A satellite-based spatio-temporal machine learning model to reconstruct daily PM2.5 concentrations across Great Britain

Schneider, Rochelle; Vicedo-Cabrera, Ana M.; Sera, Francesco; Masselot, Pierre; Stafoggia, Massimo; de Hoogh, Kees; Kloog, Itai; Reis, Stefan ORCID: https://orcid.org/0000-0003-2428-8320; Vieno, Massimo ORCID: https://orcid.org/0000-0001-7741-9377; Gasparrini, Antonio. 2020 A satellite-based spatio-temporal machine learning model to reconstruct daily PM2.5 concentrations across Great Britain [in special issue: The use of earth observations for exposure assessment in epidemiological studies] Remote Sensing, 12 (22), 3803. 19, pp. https://doi.org/10.3390/rs12223803

Before downloading, please read NORA policies.

Preview

Text
N528994JA.pdf - Published Version
Available under License Creative Commons Attribution 4.0.
Download (2MB) | Preview

Preview

Text (Correction 09.09.2021)
N528994JAX.pdf - Published Version
Available under License Creative Commons Attribution 4.0.
Download (865kB) | Preview

Official URL: http://dx.doi.org/10.3390/rs12223803

Abstract/Summary

Epidemiological studies on the health effects of air pollution usually rely on measurements from fixed ground monitors, which provide limited spatio-temporal coverage. Data from satellites, reanalysis, and chemical transport models offer additional information used to reconstruct pollution concentrations at high spatio-temporal resolutions. This study aims to develop a multi-stage satellite-based machine learning model to estimate daily fine particulate matter (PM2.5) levels across Great Britain between 2008–2018. This high-resolution model consists of random forest (RF) algorithms applied in four stages. Stage-1 augments monitor-PM2.5 series using co-located PM10 measures. Stage-2 imputes missing satellite aerosol optical depth observations using atmospheric reanalysis models. Stage-3 integrates the output from previous stages with spatial and spatio-temporal variables to build a prediction model for PM2.5. Stage-4 applies Stage-3 models to estimate daily PM2.5 concentrations over a 1 km grid. The RF architecture performed well in all stages, with results from Stage-3 showing an average cross-validated R2 of 0.767 and minimal bias. The model performed better over the temporal scale when compared to the spatial component, but both presented good accuracy with an R2 of 0.795 and 0.658, respectively. These findings indicate that direct satellite observations must be integrated with other satellite-based products and geospatial variables to derive reliable estimates of air pollution exposure. The high spatio-temporal resolution and the relatively high precision allow these estimates (approximately 950 million points) to be used in epidemiological analyses to assess health risks associated with both short- and long-term exposure to PM2.5.

Item Type:	Publication - Article
Digital Object Identifier (DOI):	https://doi.org/10.3390/rs12223803
UKCEH and CEH Sections/Science Areas:	Atmospheric Chemistry and Effects (Science Area 2017-)
ISSN:	2072-4292
Additional Information. Not used in RCUK Gateway to Research.:	Open Access paper - full text available via Official URL link.
Additional Keywords:	fine particulate matter, aerosol optical depth, satellite, reanalysis, machine learning, random forest
NORA Subject Terms:	Health Atmospheric Sciences Data and Information
Date made live:	24 Nov 2020 16:38 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/528994

Item Type:

Publication - Article

Digital Object Identifier (DOI):

https://doi.org/10.3390/rs12223803

UKCEH and CEH Sections/Science Areas:

Atmospheric Chemistry and Effects (Science Area 2017-)

ISSN:

2072-4292

Additional Information. Not used in RCUK Gateway to Research.:

Open Access paper - full text available via Official URL link.

Additional Keywords:

fine particulate matter, aerosol optical depth, satellite, reanalysis, machine learning, random forest