Title
Assessment of traffic environment using fine-tuned dynamic vehicle emission models
Abstract
In order to assess environmental impacts of local traffic flow, a two-stage parameter tuning approach is proposed for recalibration of the Comprehensive Modal Emission Model (CMEM) using on-road emission measurements collected in Chinese cities. Based on the procedure comprising of grid search and nonlinear simplex optimization, the fuel- and emission-related parameters in the model are estimated to minimize the Mean Square Error (MSE) between model outputs and real measurements. In addition, a regression-based emission model is calibrated using the same data samples to compare performance. It is shown from the numerical results that the tuning process is able of improving the model prediction accuracy, especially concerning the CO emission, when comparing with the original CMEM model and the regression-based model. In addition, the emission models are, after the tuning process, applied together with a traffic simulation model to evaluate dynamic environmental effects of traffic in a case study.
Year
DOI
Venue
2010
10.1109/ITSC.2010.5625195
ITSC
Keywords
Field
DocType
on-road emission measurement,fuel-related parameters,traffic simulation model,local traffic flow,environmental impact assessment,comprehensive modal emission model recalibration,nonlinear programming,air pollution,regression analysis,nonlinear simplex optimization,mean square error,environmental science computing,search problems,co,traffic,regression-based emission model,dynamic vehicle emission model,two-stage parameter tuning approach,traffic environment assessment,grid search,model prediction accuracy,emission-related parameters,mean square error methods,predictive models,traffic flow,data models,carbon monoxide,mathematical models,tuning,engines,china,environmental impact
Data modeling,Hyperparameter optimization,Traffic flow,Simulation,Regression analysis,Nonlinear programming,Traffic simulation,Mean squared error,Engineering,Mathematical model
Conference
Volume
Issue
ISSN
null
null
2153-0009
ISBN
Citations 
PageRank 
978-1-4244-7657-2
0
0.34
References 
Authors
0
3
Name
Order
Citations
PageRank
Wei Lei100.34
Xiaoliang Ma218218.51
Hui Chen300.34