Using Machine Learning to Estimate Global PM(2.5) for Environmental Health Studies

With the increasing awareness of health impacts of particulate matter, there is a growing need to comprehend the spatial and temporal variations of the global abundance of ground-level airborne particulate matter (PM(2.5)). Here we use a suite of remote sensing and meteorological data products together with ground based observations of PM(2.5) from 8,329 measurement sites in 55 countries taken between 1997 and 2014 to train a machine learning algorithm to estimate the daily distributions of PM(2.5) from 1997 to the present. We demonstrate that the new PM(2.5) data product can reliably represent global observations of PM(2.5) for epidemiological studies. An analysis of Baltimore schizophrenia emergency room admissions is presented in terms of the levels of ambient pollution. PM(2.5) appears to have an impact on some aspects of mental health.