Application of geostationary satellite and high-resolution meteorology data in estimating hourly PM2.5 levels during the Camp Fire episode in California

Wildland fire smoke contains large amounts of PM2.5 that can traverse tens to hundreds of kilometers, resulting in significant deterioration of air quality and excess mortality and morbidity in downwind regions. Estimating PM2.5 levels while considering the impact of wildfire smoke has been challenging due to the lack of ground monitoring coverage near the smoke plumes. We aim to estimate total PM2.5 concentration during the Camp Fire episode, the deadliest wildland fire in California history. Our random forest (RF) model combines calibrated lowcost sensor data (PurpleAir) with regulatory monitor measurements (Air Quality System, AQS) to bolster ground observations, Geostationary Operational Environmental Satellite-16 (GOES-16)'s high temporal resolution to achieve hourly predictions, and oversampling techniques (Synthetic Minority Oversampling Technique, SMOTE) to reduce model underestimation at high PM2.5 levels. In addition, meteorological fields at 3 km resolution from the High-Resolution Rapid Refresh model and land use variables were also included in the model. Our AQS-only model achieved an out of bag (OOB) R-2 (RMSE) of 0.84 (12.00 mu g/m(3)) and spatial and temporal cross-validation (CV) R-2 (RMSE) of 0.74 (16.28 mu g/m(3)) and 0.73 (16.58 mu g/m3), respectively. Our AQS + Weighted PurpleAir Model achieved OOB R-2 (RMSE) of 0.86 (9.52 mu g/m(3)) and spatial and temporal CV R-2 (RMSE) of 0.75 (14.93 mu g/m(3)) and 0.79 (11.89 mu g/m(3)), respectively. Our AQS + Weighted PurpleAir + SMOTE Model achieved OOB R-2 (RMSE) of 0.92 (10.44 mu g/m(3)) and spatial and temporal CV R-2 (RMSE) of 0.84 (12.36 mu g/m(3)) and 0.85 (14.88 mu g/m(3)), respectively. Hourly predictions from our model may aid in epidemiological investigations of intense and acute exposure to PM2.5 during the Camp Fire episode.

Automated summary

This study successfully estimated the PM2.5 concentration during the Camp Fire episode, the deadliest wildfire in California history, by using a random forest model combined with multiple data sources. The results demonstrate that the model can aid in epidemiological investigations of intense and acute exposure to PM2.5 through hourly predictions.