Global Land Use Regression Model for Nitrogen Dioxide Air Pollution

Abstract

Nitrogen dioxide is a common air pollutant with growing evidence of health impacts independent of other common pollutants such as ozone and particulate matter. However, the worldwide distribution of NO₂ exposure and associated impacts on health is still largely uncertain. To advance global exposure estimates we created a global nitrogen dioxide (NO₂) land use regression model for 2011 using annual measurements from 5,220 air monitors in 58 countries. The model captured 54% of global NO₂ variation, with a mean absolute error of 3.7 ppb. Regional performance varied from R² = 0.42 (Africa) to 0.67 (South America). Repeated 10% cross-validation using bootstrap sampling (n = 10,000) demonstrated a robust performance with respect to air monitor sampling in North America, Europe, and Asia (adjusted R² within 2%) but not for Africa and Oceania (adjusted R² within 11%) where NO₂ monitoring data are sparse. The final model included 10 variables that captured both between and within-city spatial gradients in NO₂ concentrations. Variable contributions differed between continental regions, but major roads within 100 m and satellite-derived NO₂ were consistently the strongest predictors. The resulting model can be used for global risk assessments and health studies, particularly in countries without existing NO₂ monitoring data or models.