Citation

Zhou Q, Liu Z, Huang Z. Sci. Data 2024; 11(1): e331.

Copyright

(Copyright © 2024, Nature Publishing Group)

DOI

10.1038/s41597-024-03158-7

PMID

38570520

Abstract

Identifying road surface types (paved or unpaved) can ensure road vehicle safety, reduce energy consumption, and promote economic development. Existing studies identified road surface types by using sensors mounted on mobile devices and high-resolution satellite images that are not openly accessible, which makes it difficult to apply them to large-scale (e.g., national or regional) study areas. Addressing this issue, this study developed a dataset of road surface types (paved and unpaved) for the national road network of Kenya, containing 1,267,818 road segments classified as paved or unpaved. To accomplish this, this study proposes a method that integrates crowdsourced geographic data (OpenStreetMap) and Google satellite imagery to identify road surface types. The accuracy, recall, and F1 score of the method were all above 0.94, validating the effectiveness of the method. The data sources of the method are freely available, and the method may be applied to other countries and regions. The dataset developed based on the method can provide data support and decision support for local governments to improve road infrastructure.

Language: en