Improve OMI Observations on Ground-Level NO 2 Using Multiple Observations, Simulations, and Machine Learning

Le résumé fourni par la source

Nitrogen dioxide (NO2) is a criteria air pollutant with adverse impacts on human health and the environment. An accurate ground-level NO2dataset with high spatial resolution is beneficial for NO2pollution management and public health studies. In this study, we leverage long-term Ozone Monitoring Instrument (OMI) NO2observations by converting OMI NO2vertical column densities into ground-level NO2concentrations and improving its spatial resolution to 1 km × 1 km by using the Light Gradient Boosting Machine (LightGBM) learning model in three metro areas in the United States: Metro New York, New York (NY), Baltimore, Maryland (MD), and Houston, Texas (TX). Our improved ground-level NO2products achieved robust performance across all regions, with correlation coefficient of 0.897 in New York, 0.876 in Baltimore, and 0.914 in Houston. The corresponding root mean square error (RMSE) was 3.278 ppb in New York, 2.385 ppb in Baltimore, and 2.084 ppb in Houston, respectively. Furthermore, the products effectively captured the temporal variations in observed NO2concentrations across all cities. We also found that emissions, population density, boundary layer height (BLH), and winds are consistently important contributors to NO2concentrations across all three cities, while each city also has its own significant factors. This attribution analysis will be helpful to state and local air pollution agencies in their air pollution management efforts.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.