Background: Short-term exposure to ambient PM2·5 is a leading contributor to the global burden of diseases and mortality. However, few studies have provided the global spatiotemporal variations of daily PM2·5 concentrations over recent decades.
Methods: In this modelling study, we implemented deep ensemble machine learning (DEML) to estimate global daily ambient PM2·5 concentrations at 0·1° × 0·1° spatial resolution between Jan 1, 2000, and Dec 31, 2019. In the DEML framework, ground-based PM2·5 measurements from 5446 monitoring stations in 65 countries worldwide were combined with GEOS-Chem chemical transport model simulations of PM2·5 concentration, meteorological data, and geographical features. At the global and regional levels, we investigated annual population-weighted PM2·5 concentrations and annual population-weighted exposed days to PM2·5 concentrations higher than 15 μg/m3 (2021 WHO daily limit) to assess spatiotemporal exposure in 2000, 2010, and 2019. Land area and population exposures to PM2·5 above 5 μg/m3 (2021 WHO annual limit) were also assessed for the year 2019. PM2·5 concentrations for each calendar month were averaged across the 20-year period to investigate global seasonal patterns.
Findings: Our DEML model showed good performance in capturing the global variability in ground-measured daily PM2·5, with a cross-validation R2 of 0·91 and root mean square error of 7·86 μg/m3. Globally, across 175 countries, the mean annual population-weighted PM2·5 concentration for the period 2000-19 was estimated at 32·8 μg/m3 (SD 0·6). During the two decades, population-weighted PM2·5 concentration and annual population-weighted exposed days (PM2·5 >15 μg/m3) decreased in Europe and northern America, whereas exposures increased in southern Asia, Australia and New Zealand, and Latin America and the Caribbean. In 2019, only 0·18% of the global land area and 0·001% of the global population had an annual exposure to PM2·5 at concentrations lower than 5 μg/m3, with more than 70% of days having daily PM2·5 concentrations higher than 15 μg/m3. Distinct seasonal patterns were indicated in many regions of the world.
Interpretation: The high-resolution estimates of daily PM2·5 provide the first global view of the unequal spatiotemporal distribution of PM2·5 exposure for a recent 20-year period, which is of value for assessing short-term and long-term health effects of PM2·5, especially for areas where monitoring station data are not available.
Funding: Australian Research Council, Australian Medical Research Future Fund, and the Australian National Health and Medical Research Council.
Copyright © 2023 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved.