Multivariate adaptive regression splines models for vehicular emission prediction

BackgroundRate models for predicting vehicular emissions of nitrogen oxides (NO X) are insensitive to the vehicle modes of operation, such as cruise, acceleration, deceleration and idle, because these models are usually based on the average trip speed. This study demonstrates the feasibility of using other variables such as vehicle speed, acceleration, load, power and ambient temperature to predict (NO X) emissions to ensure that the emission inventory is accurate and hence the air quality modelling and management plans are designed and implemented appropriately.MethodsWe propose to use the non-parametric Boosting-Multivariate Adaptive Regression Splines (B-MARS) algorithm to improve the accuracy of the Multivariate Adaptive Regression Splines (MARS) modelling to effectively predict NO X emissions of vehicles in accordance with on-board measurements and the chassis dynamometer testing. The B-MARS methodology is then applied to the NO X emission estimation.ResultsThe model approach provides more reliable results of the estimation and offers better predictions of NO X emissions.ConclusionThe results therefore suggest that the B-MARS methodology is a useful and fairly accurate tool for predicting NO X emissions and it may be adopted by regulatory agencies.

[1]  Nigel N. Clark,et al.  Development of a heavy-duty chassis dynamometer driving route , 1999 .

[2]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[3]  Carl Ensfield,et al.  Evaluation and comparison of portable emissions measurement systems and federal reference methods for emissions from a back-up generator and a diesel truck operated on a chassis dynamometer. , 2007, Environmental science & technology.

[4]  Seth Daniel Oduro,et al.  Prediction of NOx Vehicular Emissions Using On-Board Measurement and Chassis Dynamometer Testing , 2014 .

[5]  Stephen P. Mattingly,et al.  Statistical Model for Estimating Carbon Dioxide Emissions from a Light-Duty Gasoline Vehicle , 2013 .

[6]  J. Lewtas,et al.  Source apportionment of PM2.5 at an urban IMPROVE site in Seattle, Washington. , 2003, Environmental science & technology.

[7]  Eliseo Monfort,et al.  Source origin of trace elements in PM from regional background, urban and industrial sites of Spain , 2007 .

[8]  Barbara Zielinska,et al.  Real-world automotive emissions—Summary of studies in the Fort McHenry and Tuscarora mountain tunnels , 1995 .

[9]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[10]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[11]  Herman Wahid,et al.  Background ozone level in the Sydney basin: assessment and trend analysis , 2013 .

[12]  Hesham Rakha,et al.  Simple Comprehensive Fuel Consumption and CO2 Emissions Model Based on Instantaneous Vehicle Power , 2011 .

[13]  Nigel N Clark,et al.  Further Validation of Artificial Neural Network-Based Emissions Simulation Models for Conventional and Hybrid Electric Vehicles , 2006, Journal of the Air & Waste Management Association.

[14]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[15]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[16]  H Christopher Frey,et al.  On-Road Measurement of Vehicle Tailpipe Emissions Using a Portable Instrument , 2003, Journal of the Air & Waste Management Association.

[17]  Q. P. Ha,et al.  CO2 vehicular emission statistical analysis with instantaneous speed and acceleration as predictor variables , 2013, 2013 International Conference on Control, Automation and Information Sciences (ICCAIS).

[18]  K. V. S. Badarinath,et al.  Influence of vehicular traffic on urban air quality – A case study of Hyderabad, India , 2010 .

[19]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[20]  D L Massart,et al.  Multivariate adaptive regression splines (MARS) in chromatographic quantitative structure-retention relationship studies. , 2004, Journal of chromatography. A.