Granularity at Scale: Estimating Neighborhood Socioeconomic Indicators From High-Resolution Orthographic Imagery and Hybrid Learning

Many areas of the world are without basic information on the socioeconomic well-being of the residing population due to limitations in existing data collection methods. Overhead images obtained remotely, such as from satellite or aircraft, can help serve as windows into the state of life on the grou...

Full description

Saved in:
Bibliographic Details
Main Authors: Ethan Brewer, Giovani Valdrighi, Parikshit Solunke, Joao Rulff, Yurii Piadyk, Zhonghui Lv, Jorge Poco, Claudio Silva
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10443032/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850041075416170496
author Ethan Brewer
Giovani Valdrighi
Parikshit Solunke
Joao Rulff
Yurii Piadyk
Zhonghui Lv
Jorge Poco
Claudio Silva
author_facet Ethan Brewer
Giovani Valdrighi
Parikshit Solunke
Joao Rulff
Yurii Piadyk
Zhonghui Lv
Jorge Poco
Claudio Silva
author_sort Ethan Brewer
collection DOAJ
description Many areas of the world are without basic information on the socioeconomic well-being of the residing population due to limitations in existing data collection methods. Overhead images obtained remotely, such as from satellite or aircraft, can help serve as windows into the state of life on the ground and help &#x201C;fill in the gaps&#x201D; where community information is sparse, with estimates at smaller geographic scales requiring higher resolution sensors. Concurrent with improved sensor resolutions, recent advancements in machine learning and computer vision have made it possible to quickly extract features from and detect patterns in image data, in the process correlating these features with other information. In this work, we explore how well two approaches&#x2014;a supervised convolutional neural network and semisupervised clustering based on bag-of-visual-words&#x2014;estimate population density, median household income, and educational attainment of individual neighborhoods from publicly available high-resolution imagery of cities throughout the United States. Results and analyses indicate that features extracted from the imagery can accurately estimate the density (<italic>R</italic><inline-formula><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> up to 0.81) of neighborhoods, with the supervised approach able to explain about half the variation in a population&#x0027;s income and education. In addition to the presented approaches serving as a basis for further geographic generalization, the novel semisupervised approach provides a foundation for future work seeking to estimate fine-scale information from aerial imagery without the need for label data.
format Article
id doaj-art-cb1e829b75bb462caa9c9400c75f8c84
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-cb1e829b75bb462caa9c9400c75f8c842025-08-20T02:55:53ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-01175668567910.1109/JSTARS.2024.336801810443032Granularity at Scale: Estimating Neighborhood Socioeconomic Indicators From High-Resolution Orthographic Imagery and Hybrid LearningEthan Brewer0https://orcid.org/0000-0002-4367-0763Giovani Valdrighi1https://orcid.org/0000-0003-0106-4789Parikshit Solunke2https://orcid.org/0009-0003-5546-0135Joao Rulff3https://orcid.org/0000-0003-3341-7059Yurii Piadyk4https://orcid.org/0000-0002-2975-635XZhonghui Lv5https://orcid.org/0000-0001-5186-3699Jorge Poco6https://orcid.org/0000-0001-9096-6287Claudio Silva7https://orcid.org/0000-0003-2452-2295Spectral Sciences, Inc., Burlington, USAFunda&#x00E7;&#x00E3;o Getulio Vargas, Rio de Janeiro, BrazilNew York University, New York, USANew York University, New York, USANew York University, New York, USAWilliam and Mary, Williamsburg, USAFunda&#x00E7;&#x00E3;o Getulio Vargas, Rio de Janeiro, BrazilNew York University, New York, USAMany areas of the world are without basic information on the socioeconomic well-being of the residing population due to limitations in existing data collection methods. Overhead images obtained remotely, such as from satellite or aircraft, can help serve as windows into the state of life on the ground and help &#x201C;fill in the gaps&#x201D; where community information is sparse, with estimates at smaller geographic scales requiring higher resolution sensors. Concurrent with improved sensor resolutions, recent advancements in machine learning and computer vision have made it possible to quickly extract features from and detect patterns in image data, in the process correlating these features with other information. In this work, we explore how well two approaches&#x2014;a supervised convolutional neural network and semisupervised clustering based on bag-of-visual-words&#x2014;estimate population density, median household income, and educational attainment of individual neighborhoods from publicly available high-resolution imagery of cities throughout the United States. Results and analyses indicate that features extracted from the imagery can accurately estimate the density (<italic>R</italic><inline-formula><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> up to 0.81) of neighborhoods, with the supervised approach able to explain about half the variation in a population&#x0027;s income and education. In addition to the presented approaches serving as a basis for further geographic generalization, the novel semisupervised approach provides a foundation for future work seeking to estimate fine-scale information from aerial imagery without the need for label data.https://ieeexplore.ieee.org/document/10443032/Aerial imagerycomputer visiondeep learningremote sensingsustainable development
spellingShingle Ethan Brewer
Giovani Valdrighi
Parikshit Solunke
Joao Rulff
Yurii Piadyk
Zhonghui Lv
Jorge Poco
Claudio Silva
Granularity at Scale: Estimating Neighborhood Socioeconomic Indicators From High-Resolution Orthographic Imagery and Hybrid Learning
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Aerial imagery
computer vision
deep learning
remote sensing
sustainable development
title Granularity at Scale: Estimating Neighborhood Socioeconomic Indicators From High-Resolution Orthographic Imagery and Hybrid Learning
title_full Granularity at Scale: Estimating Neighborhood Socioeconomic Indicators From High-Resolution Orthographic Imagery and Hybrid Learning
title_fullStr Granularity at Scale: Estimating Neighborhood Socioeconomic Indicators From High-Resolution Orthographic Imagery and Hybrid Learning
title_full_unstemmed Granularity at Scale: Estimating Neighborhood Socioeconomic Indicators From High-Resolution Orthographic Imagery and Hybrid Learning
title_short Granularity at Scale: Estimating Neighborhood Socioeconomic Indicators From High-Resolution Orthographic Imagery and Hybrid Learning
title_sort granularity at scale estimating neighborhood socioeconomic indicators from high resolution orthographic imagery and hybrid learning
topic Aerial imagery
computer vision
deep learning
remote sensing
sustainable development
url https://ieeexplore.ieee.org/document/10443032/
work_keys_str_mv AT ethanbrewer granularityatscaleestimatingneighborhoodsocioeconomicindicatorsfromhighresolutionorthographicimageryandhybridlearning
AT giovanivaldrighi granularityatscaleestimatingneighborhoodsocioeconomicindicatorsfromhighresolutionorthographicimageryandhybridlearning
AT parikshitsolunke granularityatscaleestimatingneighborhoodsocioeconomicindicatorsfromhighresolutionorthographicimageryandhybridlearning
AT joaorulff granularityatscaleestimatingneighborhoodsocioeconomicindicatorsfromhighresolutionorthographicimageryandhybridlearning
AT yuriipiadyk granularityatscaleestimatingneighborhoodsocioeconomicindicatorsfromhighresolutionorthographicimageryandhybridlearning
AT zhonghuilv granularityatscaleestimatingneighborhoodsocioeconomicindicatorsfromhighresolutionorthographicimageryandhybridlearning
AT jorgepoco granularityatscaleestimatingneighborhoodsocioeconomicindicatorsfromhighresolutionorthographicimageryandhybridlearning
AT claudiosilva granularityatscaleestimatingneighborhoodsocioeconomicindicatorsfromhighresolutionorthographicimageryandhybridlearning