis, house value estimation, urban population estimation and urban social vulnerability assessment. Expand
Deep Residual Learning for Image Recognition
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. Expand
A Coefficient of Agreement for Nominal Scales
CONSIDER Table 1. It represents in its formal characteristics a situation which arises in the clinical-social-personality areas of psychology, where it frequently occurs that the only useful level ofExpand
A 'missing' family of classical orthogonal polynomials
We study a family of 'classical' orthogonal polynomials which satisfy (apart from a three-term recurrence relation) an eigenvalue problem with a differential operator of Dunkl type. These polynomialsExpand