Modeling particle number concentrations along Interstate 10 in El Paso, Texas

Abstract

Annual average daily particle number concentrations around a highway were estimated with an atmospheric dispersion model and a land use regression model. The dispersion model was used to estimate particle concentrations along Interstate 10 at 98 locations within El Paso, Texas. This model employed annual averaged wind speed and annual average daily traffic counts as inputs. A land use regression model with vehicle kilometers traveled as the predictor variable was used to estimate local background concentrations away from the highway to adjust the near-highway concentration estimates. Estimated particle number concentrations ranged between 9.8 × 10³ particles/cc and 1.3 × 10⁵ particles/cc, and averaged 2.5 × 10⁴ particles/cc (SE 421.0). Estimates were compared against values measured at seven sites located along I10 throughout the region. The average fractional error was 6% and ranged between -1% and -13% across sites. The largest bias of -13% was observed at a semi-rural site where traffic was lowest. The average bias amongst urban sites was 5%. The accuracy of the estimates depended primarily on the emission factor and the adjustment to local background conditions. An emission factor of 1.63 × 10¹⁴ particles/veh-km was based on a value proposed in the literature and adjusted with local measurements. The integration of the two modeling techniques ensured that the particle number concentrations estimates captured the impact of traffic along both the highway and arterial roadways. The performance and economical aspects of the two modeling techniques used in this study shows that producing particle concentration surfaces along major roadways would be feasible in urban regions where traffic and meteorological data are readily available.

Keywords: Dispersion model; Land use regression; US-Mexico border; Ultrafine.

Figure 1

Map of the study showing the measurements sites and near-highway grid where PNC estimates were performed.

Figure 2

PNC as a function of distance from the highway. Circles represent the average of the median values observed at all 7 sites along I-10 in El Paso. Data from all sample collection dates were used (Table S1).

Figure 3

Observed hourly variation of PNC_B averaged across sites. Data from all background sites and sample collection dates were used.

Figure 4

Dispersion model PNC estimates produced with an emission factor of 7.26 × 10¹⁴ #/veh-km. With circles represent the average of the median values observed at all 7 sites along I-10 in El Paso. Data from all sample collection dates were used (Table S1).

Figure 5

Dispersion model PNC estimates; a) produced with different emission factor values, b) produced with different w* values. Measured values represent data from all sample collection dates were used (Table S1).

Figure 6

Adjusted PNC estimates produced with an emission factor of 1.82 × 10¹⁴ #/veh-km and compared against averaged measurements per site.

Figure 7

Long-term PNC surface along Interstate 10 in El Paso, Texas. Surface was produced with PNC estimates produced with the dispersion model and adjusted to local background concentrations (PNC_B) estimated with the LUR model at 98 locations along I10.