The project developed an urban traffic system (UTS) to address the human and vehicle traffic challenges in Riyadh. It contained both short-term and long-term components. For the short-term, it attempted to investigate and improve the performance of the current road network by using traffic models that account for detailed driver behavior and vehicle technology models. The long-term approach addressed future development patterns across the Riyadh region, the added burden they will place on the road networks, and the major infrastructure improvements they will require.

The tools employed include macro and micro models relying on data including mobile phone usage information and traffic flow/volume figures. By combining information on usage patterns, traffic congestion, and urban development, the project followed an integrated approach to addressing the challenges of local traffic management. The macro model, is comprised of 3 components: the human mobility model, the vehicle flow model, and the planning model.

The human mobility model incorporates mobile phone spatial-temporal data, thereby mapping the locations of users within the city at a given time of day. It is thus a two-dimensional map with an additional time dimension to show the movement of people throughout the day.

The flow model captures the road network and is concerned with linear flows as opposed to the spatial construct of the human mobility model that utilizes a general area map of the city.

The planning model, on the other hand, is the long-term component of the project. It involves anticipating and forecasting changes in population, economic factors pertaining to transportation development, and how existing and planned infrastructure can cope. The 3 components constitute the macro models of UTS.

The purpose of the micro model is to zoom into areas where the macro model identifies traffic problems, understand how individual vehicle interactions lead to such problems and suggest solutions for alleviating the traffic pressures. The micro model yielded detailed link specific metrics, such as energy consumption and emission patterns. It was then embedded within an optimization framework, and used to identify novel mobility strategies that improved the reliability, robustness, efficiency and sustainability of the network.