Modeled probability of congestion for selected cities

Modeled traffic jam probability for selected cities based on Twitter and OpenStreetMap data based on grid cells in 100 meters resolution. The dataset includes the cities of Barcelona, Berlin, Cincinnati, Kiev, London, Madrid, Nairobi, New York City, San Francisco, Sao Paulo and Seattle. The range of values ranges from 0 (probably normal traffic flow) to 1 (high probability of delaying the reverse flow). Methodology: Based on Twitter and OpenStreetMap (OSM) data, machine learning has been used to train a model that predicts the probability of congestion within cities. As reference data, publicly provided data from UBER was used (https://movement.uber.com). As indicators in the model, the number of tweets and the number of points-of-interest from OSM near roads 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.