Satellite Embedding-Based Population Imputation for Areas with Missing Building Footprint Data: A Computer Vision-Based Approach
Jeong, Byeonghwa, Adams, Daniel, Zimmer, Andrew et al. · 2026
Read Satellite Embedding-Based Population Imputation for Areas with Missing Building Footprint Data: A Computer Vision-Based Approach by Jeong, Byeonghwa, Adams, Daniel, Zimmer, Andrew et al. (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/doe-osti-3022921-satellite-embedding-based-population-imp.txt.
Description
Oak Ridge National Laboratory report ORNL/TM-2026/4420, by Byeonghwa Jeong, Daniel Adams, Andrew Zimmer, and Marie Urban, attacks a gap in global population mapping. The laboratory's LandScan program estimates population building by building, but footprint data are missing or sparse across much of the world, leaving those regions unmapped at fine resolution.
The proposed fix reads satellite imagery directly. Combining Google Earth Engine satellite embeddings with a UNet computer vision model, the framework imputes population on a grid without needing footprints. Applied to Taiwan as a test case, it reached an R-squared of 0.89 with a root mean square error of 18.70, beating traditional machine learning baselines. It also corrected false positives in settlement data, recognizing uninhabited places that building-based layers wrongly mark as populated.
Catalog record
| CREATOR | Jeong, Byeonghwa, Adams, Daniel, Zimmer, Andrew et al. |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| LICENSE | Public Domain |
| RIGHTS | PUBLIC DOMAIN |
| SOURCE | DOE OSTI |