Lei Zhang, Ph.D.
Director, National Transportation Center
University of Maryland
Smart mobility and transportation demand management are extremely compatible with digital modeling and computing tools, which organizations and businesses can use in a growing number of innovative ways. Dr. Lei Zhang, director of the National Transportation Center at the University of Maryland, notes a longstanding history of simulation modeling, which is benefitting from an expanded range of next-generation tools including performance-based decision-making and parallel/GPU/cloud computing.
The second major type of modeling is travel behavior modeling, which seeks to estimate how and when people travel on an individual level. Again, digital tools are emerging as a key aspect of the behavior modeling arsenal, and advanced computing platforms are also making it easier to integrate the two major types of models to create wholly new and innovative approaches to TDM issues.
Big data is also playing an increasingly prominent role. In 2016, the University of Maryland’s National Transportation Center processed an average of 8 billion records per day, related to everything from speed and travel times to accident data and parking conditions. By 2018, Zhang expects this figure to grow to about 10 trillion records per day. These records cover both individual-level and system-level information, and can be mined to create accurate broad, whole-picture insights as well as highly specific and targeted insights.
The most advanced travel and traffic modeling systems currently available are capable of generating real-time system control and optimization applications based on the collection of integrated travel behavior and dynamic traffic data. Combined with big data and cloud computing applications, which can generate faster-than-real-time insights, information can be prepared for delivery on an individual level through smartphone and/or web-based interfaces
Simply put, technology has the power to harness an incredible amount of information, which can be used to maximize traffic efficiency and communicate the quickest and most convenient route and mode options to individual users. The data-assisted optimization of traffic flow holds the potential to generate major decreases in the amount of pollution generated during both peak and off-peak travel periods.