A framework for global highway network change detection applied to Landsat data
Multi-temporal geospatial data measuring the evolution of transportation networks is scarce, impeding our quantitative knowledge on the dynamics of highway and other transportation networks at global scale. To tackle this issue, we developed a framework that integrates contemporary road network data with road presence probabilities extracted from historical, multispectral Landsat data (1990-2024), enabling the measurement of highway network growth from 1990 onwards. The framework also supports earlier Landsat data, other geohistorical data such as historical maps or pre Landsat aerial imagery. First experiments conducted for a study area in the United States yield promising results, achieving Area-under-the-Curve values of up to 0.88.
UHL Johannes H.;
MAFFENINI Luca;
POLITIS Panagiotis;
KRASNODEBSKA Katarzyna;
PESARESI Martino;
JAWORSKI Taylor;
KITCHENS Carl;
2026-02-27
Publications Office of the European Union
JRC145536
978-92-68-31935-2 (online),
https://publications.jrc.ec.europa.eu/repository/handle/JRC145536,
10.2760/2119408 (online),
Additional supporting files
| File name | Description | File type | |
|---|
