Monte Carlo simulation is a numerical analysis technique that uses repeated random sampling to obtain the distribution of an unknown probabilistic entity. It provides a powerful computational framework for spatial analysis, and has become increasingly popular with rising computing power. Some applications include data disaggregation, designing a statistical significance test, and detecting spatial patterns.
This chapter demonstrates the Monte Carlo technique in a case study of simulating urban traffic flows. The commonly known Urban Transportation Modeling System (UTMS) or Urban Transportation Planning System (UTPS) typically uses the four-step travel demand model, composed of trip generation, trip distribution, mode choice, and trip assignment. Each step requires significant efforts in data collection, model calibration, and validation. Even with advanced transportation modeling packages, implementation of the whole process is often arduous or infeasible. A prototype program of traffic simulation modules for education (TSME) is developed to simulate traffic with data that are widely accessible such as the Census Transportation Planning Package (CTPP) and TIGER files from the Census. Speficically, the Monte Carlo method is used in two critical steps of the program: one on disaggregating area-based residential and employment data to individual trip origins (O) and destinations (D), and another on forming realistic O-D pairs. Validation of the model compares simulated traffic to data obtained at traffic monitoring stations from Baton Rouge, Louisiana, and the results are promising.