Exposure Assessment of Traffic-Related Air Pollution Based on CFD and BP Neural Network and Artificial Intelligence Prediction of Optimal Route in an Urban Area

Due to rapid global economic development, the number of motor vehicles has increased sharply, causing significant traffic pollution and posing a threat people’s health. People’s exposure traffic-related particulate matter with an aerodynamic diameter less than 2.5 μm (PM2.5) primarily occurs during commuting. Many studies have used risk assessment models assess possible adverse effects PM2.5, but few them plan low-risk pathways for commuters. This study simulated pollutant concentration distribution in idealized urban area different scenarios. We then back propagation (BP) neural network predict concentration. The commuter respiratory deposition dose was calculated based on BP prediction results, converted into obstacles commuting map. Finally, rapidly exploring random tree star (RRT*) algorithm paths results indicate that pollutants discharged by cars planting can significantly affect A 30.25 μg/m3 increase resulted 7~13 air sidewalks. Combining computational fluid dynamics simulation, model, RRT* provides system work proposes artificial-intelligence-based calculating choosing path ensure healthy travel.