A bus rapid transit (BRT) system began operation in Jakarta City, Indonesia, in January 2004 and led to a modal shift from private to public modes of transport. This modal shift from car and motorcycle to BRT reduced the emission intensity of primary pollutants, such as NO x and CO. We applied a combined structural equation model and an artificial neural network to evaluate the impact of the BRT system on the concentration of secondary pollutants in the roadside areas in the BRT corridors. An empirical analysis was carried out using data collected at five continuous ambient air quality monitoring stations located near to the BRT TransJakarta corridors in 2005. The establishment of our structural equation model gives a better understanding of the cause-effect relationship among the factors influencing roadside ambient air pollution, and was useful in simplifying the complexity of our artificial neural network model for predicting the modal shift's impact on the PM 10 values and concentration of O 3 . The introduction of the BRT system, and the modal shift it produced, had a greater influence on rapidly decaying pollutants, such as PM 10 , than on O 3 because of the exposure to near-source microenvironments, such as the roadside of the TransJakarta corridors.