AUTHOR=Larkin Andrew , Anenberg Susan , Goldberg Daniel L. , Mohegh Arash , Brauer Michael , Hystad Perry TITLE=A global spatial-temporal land use regression model for nitrogen dioxide air pollution JOURNAL=Frontiers in Environmental Science VOLUME=Volume 11 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2023.1125979 DOI=10.3389/fenvs.2023.1125979 ISSN=2296-665X ABSTRACT=The World Health Organization (WHO) recently reduced its health guideline for Nitrogen dioxide (NO2) to annual and 24-hr means of 10 µg/m3 (5.3 ppb) and 25 µg/m3 (13.3 ppb). NO2 is a criteria air pollutant that varies spatiotemporally at fine resolutions due to its relatively short lifetime (~hours) and current models have limited ability to capture this variation. To advance global exposure estimates, we created a daily global land use regression (LUR) model with 50 x 50 m2 spatial resolution using 5.7 million daily air monitor averages collected from 8,250 monitor locations. In cross-validation, the model captured 47%, 59%, and 63% of daily, monthly, and annual global NO2 variation. Daily, monthly, and annual root mean square error were 6.8, 5.0, and 4.4 ppb and absolute bias were 46%, 30%, and 21%, respectively. The final model has 11 variables, including road density and built environments with fine (30 m or less) spatial resolution and meteorological and satellite data with daily temporal resolution. Major roads and satellite-based estimates of NO2 were consistently the strongest predictors in all regions. Daily model estimates from 2005-2019 are available and can be used for global risk assessments and health studies, particularly in countries without NO2 monitoring.