TRAFFIC SPEED MODELLING TO IMPROVE TRAVEL TIME ESTIMATION IN OPENROUTESERVICE

Abstract. Time-dependent traffic speed information at a street level is important for routing services to estimate accurate travel times and recommend routes which avoid congestion. Still, most open-source machines that use OpenStreetMap (OSM) as the primary data source rely on static driving speeds derived from OSM tags, since comprehensive not openly available. In this study, method was developed model by hour of day using open OpenStreetMap, Twitter population data. The modelled subsequently integrated into engine openrouteservice improve time estimation in route planning. Machine learning models were trained ten cities worldwide Uber Movement reference Different indicators based geolocation timestamp well geographically adapted betweeness centrality indicator evaluated their potential prediction accuracy. all cities, improved model, although effect only visible certain road types. but lesser extent. Google Routing API used evaluate accuracy estimation. Deviations regionally different partly alleviated including raw or openrouteservice.