Transportation forecasting

[1] Traffic forecasts are used for several key purposes in transportation policy, planning, and engineering: to calculate the capacity of infrastructure, e.g., how many lanes a bridge should have; to estimate the financial and social viability of projects, e.g., using cost–benefit analysis and social impact assessment; and to calculate environmental impacts, e.g., air pollution and noise.

Although their obvious advantages for environmental purposes were recognized by Shiftan almost a decade ago,[3] applications to exposure models remain scarce.

[9] Policy makers can use activity-based models to devise strategies that reduce exposure by changing time activity patterns or that target specific groups in the population.

This will lead to more accurate predictions, enhanced ability to control traffic for customized prioritization of particular drivers, but also to ethical concerns as local and national governments use more data about identifiable individuals.

While the integration of such partially personal data is tempting, there are considerable privacy concerns over the possibilities, related to the criticisms of mass surveillance.

In the early days, in the USA, census data was augmented that with data collection methods that had been developed by the Bureau of Public Roads (a predecessor of the Federal Highway Administration): traffic counting procedures, cordon "where are you coming from and where are you going" counts, and home interview techniques.

The main difference between now and then is the development of some analytic resources specific to transportation planning, in addition to the BPR data acquisition techniques used in the early days.

In the 1990s, most federal investment in model research went to the Transims project at Los Alamos National Laboratory, developed by physicists.

[14][15] A 2009 Government Accountability Office report noted that federal review of transportation modeling focused more on process requirements (for example, did the public have adequate opportunity to comment?)

than on transportation outcomes (such as reducing travel times, or keeping pollutant or greenhouse gas emissions within national standards).