An empirical validation of network learning with taxi GPS data from Wuhan, China

In prior research, a statistically cheap method was developed to monitor transportation network performance by using only a few groups of agents without having to forecast the population flows. The current study validates this multiagent inverse optimization (MAIO) method using taxi GPS trajectory data from the city of Wuhan, China. Using a controlled 2,062-link network environment and different GPS data processing algorithms, an online monitoring environment was simulated using real data over a 4-h period. Results show that using samples from only one origin-destination (OD) pair, the MAIO method can learn network parameters such that forecasted travel times have a 0.23 correlation with the observed travel times. By increasing the monitoring from just two OD pairs, the correlation improved further, to 0.56.