Massive data, from various sources, provides unprecedented opportunity for the transportation industry to understand travel behavior and to propose efficient management strategies. However, those data sources are usually established by disparate public agencies and private sectors. They rarely communicate with each other and, as a result, data is only used and analyzed for a particular piece of a transportation system, such as an intersection, a stretch of freeway, or bus routes operated by the same agency. With disparate data sources, each part of the system is individually operated, making the entire transportation system far from socially optimal.

MAC has been collecting and integrating various multi-modal data sets around the Pittsburgh region, which include roadway traffic, probe vehicles, public transit, parking, incidents, bicycles, buildings, energy consumption, emissions, social media, etc. The data infrastructure is established on hierarchical systems, large-scale data archives and integration, statistical learning algorithms, and optimal decision making processes. Multi-modal transportation systems are analyzed integratively. The decision-making of one mode of transportation system must take into account its impact to other modes and vice versa. The data infrastructure is closely aligned to on-going research at Carnegie Mellon, including urban systems, air quality studies, climate change, connected/autonomous vehicles, energy policies, and infrastructure life cycle analysis. Interactions with those groups in other disciplines will have synergistic effects on the integration and optimization of sustainable urban systems.