Lightweight and Robust Representation of Economic Scales from Satellite Imagery
This work addresses the challenge of estimating district-level economic scales, particularly for developing countries where such data is often unavailable, by leveraging satellite imagery.
The authors tackled the problem of extracting meaningful information about human habitation patterns and economic scales from high-resolution satellite imagery, presenting READ, a deep learning approach that outperforms state-of-the-art methods in predicting economic scales like population density in South Korea with an R^2 of 0.9617.
Satellite imagery has long been an attractive data source that provides a wealth of information on human-inhabited areas. While super resolution satellite images are rapidly becoming available, little study has focused on how to extract meaningful information about human habitation patterns and economic scales from such data. We present READ, a new approach for obtaining essential spatial representation for any given district from high-resolution satellite imagery based on deep neural networks. Our method combines transfer learning and embedded statistics to efficiently learn critical spatial characteristics of arbitrary size areas and represent them into a fixed-length vector with minimal information loss. Even with a small set of labels, READ can distinguish subtle differences between rural and urban areas and infer the degree of urbanization. An extensive evaluation demonstrates the model outperforms the state-of-the-art in predicting economic scales, such as population density for South Korea (R^2=0.9617), and shows a high potential use for developing countries where district-level economic scales are not known.