Using satellite imagery to map rural marketplaces and monitor their activity at high frequency.

Abstract

In many rural areas of low- and middle-income countries, weekly gatherings of buyers and sellers are the most tangible manifestation of the market economy. Identifying and tracking these markets could provide insights into economic activity in data-scarce settings. However, because these markets are informal and dispersed across often-remote regions, systematic data are sparse. We develop, test, and apply a method that leverages distinctive temporal patterns in satellite imagery to detect periodic markets. Using secondary data from Kenya, Malawi, and Mozambique, we first confirm that we detect markets with high sensitivity and specificity. We then map 1,776 markets in Ethiopia and track their activity at up-to-weekly frequency between 2017 and 2024. Market activity follows seasonal agricultural cycles and responds to weather and conflict shocks. Once locations are identified, the method can be automated to track market activity at high frequency, allowing detection of changing conditions where other high-frequency data are limited.