Smoke Exposure (PM2.5) Monthly (Naman Paul, Jiayun Yao, Kathleen E. McLean, David M. Stieb, Sarah B. Henderson, The Canadian Optimized Statistical Smoke Exposure Model (CanOSSEM): A machine learning approach to estimate national daily fine particulate matter (PM2.5) exposure, Science of The Total Environment, 2022.)

The Canadian Optimized Statistical Smoke Model (CanOSSEM) was developed by the Environmental Health Services of the BC Centre for Disease Control and used to produce estimated concentrations of fine particulate across all populated regions of Canada. The estimates are optimized for wildfire smoke through use of multiple variables that are specific to this source. NOTE: Daily data indexed to postal codes will be available shortly. Un-indexed grid files are available on request to naman.paul@bccdc.ca.CanOSSEM is a random forest machine learning model that uses potential predictor variables integrated from multiple data sources and estimates daily mean (24-hour) PM2.5 concentrations at a 5 km × 5 km spatial resolution. The training and prediction datasets were generated using observations from National Air Pollution Surveillance (NAPS) network. The Root Mean Squared Error (RMSE) between predicted and observed PM2.5 concentration was 2.85 µg/m3 for the entire prediction set, with over 95% of the predictions lying within an absolute difference of 5 µg/m3 from the NAPS PM2.5 measurements. The model was evaluated using 10-fold cross-validation, leave-one-region-out and leave-one-year-out cross-validation.