Probabilistic analysis of during cycle-based highway vehicle emission factors.

A probabilistic methodology for quantifying intervehicle variability and fleet average uncertainty in highway vehicle emission factors is developed. The methodology features the use of empirical distributions of emissions measurement data to characterize variability and the use of bootstrap simulation to characterize uncertainty. For the base emission rate as a function of mileage accumulation under standard conditions, a regression-based approach was employed in which the residual error terms were included in the probabilistic analysis. Probabilistic correction factors for different driving cycles, ambient temperature, and fuel Reid vapor pressure (RVP) were developed without interpolation or extrapolation of available data. The method was demonstrated for tailpipe carbon monoxide, hydrocarbon, and nitrogen oxides emissions for a selected light-duty gasoline vehicle technology. Intervehicle variability in emissions was found to span typically 2 or 3 orders of magnitude. The uncertainty in the fleet average emission factor was as low as +/- 10% for a 95% probability range, in the case of standard conditions, to as much as -90% to +280% when correction factors for alternative driving cycles, temperature, and RVP are applied. The implications of the results for method selection and for decision making are addressed.