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

TL;DR

This paper presents a satellite imagery-based method to identify and monitor rural markets in low-income countries, providing high-frequency insights into their activity and seasonal patterns without ground data.

Contribution

The study introduces a novel automated approach to detect and track rural markets using satellite imagery, applicable across various regions with no ground data needed.

Findings

Successfully detected markets with high sensitivity and specificity

Mapped 1,776 markets in Ethiopia and tracked weekly activity from 2017 to 2024

Observed seasonal patterns and responses to weather and conflict shocks

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. Knowing these markets' whereabouts and activity over time could provide insights in otherwise data-scarce environments, helping researchers and policymakers to better understand poor rural economies. But these markets are by nature informal and scattered widely across often-remote regions. As a result, data on this fundamental institution are sparse and inconsistent. We develop, test, and apply a method to fill this gap, leveraging market activity's unique temporal and visual signature in satellite imagery. Using secondary data from Kenya, Malawi, and Mozambique, we first confirm that we detect markets with high sensitivity and specificity. We then derive a map of 1,776 markets in Ethiopia and track their activity at up-to-weekly frequency between 2017 and 2024. Measured market activity exhibits seasonal patterns following local agricultural calendars and responds to weather and conflict shocks. Our approach is applicable wherever satellites can regularly acquire images of rural periodic markets and requires no ground data. Once markets are mapped, our approach can be fully automated to produce an up-to-weekly measure of economic conditions in areas where such data is otherwise generally not available.