Exploration of OpenStreetMap missing built-up areas using twitter hierarchical clustering and deep learning in Mozambique

• Verfasst von: Li, Hao [VerfasserIn]
• Verfasst von: Herfort, Benjamin [VerfasserIn]
• Verfasst von: Huang, Wei [VerfasserIn]
• Verfasst von: Zia, Mohammed [VerfasserIn]
• Verfasst von: Zipf, Alexander [VerfasserIn]
• Titel: Exploration of OpenStreetMap missing built-up areas using twitter hierarchical clustering and deep learning in Mozambique
• Verf.angabe: Hao Li, Benjamin Herfort, Wei Huang, Mohammed Zia, Alexander Zipf
• E-Jahr: 2020
• Jahr: 07 June 2020
• Umfang: 11 S.
• Fussnoten: Gesehen am 26.08.2020
• Titel Quelle: Enthalten in: International Society for Photogrammetry and Remote SensingISPRS journal of photogrammetry and remote sensing
• Ort Quelle: Amsterdam [u.a.] : Elsevier, 1989
• Jahr Quelle: 2020
• Band/Heft Quelle: 166(2020), Seite 41-51
• ISSN Quelle: 0924-2716
• DOI: doi:10.1016/j.isprsjprs.2020.05.007
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Data quality
• Sach-SW: Deep learning
• Sach-SW: Hierarchical DBSCAN
• Sach-SW: Humanitarian mapping
• Sach-SW: OpenStreetMap
• Sach-SW: Twitter
• Sach-SW: Volunteered geographical information
• K10plus-PPN: 1727815505

Abstract

Accurate and detailed geographical information digitizing human activity patterns plays an essential role in response to natural disasters. Volunteered geographical information, in particular OpenStreetMap (OSM), shows great potential in providing the knowledge of human settlements to support humanitarian aid, while the availability and quality of OSM remains a major concern. The majority of existing works in assessing OSM data quality focus on either extrinsic or intrinsic analysis, which is insufficient to fulfill the humanitarian mapping scenario to a certain degree. This paper aims to explore OSM missing built-up areas from an integrative perspective of social sensing and remote sensing. First, applying hierarchical DBSCAN clustering algorithm, the clusters of geo-tagged tweets are generated as proxies of human active regions. Then a deep learning based model fine-tuned on existing OSM data is proposed to further map the missing built-up areas. Hit by Cyclone Idai and Kenneth in 2019, the Republic of Mozambique is selected as the study area to evaluate the proposed method at a national scale. As a result, 13 OSM missing built-up areas are identified and mapped with an over 90% overall accuracy, being competitive compared to state-of-the-art products, which confirms the effectiveness of the proposed method.