Efficient Poverty Mapping using Deep Reinforcement Learning
This addresses the cost barrier for scaling high-resolution-based sustainability applications, though it is incremental as it builds on prior object detection methods.
The paper tackles the high cost of acquiring high-resolution satellite imagery for poverty prediction by proposing a reinforcement learning method that uses free low-resolution imagery to guide selective acquisition, achieving better performance on poverty prediction in Uganda while using 80% fewer high-resolution images.
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. Our approach could have application in many sustainability domains that require high-resolution imagery.