Exploiting deep learning and volunteered geographic information for mapping buildings in Kano, Nigeria

• Published in: Scientific data 2018-10, Vol.5 (1), p.180217-180217, Article 180217
• Main Authors: Yuan, Jiangye, Roy Chowdhury, Pranab K., McKee, Jacob, Yang, Hsiuhan Lexie, Weaver, Jeanette, Bhaduri, Budhendra
• Format: Article
• Language: English
• Subjects: 706/134; 706/2808; 706/648/697/129; Data Descriptor; Developing countries; Developing world; GENERAL AND MISCELLANEOUS; Geography; Humanities and Social Sciences; LDCs; Mapping; multidisciplinary; Neural networks; Science
• ISSN: 2052-4463; 2052-4463
• DOI: 10.1038/sdata.2018.217

Buildings in the developing world are inadequately mapped. Lack of such critical geospatial data adds unnecessary challenges to locating and reaching a large segment of the world’s most vulnerable population, impeding sustainability goals ranging from disaster relief to poverty reduction. Use of volunteered geographic information (VGI) has emerged as a widely accepted source to fill such voids. Despite its promise, availability of building maps for developing countries significantly lags behind demand. We present a new approach, coupling deep convolutional neural networks (CNNs) with VGI for automating building map generation from high-resolution satellite images for Kano state, Nigeria. Specifically, we trained a CNN with VGI building outlines of limited quality and quantity and generated building maps for a 50,000 km 2 area. Resulting maps are in strong agreement with existing settlement maps and require a fraction of the manual input needed for the latter. The VGI-based maps will provide support across multiple facets of socioeconomic development in Kano state, and demonstrates potential advancements in current mapping capabilities in resource constrained countries. Design Type(s) process-based data analysis objective • modeling and simulation objective Measurement Type(s) geographic location Technology Type(s) Neural networks models Factor Type(s) Sample Characteristic(s) Kano State • Yaounde • anthropogenic environment Machine-accessible metadata file describing the reported data (ISA-Tab format)