Mapping racial diversity with satellite data

Tomasz Stepinski describes himself as a “physicist, astrophysicist, planetary scientists, and mathematician”. After spending years in Houston creating computer models to automatically map craters and valleys on Mars for NASA, he was offered the unusual position of Chair of Space Exploration in the Geography Department at the University of Cincinnati. Not finding many space-enthusiasts among colleagues, he started looking downwards and found ways to apply his previous experience with spatial analysis and automatic mapping of remote sensing data to more earthly matters. His latest research project, for example, aims at providing a new view of the diversity of US neighborhoods, a previously neglected topic.

Screenshot of the diversity map created by Stepinski

Currently, while Census data is collected at the household level by the US government, it is rendered in aggregated blocks for privacy reasons. Additionally, the block lines might fluctuate between surveys, making it almost impossible for end-users without a significant prior knowledge in GIS to easily compare data and find long-term patterns.

Using LandSat-8 satellite data, land cover data sets, dasymetric modeling, and a specifically designed statistical model that only places people in populated areas, professor Stepinski and his team were able to algorithmically layer the Census data onto a map of the United States with unprecedented accuracy, all the way to the street level. This new view will help even non-technical users track changes “from year to year, and pixel to pixel because the grid doesn’t change”. Currently, the map can display data from 1990, 2000, and 2010, however professor Stepinski plans to add new 2020 data as soon as it is made publicly available.

While waiting for the data, professor Stepinski is currently working on a model to predict changes in the composition of the diversity landscape in the United States. Having a functional model on population migration patterns would be a great asset for many industries and government functions, ranging from city planning, urban development, disaster prevention, or even retail and commerce looking into new places to open stores.

Mapping racial diversity with satellite data
linkedin facebook pinterest youtube rss twitter instagram facebook-blank rss-blank linkedin-blank pinterest youtube twitter instagram