A hybrid approach to predict daily NO₂ concentrations at city block scale

Estimating the ambient concentration of nitrogen dioxide (NO₂) is challenging because NO₂ generated by local fossil fuel combustion varies greatly in concentration across space and time. This study demonstrates an integrated hybrid approach combining dispersion modeling and land use regression (LUR) to predict daily NO₂ concentrations at a high spatial resolution (e.g., 50 m) in the New York tri-state area. The daily concentration of traffic-related NO₂ was estimated at the Environmental Protection Agency's NO₂ monitoring sites in the study area for the years 2015–2017, using the Research LINE source (R-LINE) model with inputs of traffic data provided by the Highway Performance and Management System and meteorological data provided by the NOAA Integrated Surface Database. We used the R-LINE-predicted daily concentrations of NO₂ to build mixed-effects regression models, including additional variables representing land use features, geographic characteristics, weather, and other predictors. The mixed model was selected by the Elastic Net method. Each model's performance was evaluated using the out-of-sample coefficient of determination (R²) and the square root of mean squared error (RMSE) from ten-fold cross-validation (CV). The mixed model showed a good prediction performance (CV R²: 0.75–0.79, RMSE: 3.9–4.0 ppb). R-LINE outputs improved the overall, spatial, and temporal CV R² by 10.0%, 18.9% and 7.7% respectively. Given the output of R-LINE is point-based and has a flexible spatial resolution, this hybrid approach allows prediction of daily NO₂ at an extremely high spatial resolution such as city blocks.