Evaluating Environmental Impact of Traffic Congestion in Real Time Based on Sparse Mobile Crowd-Sourced Data
Traffic congestion at arterial intersections and freeway bottleneck degrades the air quality and threatens the public health, especially for people living and working near major roadways. Emission models such as MOVES could evaluate the air pollutant emissions in a microscopic level with second-by-second speed/acceleration profiles as the key inputs. Sparse mobile crowd-sourced data, such as cellular network data and GPS data, have inherent advantage to satisfy the data requirement for microscopic emission models.
This research will establish a framework for traffic-related air pollution evaluation using sparse mobile data and PeMS data. It develops an effective tool to evaluate the environmental impact of traffic congestion in an accurate, timely and economic way. The proposed model is applicable to varying traffic conditions and multiple transport modes on either urban arterials or freeways. The proposed system will provide suggestions to the transportation operator and public health officials to alleviate the risk of air pollutant. A livability evaluation model will also be developed to estimate the localized emissions in community and analyze the environmental justice issue. A prototype will also be developed to visualize the traffic emission and dispersion in a network in Southern California.