Abstract
Air pollution is one of the leading causes of mortality worldwide. An accurate assessment of its spatial and temporal distribution is mandatory to conduct epidemiological studies able to estimate long-term (e.g., annual) and short-term (e.g., daily) health effects. While spatiotemporal models for particulate matter (PM) have been developed in several countries, estimates of daily nitrogen dioxide (NO2) and ozone (O3) concentrations at high spatial resolution are lacking, and no such models have been developed in Sweden. We collected data on daily air pollutant concentrations from routine monitoring networks over the period 2005–2016 and matched them with satellite data, dispersion models, meteorological parameters, and land-use variables. We developed a machine-learning approach, the random forest (RF), to estimate daily concentrations of PM10 (PM<10 microns), PM2.5 (PM<2.5 microns), PM2.5–10 (PM between 2.5 and 10 microns), NO2, and O3 for each squared kilometer of Sweden over the period 2005–2016. Our models were able to describe between 64% (PM10) and 78% (O3) of air pollutant variability in held-out observations, and between 37% (NO2) and 61% (O3) in held-out monitors, with no major differences across years and seasons and better performance in larger cities such as Stockholm. These estimates will allow to investigate air pollution effects across the whole of Sweden, including suburban and rural areas, previously neglected by epidemiological investigations.
Highlights
Air pollution is a major risk factor to human health, causing >4 million premature deaths every year worldwide, with more than 90% of the population living in areas exceeding the guideline limits from the World Health Organization [1].The health effects of air pollution have been extensively documented in the epidemiological literature, and they have been broadly distinguished into acute effects stemming from short-term exposures [2,3,4] and chronic effects induced by long-term exposures [5]
In the former, the hypothesis is that day-to-day variability in air pollutants is causally related to daily peaks in mortality outcomes, whereas in the latter it is assumed that residing in areas with larger-than-average air pollution exposures will increase adverse health effects in the long run
Most of the evidence on the health effects of air pollution has focused on particulate matter (PM), especially the fine fraction (PM2.5 ), and previous studies have generally been conducted in urban areas due to lack of observations or reliable model estimates for suburban or rural areas [5,6,7]
Summary
Air pollution is a major risk factor to human health, causing >4 million premature deaths every year worldwide, with more than 90% of the population living in areas exceeding the guideline limits from the World Health Organization [1].The health effects of air pollution have been extensively documented in the epidemiological literature, and they have been broadly distinguished into acute effects stemming from short-term (e.g., daily) exposures [2,3,4] and chronic effects induced by long-term (e.g., annual) exposures [5]. Most of the evidence on the health effects of air pollution has focused on particulate matter (PM), especially the fine fraction (PM2.5 ), and previous studies have generally been conducted in urban areas due to lack of observations or reliable model estimates for suburban or rural areas [5,6,7]. This is a limitation, since many people live in non-urban areas characterized by a different source profile of air pollution compared to cities [8]. Concentrations of PM2.5 and nitrogen dioxide (NO2 ) are expected to be lower away from the major cities, and most of recent research is trying to understand whether there exist health effects from air pollution that require revision of the air quality standards
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call