edoc

Estimation of daily PM10 and PM2.5; concentrations in Italy, 2013-2015, using a spatiotemporal land-use random-forest model

Stafoggia, Massimo and Bellander, Tom and Bucci, Simone and Davoli, Marina and de Hoogh, Kees and De' Donato, Francesca and Gariazzo, Claudio and Lyapustin, Alexei and Michelozzi, Paola and Renzi, Matteo and Scortichini, Matteo and Shtein, Alexandra and Viegi, Giovanni and Kloog, Itai and Schwartz, Joel. (2019) Estimation of daily PM10 and PM2.5; concentrations in Italy, 2013-2015, using a spatiotemporal land-use random-forest model. Environment international, 124. pp. 170-179.

[img] PDF - Accepted Version
Available under License CC BY-NC-ND (Attribution-NonCommercial-NoDerivatives).

1548Kb

Official URL: https://edoc.unibas.ch/68752/

Downloads: Statistics Overview

Abstract

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 PM; 10; (PM < 10 μm), fine (PM < 2.5 μm, PM; 2.5; ) and coarse particles (PM between 2.5 and 10 μm, PM; 2.5-10; ) at 1-km; 2; grid for 2013-2015 using a machine learning approach, the Random Forest (RF). Separate RF models were defined to: predict PM; 2.5; and PM; 2.5-10; concentrations in monitors where only PM; 10; 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-km; 2; 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) R; 2; of 0.75 and 0.80 (stage 3) and 0.84 and 0.86 (stage 5) for PM; 10; and PM; 2.5; , respectively. Model fitting was less optimal for PM; 2.5-10; , 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.
Faculties and Departments:09 Associated Institutions > Swiss Tropical and Public Health Institute (Swiss TPH)
09 Associated Institutions > Swiss Tropical and Public Health Institute (Swiss TPH) > Department of Epidemiology and Public Health (EPH) > Environmental Exposures and Health > Physical Hazards and Health (Röösli)
UniBasel Contributors:de Hoogh, Kees
Item Type:Article, refereed
Article Subtype:Research Article
Publisher:Elsevier
ISSN:0160-4120
Note:Publication type according to Uni Basel Research Database: Journal article
Language:English
Identification Number:
Last Modified:29 Jan 2019 15:47
Deposited On:29 Jan 2019 15:47

Repository Staff Only: item control page