Urban poverty maps: From characterising deprivation using geo-spatial data to capturing deprivation from space

Eqi Luo, M. Kuffer*, Jiong Wang

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

15 Downloads (Pure)

Abstract

Most earth observation (EO) approaches only yield a binary delineation of deprived/non-deprived areas – an oversimplified characterisation with little information inferred regarding the diversity of intra-urban deprivation. In this study, we attempt to explore the potential of using VHR EO-based data to predict the degrees of intra-urban deprivation in Nairobi, Kenya. This involves a two-step workflow of characterising and predicting a continuous index of deprivation degrees. First, a principal component analysis (PCA) is conducted to characterise the multi-dimensionality of deprivation using open geospatial datasets as a set of continuous indices. Next, a convolution neural network (CNN) based regression model is trained to directly predict the deprivation indices using SPOT-7 images. The best prediction of the proposed CNN regression model is obtained in the morphology-based domain, with an R2 of 0.6543. We demonstrate the potential of an EO-based method to directly capture the degrees of morphological deprivation with relatively high accuracy, while also acknowledging its limitations in predicting the complexity of deprivation.

Original languageEnglish
Article number104033
Number of pages17
JournalSustainable Cities and Society
Volume84
Early online date1 Jul 2022
DOIs
Publication statusPublished - Sep 2022

Keywords

  • Deep learning
  • Deprivation
  • Earth observation
  • Low- to middle-income countries
  • Slums
  • UT-Hybrid-D
  • ITC-ISI-JOURNAL-ARTICLE
  • ITC-HYBRID

Fingerprint

Dive into the research topics of 'Urban poverty maps: From characterising deprivation using geo-spatial data to capturing deprivation from space'. Together they form a unique fingerprint.

Cite this