Building Coverage Estimation with Low-resolution Remote Sensing Imagery

TL;DR

This paper introduces a novel method for estimating building coverage globally using low-resolution satellite imagery, enabling more frequent updates and broader applicability in developing regions.

Contribution

The paper presents a low-resolution imagery-based model with a multi-node quantile regression layer that improves spatial and temporal generalization for building coverage estimation.

Findings

Achieves an R^2 of 0.968 in predicting building coverage.

Generalizes well to unseen countries and continents.

Uses publicly available low-resolution satellite data.

Abstract

Building coverage statistics provide crucial insights into the urbanization, infrastructure, and poverty level of a region, facilitating efforts towards alleviating poverty, building sustainable cities, and allocating infrastructure investments and public service provision. Global mapping of buildings has been made more efficient with the incorporation of deep learning models into the pipeline. However, these models typically rely on high-resolution satellite imagery which are expensive to collect and infrequently updated. As a result, building coverage data are not updated timely especially in developing regions where the built environment is changing quickly. In this paper, we propose a method for estimating building coverage using only publicly available low-resolution satellite imagery that is more frequently updated. We show that having a multi-node quantile regression layer greatly improves the model's spatial and temporal generalization. Our model achieves a coefficient of determination ($R^2$) as high as 0.968 on predicting building coverage in regions of different levels of development around the world. We demonstrate that the proposed model accurately predicts the building coverage from raw input images and generalizes well to unseen countries and continents, suggesting the possibility of estimating global building coverage using only low-resolution remote sensing data.