loading page

Estimation of socioeconomic indicators through satellite imagery - Analysis of urban areas overlapping
  • +3
  • Carlos Massao Oishi Giuzio,
  • Igor Varela Zoeller,
  • Rafael Coelho,
  • M. Jeaneth Machicao Justo,
  • Pedro Corrêa,
  • Pedro Ribeiro de Andrade Neto
Carlos Massao Oishi Giuzio
University of Sao Paulo, Universidade de São Paulo Escola Politécnica

Corresponding Author:carlosgiuzio@usp.br

Author Profile
Igor Varela Zoeller
University of Sao Paulo, Universidade de São Paulo Escola Politécnica
Author Profile
Rafael Coelho
University of Sao Paulo, Universidade de São Paulo Escola Politécnica
Author Profile
M. Jeaneth Machicao Justo
Universidade de São Paulo Escola Politécnica
Author Profile
Pedro Corrêa
Universidade de São Paulo Escola Politécnica,Escola Politécnica da Universidade de São Paulo
Author Profile
Pedro Ribeiro de Andrade Neto
Instituto Nacional de Pesquisas Espaciais
Author Profile

Abstract

The NEXUS area covers approximately 30% of the Brazilian territory. In order to assist preservation and sustainable development policies in that region, this study proposes to replicate the work done by Yeh et al in Africa , in which a convolutional neural network estimates indicators through satellite images, each covering a region of approximately 45 km². This work compares the size and distribution of Brazil’s census tracts with those in Africa to define if the scale of images can be maintained and to define the clusters that will be used. To avoid biasing the model, special care must be taken in selecting clusters, such as keeping a balance between urban and rural sectors and, most importantly, making sure that there is little to no overlap of clusters. To do so, two approaches were proposed. The first one samples tracts in each municipality as centroids for clusters, the second merges neighboring urban tracts into a single group and fits clusters to these groups.