Deriving economic and social indicators from imagery

Abstract

The application of remote sensing to the social sciences is an emerging research area. People's behavior and values shape the environment in which they live. Similarly, values and behaviors are influenced by the environment. This study explores the relationship between features observable in overhead imagery and direct measurements of attitudes obtained through surveys. We focus on three topic areas:• Income and Economic Development • Centrality and Decision Authority • Social CapitalUsing commercial satellite imagery data from rural Afghanistan, we present an exploration of the direct and indirect indicators derived from the imagery. We demonstrate a methodology for extracting relevant measures from the imagery, using a combination of human-guided and automated methods. These imagery observables indicate characteristics of the villages which will be compared to survey data in future modeling work. Preliminary survey modeling, based on data from sub-Saharan Africa, suggests that modeling of the Afghan data will also demonstrate a relationship between remote sensing data and survey-based measures of economic and social phenomena. We conclude with a discussion of the next steps, which include extensions to new regions of the world.

Combining remote sensing and social media data to predict indicators of political and economic instability

“…Modern satellite imagery provides a potential avenue for abstracting socio-economic context at scale. Satellite images contain infrastructural and agricultural information that, in a previous study focused on Afghanistan and Botswana [1] [2] were shown to be useful for abstracting regional socio-economic information. Survey responses about wealth, governance, social capital, and crime were predicted with supervised machine learning models via their image features, which were derived from their spatially coincident satellite images.…”

“…We derive the context information from commercial imagery, which is globally accessible. Previous research has demonstrated the connection between machine-recognizable imagery features and local socio-economic descriptors for selected regions [1] [2] [3]. Previous machine learning models have demonstrated predictions of conditions in Afghanistan, Botswana, Brazil, Kenya, Nigeria, Venezuela, and Zimbabwe.…”