Remote Sensing to Analyze Wealth, Poverty, and Crime

understanding of economic, social, and cultural characteristics of a society is critical to effective government policy and successful commercial undertakings. Obtaining this information, however, often requires direct interactions with the local populace through surveys or other costly methods. We...

Full description

Saved in:
Bibliographic Details
Main Authors: Irvine, John M., Wood, Richard J., McBee, Payden
Format: Conference Proceeding
Language:English
Subjects:
Biological system modeling
Computational modeling
Economics
Feature extraction
Predictive models
Remote sensing
Satellites
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:understanding of economic, social, and cultural characteristics of a society is critical to effective government policy and successful commercial undertakings. Obtaining this information, however, often requires direct interactions with the local populace through surveys or other costly methods. We address this challenge by combining automated processing of satellite imagery with advanced modeling techniques. We have developed methods for inferring measures of wellbeing and perceptions of crime from commercial satellite imagery. Through analysis of commercial satellite imagery and coincident survey data, previous research has demonstrated models for rural afghanistan and selected countries in sub-saharan africa. The findings show the potential for predicting peoples' attitudes about the a variety of social, economic, and political issues, based only on the imagery-derived information. This paper extends the previous research, focusing on wealth, poverty, and crime. We present models to predict indicators and quantify model performance through cross-validation. The paper concludes with recommendations for future exploration.
ISSN:2332-5615
DOI:10.1109/AIPR.2017.8457971