Lightweight and Robust Representation of Economic Scales from Satellite Imagery

  • Sungwon Han Korea Advanced Institute of Science and Technology and Institute for Basic Science
  • Donghyun Ahn Korea Advanced Institute of Science and Technology and Institute for Basic Science
  • Hyunji Cha Korea Advanced Institute of Science and Technology and Institute for Basic Science
  • Jeasurk Yang Seoul National University and Institute for Basic Science
  • Sungwon Park Korea Advanced Institute of Science and Technology and Institute for Basic Science
  • Meeyoung Cha Institute for Basic Science and Korea Advanced Institute of Science and Technology

Abstract

Satellite imagery has long been an attractive data source providing a wealth of information regarding human-inhabited areas. While high-resolution satellite images are rapidly becoming available, limited studies have focused on how to extract meaningful information regarding 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 the critical spatial characteristics of arbitrary size areas and represent such characteristics in 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 that the model outperforms state-of-the-art models in predicting economic scales, such as the population density in South Korea (R2=0.9617), and shows a high use potential in developing countries where district-level economic scales are unknown.

Published
2020-04-03
Section
AAAI Special Technical Track: AI for Social Impact