Efficient Poverty Mapping from High Resolution Remote Sensing Images

Authors

  • Kumar Ayush Department of Computer Science, Stanford University
  • Burak Uzkent Department of Computer Science, Stanford University
  • Kumar Tanmay Department of Electrical Engineering, IIT Kharagpur
  • Marshall Burke Department of Earth Science, Stanford University
  • David Lobell Department of Earth Science, Stanford University
  • Stefano Ermon Department of Computer Science, Stanford University

Keywords:

Energy, Environment & Sustainability, Applications, Reinforcement Learning

Abstract

The combination of high-resolution satellite imagery and machine learning have proven useful in many sustainability-related tasks, including poverty prediction, infrastructure measurement, and forest monitoring. However, the accuracy afforded by high-resolution imagery comes at a cost, as such imagery is extremely expensive to purchase at scale. This creates a substantial hurdle to the efficient scaling and widespread adoption of high-resolution-based approaches. To reduce acquisition costs while maintaining accuracy, we propose a reinforcement learning approach in which free low-resolution imagery is used to dynamically identify where to acquire costly high-resolution images, prior to performing a deep learning task on the high-resolution images. We apply this approach to the task of poverty prediction in Uganda, building on an earlier approach that used object detection to count objects and use these counts to predict poverty. Our approach exceeds previous performance benchmarks on this task while using 80% fewer high-resolution images, and could be useful in many domains that require high-resolution imagery.

Downloads

Published

2021-05-18

How to Cite

Ayush, K., Uzkent, B., Tanmay, K., Burke, M., Lobell, D., & Ermon, S. (2021). Efficient Poverty Mapping from High Resolution Remote Sensing Images. Proceedings of the AAAI Conference on Artificial Intelligence, 35(1), 12-20. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16072

Issue

Section

AAAI Technical Track on Application Domains