Application of commercial remote sensing to issues in human geography

Characterizing attributes of a society is fundamental to human geography. Cultural, social, and economic factors that are critical to understanding societal attitudes are associated with specific phenomena that are observable from overhead imagery. The application of remote sensing to specific issues, such as population estimation, agricultural analysis, and environmental monitoring, has shown great promise. Extending these concepts, we explore the potential for assessing aspects of governance, well-being, and social capital. Social science theory indicates the relationships among physical structures, institutional features, and social structures. Motivated by this underlying theory, we explore the relationship between observable physical phenomena and attributes of the society. Using imagery data from two study regions: sub-Saharan Africa and rural Afghanistan, we present an initial 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 machine learning methods. Our comparison of results for the two regions demonstrates the degree to which methods can generalize or must be tailored to a specific study area.