Di, Q; Amini, H; Shi, LH; Kloog, I; Silvern, R; Kelly, J; Sabath, MB; Choirat, C; Koutrakis, P; Lyapustin, A; Wang, YJ; Mickley, LJ; Schwartz, J (2019). An ensemble-based model of PM2.5 concentration across the contiguous United States with high spatiotemporal resolution. ENVIRONMENT INTERNATIONAL, 130, UNSP 104909.

Various approaches have been proposed to model PM2.5 in the recent decade, with satellite-derived aerosol optical depth, land-use variables, chemical transport model predictions, and several meteorological variables as major predictor variables. Our study used an ensemble model that integrated multiple machine learning algorithms and predictor variables to estimate daily PM(2.5 )at a resolution of 1 km x 1 km across the contiguous United States. We used a generalized additive model that accounted for geographic difference to combine PM2.5 estimates from neural network, random forest, and gradient boosting. The three machine learning algorithms were based on multiple predictor variables, including satellite data, meteorological variables, land-use variables, elevation, chemical transport model predictions, several reanalysis datasets, and others. The model training results from 2000 to 2015 indicated good model performance with a 10-fold cross-validated R-2 of 0.86 for daily PM2.5 predictions. For annual PM2.5 estimates, the cross-validated R-2 was 0.89. Our model demonstrated good performance up to 60 mu g/m(3). Using trained PM2.5 model and predictor variables, we predicted daily PM2.5 from 2000 to 2015 at every 1 km x 1 km grid cell in the contiguous United States. We also used localized land-use variables within 1 km x 1 km grids to downscale PM2.5 predictions to 100 m x 100 m grid cells. To characterize uncertainty, we used meteorological variables, land-use variables, and elevation to model the monthly standard deviation of the difference between daily monitored and predicted PM2.5 for every 1 km x 1 km grid cell. This PM2.5 prediction dataset, including the downscaled and uncertainty predictions, allows epidemiologists to accurately estimate the adverse health effect of PM2.5. Compared with model performance of individual base learners, an ensemble model would achieve a better overall estimation. It is worth exploring other ensemble model formats to synthesize estimations from different models or from different groups to improve overall performance.