Universität zu Köln

Kramm, Tanja ORCID: 0000-0003-2684-7157, Nyamari, Nicodemus ORCID: 0000-0002-4018-8322, Moseti, Vincent, Klee, Annika, Vehlken, Leon ORCID: 0009-0009-1227-9516, Anderson, David M., Bogner, Christina ORCID: 0000-0003-4495-0676 and Bareth, Georg ORCID: 0000-0003-3692-8655 (2025). Deep learning-based extraction of Kenya’s historical road network from topographic maps. Scientific Data, 12 (1). pp. 1-14. Springer Nature. ISSN 2052-4463

PDF s41597-025-05442-6.pdf Bereitstellung unter der CC-Lizenz: Creative Commons Attribution. Download (3MB)

Abstract

[Artikel-Nr.: 1149] Kenya’s road network significantly influences environmental and socio-economic dynamics. High-quality road data is essential for analyzing its impact on various factors, including land-use, biodiversity, migration, livelihoods, and economy. Like many countries, Kenya faces challenges in the availability of accurate and detailed digital historical road datasets. To address this, we used deep learning techniques to extract Kenya’s road network from 533 historical topographic maps (1:50,000 and 1:100,000 scale) covering the 1950s–1980s. This involved digitizing, georeferencing, and classifying of 20 different road symbols on all maps, then converting and merging them into a seamless dataset. The statistical evaluation was conducted against manually created roads from seven representative map sheets by calculating precision, recall, and F1 score. Our study provides a detailed historical road dataset for Kenya containing over 56,000 km of historical roads. The statistical validation showed an average F1 score of 0.84, indicating a high classification performance. The methodology offers an applicable approach for national-level historic road network mapping, also transferable to other regions, map types or features.

Item Type:	Article
Creators:	Creators Email ORCID ORCID Put Code Kramm, Tanja UNSPECIFIED https://orcid.org/0000-0003-2684-7157 UNSPECIFIED Nyamari, Nicodemus UNSPECIFIED https://orcid.org/0000-0002-4018-8322 UNSPECIFIED Moseti, Vincent UNSPECIFIED UNSPECIFIED UNSPECIFIED Klee, Annika UNSPECIFIED UNSPECIFIED UNSPECIFIED Vehlken, Leon UNSPECIFIED https://orcid.org/0009-0009-1227-9516 UNSPECIFIED Anderson, David M. UNSPECIFIED UNSPECIFIED UNSPECIFIED Bogner, Christina UNSPECIFIED https://orcid.org/0000-0003-4495-0676 UNSPECIFIED Bareth, Georg UNSPECIFIED https://orcid.org/0000-0003-3692-8655 UNSPECIFIED
URN:	urn:nbn:de:hbz:38-809393
Identification Number:	10.1038/s41597-025-05442-6
Journal or Publication Title:	Scientific Data
Volume:	12
Number:	1
Page Range:	pp. 1-14
Number of Pages:	14
Date:	5 July 2025
Publisher:	Springer Nature
ISSN:	2052-4463
Language:	English
Faculty:	Faculty of Mathematics and Natural Sciences
Divisions:	Global South Studies Center Faculty of Mathematics and Natural Sciences > Department of Geosciences > Geographisches Institut
Subjects:	Earth sciences Geography and travel
['eprint_fieldname_oa_funders' not defined]:	Publikationsfonds UzK
Refereed:	Yes
URI:	http://kups.ub.uni-koeln.de/id/eprint/80939