Paper details

Paper authors	Bo Percival
In panel on	Towards responsible use of AI and geospatial data in preparedness and response to natural hazards and complex emergencies
Paper presenter(s) will be presenting	In-Person / Online

Abstract

In 2020/21, the Humanitarian OpenStreetMap team undertook a study to understand both the acceptability and effectiveness of AI-assisted open mapping, specifically focused on the digitization of building features derived from satellite imagery for use in OpenStreetMap(OSM). The purpose of this study was to empirically explore the value and application of AI/ML and better understand how it can amplify and augment the efforts of local mapping for disaster preparedness or in response to emergencies. Findings from this study suggest AI has significant potential to both the speed and quality of feature digitization for OSM potential, however, also comes with potential downside potential if implemented irresponsibly.

Back