Search

While multiple information sources exist concerning surface‐level air pollution, no individual source simultaneously provides large‐scale spatial coverage, fine spatial and temporal resolution, and high accuracy. It is, therefore, necessary to integrate multiple data sources, using the strengths of each source to compensate for the weaknesses of others. In this study, we propose a method incorporating outputs of NASA's GEOS Composition Forecasting model system with satellite information from the TROPOMI instrument and ground measurement data on surface concentrations. Although we use ground monitoring data from the Environmental Protection Agency network in the continental United States, the model and satellite data sources used have the potential to allow for global application. This method is demonstrated using surface measurements of nitrogen dioxide as a test case in regions surrounding five major US cities. The proposed method is assessed through cross‐validation against withheld ground monitoring sites. In these assessments, the proposed method demonstrates major improvements over two baseline approaches which use ground‐based measurements only. Results also indicate the potential for near‐term updating of forecasts based on recent ground measurements. Plain Language Summary: Air quality is a major health concern worldwide, leading to millions of premature deaths annually. In order to better understand this risk and mitigate its impacts, there are numerous sources of information about air quality. These include ground‐based measurement stations, satellites, and global air quality models. By combining these data sources together, we can use the strengths of each source to compensate for the weaknesses of others. This paper presents one method of combining these data sources and uses it to make air quality forecasts over five US cities up to one day in advance. These forecasts are compared to pollution estimates made using ground‐based measurement data only to see how integrating additional data sources improves the forecast. Overall, we find that there are large increases in accuracy of forecasting using the proposed method, and that further improvements can be made by comparing the forecasts to the most recent ground‐based measurements and making some more final adjustments. Methods like this, which use a combination of globally available satellite and model data together with some local measurements, can be applied to different types of air pollution in all regions of the world, thereby improving our understanding of air pollution globally. Key Points: Multiple air quality data sources (GOES‐CF model, TROPOMI satellite, Environmental Protection Agency monitors) are combined to improve city‐scale NO2 forecastsForecasts using combined data outperform forecasts using ground‐based measurements onlyUpdating of forecasts based on residuals against the most recent ground measurements further improves short‐term forecasting [ABSTRACT FROM AUTHOR]