Exposure assessment models for elemental components of particulate matter in an urban environment: A comparison of regression and random forest approaches

Abstract

Exposure assessment for elemental components of particulate matter (PM) using land use modeling is a complex problem due to the high spatial and temporal variations in pollutant concentrations at the local scale. Land use regression (LUR) models may fail to capture complex interactions and non-linear relationships between pollutant concentrations and land use variables. The increasing availability of big spatial data and machine learning methods present an opportunity for improvement in PM exposure assessment models. In this manuscript, our objective was to develop a novel land use random forest (LURF) model and compare its accuracy and precision to a LUR model for elemental components of PM in the urban city of Cincinnati, Ohio. PM smaller than 2.5 μm (PM2.5) and eleven elemental components were measured at 24 sampling stations from the Cincinnati Childhood Allergy and Air Pollution Study (CCAAPS). Over 50 different predictors associated with transportation, physical features, community socioeconomic characteristics, greenspace, land cover, and emission point sources were used to construct LUR and LURF models. Cross validation was used to quantify and compare model performance. LURF and LUR models were created for aluminum (Al), copper (Cu), iron (Fe), potassium (K), manganese (Mn), nickel (Ni), lead (Pb), sulfur (S), silicon (Si), vanadium (V), zinc (Zn), and total PM2.5 in the CCAAPS study area. LURF utilized a more diverse and greater number of predictors than LUR and LURF models for Al, K, Mn, Pb, Si, Zn, TRAP, and PM2.5 all showed a decrease in fractional predictive error of at least 5% compared to their LUR models. LURF models for Al, Cu, Fe, K, Mn, Pb, Si, Zn, TRAP, and PM2.5 all had a cross validated fractional predictive error less than 30%. Furthermore, LUR models showed a differential exposure assessment bias and had a higher prediction error variance. Random forest and other machine learning methods may provide more accurate exposure assessment.

Keywords: Elemental PM2.5; Land use regression; Random forest.

Fig. 1

The location of the CCAAPS sampling sites in red and the birth addresses of the CCAAPS cohort in black. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)

Fig. 2

Box plot of average elemental concentrations, TRAP, and total PM2.5 used to train the land use models.

Fig. 3

Spearman correlation matrix of average elemental concentrations, TRAP, and total PM2.5. A darker blue and larger circle in the upper triangle of the grid corresponds to a larger Spearman’s rho statistic shown in the lower triangle of the grid. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)

Fig. 4

Cross validated absolute predictive error and 95% confidence interval for each elemental model, each built both using a LUR model and a LURF model.

Fig. 5

LOOCV predictions from the LURF and LUR land use models according to the true observed values. The dotted line represents the perfect agreement between observed and predicted concentrations.