Measuring Human and Economic Activity from Satellite Imagery to Support City-Scale Decision-Making during COVID-19 Pandemic
Rodrigo Minetto, Mauricio Pamplona Segundo, Gilbert Rotich, Sudeep Sarkar
TLDR
This paper presents a deep learning framework using satellite imagery to automatically detect and quantify human and economic activity changes during the COVID-19 pandemic to aid city-scale decision-making.
Key contributions
- Developed an ensemble of lightweight CNNs combined with strategic location sampling for object detection in satellite images.
- Demonstrated the framework's effectiveness on benchmark datasets like the US IARPA fMoW and the xView challenge, achieving top-tier performance.
- Applied the method to analyze temporal changes in economic indicators before and after COVID-19 lockdowns, providing actionable insights for policymakers.
Why it matters
This work is important because it leverages satellite imagery and advanced deep learning to provide near real-time, scalable, and objective measurements of economic and social activity disruptions caused by the COVID-19 pandemic. Such data-driven insights can support governments and analysts in monitoring recovery progress and making informed decisions during crises when traditional data sources may be delayed or unavailable.
Original Abstract
The COVID-19 outbreak forced governments worldwide to impose lockdowns and quarantines to prevent virus transmission. As a consequence, there are disruptions in human and economic activities all over the globe. The recovery process is also expected to be rough. Economic activities impact social behaviors, which leave signatures in satellite images that can be automatically detected and classified. Satellite imagery can support the decision-making of analysts and policymakers by providing a different kind of visibility into the unfolding economic changes. In this work, we use a deep learning approach that combines strategic location sampling and an ensemble of lightweight convolutional neural networks (CNNs) to recognize specific elements in satellite images that could be used to compute economic indicators based on it, automatically. This CNN ensemble framework ranked third place in the US Department of Defense xView challenge, the most advanced benchmark for object detection in satellite images. We show the potential of our framework for temporal analysis using the US IARPA Function Map of the World (fMoW) dataset. We also show results on real examples of different sites before and after the COVID-19 outbreak to illustrate different measurable indicators. Our code and annotated high-resolution aerial scenes before and after the outbreak are available on GitHub (https://github.com/maups/covid19-satellite-analysis).
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.