Modelled road-level traffic speed for 11 cities

Modeled hourly traffic speed (km/h) at road level on an average day based on Twitter, OpenStreetMap and Uber Movement data. The dataset includes the cities of Barcelona, Berlin, Cincinnati, Kiev, London, Madrid, Nairobi, New York City, San Francisco, Sao Paulo and Seattle. Methodology: Based on Twitter and OpenStreetMap (OSM) data, machine learning has been used to train several models that predict traffic speed within cities. As reference data, publicly provided data from UBER was used (https://movement.uber.com). As indicators in the model, the OSM tags ‘highway’ and ‘maxspeed’, the hour of the day and the number of tweets near the respective road were used. In addition, car journeys using the openroute service based on the spatial distribution of the population and relevant POIs were simulated and taken into account in the model. Data from Uber Movement, (c) 2022 Uber Technologies, Inc., (https://movement.uber.com), OpenStreetMap (ohsome API and Geofabrik) and Twitter API (https://developer.twitter.com/en/docs/twitter-api) were used for modeling traffic speeds.