A peer-reviewed open access journal published by the National Institute of Environmental Health Sciences

Particulate matter (PM) air pollution is one of the major causes of death worldwide, with demonstrated adverse effects from both short-term and long-term exposure. Most of the epidemiological studies have been conducted in cities because of the lack of reliable spatiotemporal estimates of particles exposure in nonurban settings. The objective of this study is to estimate daily PM10 (PM < 10 μm), fine (PM < 2.5 μm, PM2.5) and coarse particles (PM between 2.5 and 10 μm, PM2.5-10) at 1-km2 grid for 2013-2015 using a machine learning approach, the Random Forest (RF). Separate RF models were defined to: predict PM2.5 and PM2.5-10 concentrations in monitors where only PM10 data were available (stage 1); impute missing satellite Aerosol Optical Depth (AOD) data using estimates from atmospheric ensemble models (stage 2); establish a relationship between measured PM and satellite, land use and meteorological parameters (stage 3); predict stage 3 model over each 1-km2 grid cell of Italy (stage 4); and improve stage 3 predictions by using small-scale predictors computed at the monitor locations or within a small buffer (stage 5). Our models were able to capture most of PM variability, with mean cross-validation (CV) R2 of 0.75 and 0.80 (stage 3) and 0.84 and 0.86 (stage 5) for PM10 and PM2.5, respectively. Model fitting was less optimal for PM2.5-10, in summer months and in southern Italy. Finally, predictions were equally good in capturing annual and daily PM variability, therefore they can be used as reliable exposure estimates for investigating long-term and short-term health effects.

Few studies have explored the role of air pollution in neurodegenerative processes, especially various types of dementia. Our aim was to evaluate the association between long-term exposure to air pollution and first hospitalization for dementia subtypes in a large administrative cohort. We selected 350,844 subjects (free of dementia) aged 65–100 years at inclusion (21/10/2001) and followed them until 31/12/2013. We selected all subjects hospitalized for the first time with primary or secondary diagnoses of various forms of dementia. We estimated the exposure at residence using land use regression models for nitrogen oxides (NOx, NO2) and particulate matter (PM) and a chemical transport model for ozone (O3). We used Cox models to estimate the association between exposure and first hospitalization for dementia and its subtypes: vascular dementia (Vd), Alzheimer’s disease (Ad) and senile dementia (Sd). We selected 21,548 first hospitalizations for dementia (7497 for Vd, 7669 for Ad and 7833 for Sd). Overall, we observed a negative association between exposure to NO2 (10 μg/m3) and dementia hospitalizations (HR = 0.97; 95% CI: 0.96–0.99) and a positive association between exposure to O3, NOx and dementia hospitalizations, (O3: HR = 1.06; 95% CI: 1.04–1.09 per 10 μg/m3; NOx: HR = 1.01; 95% CI: 1.00–1.02 per 20 μg/m3).H. Exposure to NOx, NO2, PM2.5, and PM10 was positively associated with Vd and negatively associated with Ad. Hospitalization for Sd was positively associated with exposure to O3 (HR = 1.20; 95% CI: 1.15–1.24 per 10 μg/m3). Our results showed a positive association between exposure to NOx and O3 and hospitalization for dementia and a negative association between NO2 exposure and hospitalization for dementia. In the analysis by subtype, exposure to each pollutants (except O3) demonstrated a positive association with vascular dementia, while O3 exposure was associated with senile dementia. The results regarding vascular dementia are a clear indication that the brain effects of air pollution are linked with vascular damage.

Cities are severely affected by air pollution. Local emissions and urban structures can produce large spatial heterogeneities. We aim to improve the estimation of NO2, O3, PM2.5 and PM10 concentrations in 6 Italian metropolitan areas, using chemical-transport and machine learning models, and to assess the effect on population exposure by using information on urban population mobility. Three years (2013-2015) of simulations were performed by the Chemical-Transport Model (CTM) FARM, at 1 km resolution, fed by boundary conditions provided by national-scale simulations, local emission inventories and meteorological fields. A downscaling of daily air pollutants at higher resolution (200 m) was then carried out by means of a machine learning Random-Forest (RF) model, considering CTM and spatial-temporal predictors, such as population, land-use, surface greenness and vehicular traffic, as input. RF achieved mean cross-validation (CV) R2 of 0.59, 0.72, 0.76 and 0.75 for NO2, PM10, PM2.5 and O3, respectively, improving results from CTM alone. Mean concentration fields exhibited clear geographical gradients caused by climate conditions, local emission sources and photochemical processes. Time series of population weighted exposure (PWE) were estimated for two months of the year 2015 and for five cities, by combining population mobility data (derived from mobile phone traffic volumes data), and concentration levels from the RF model. PWE_RF metric better approximated the observed concentrations compared with the predictions from either CTM alone or CTM and RF combined, especially for pollutants exhibiting strong spatial gradients, such as NO2. 50% of the population was estimated to be exposed to NO2 concentrations between 12 and 38 μg/m3 and PM10 between 20 and 35 μg/m3. This work supports the potential of machine learning methods in predicting air pollutant levels in urban areas at high spatial and temporal resolutions.