Back to Search
Start Over
A Satellite-Based Spatio-Temporal Machine Learning Model to Reconstruct Daily PM 2.5 Concentrations across Great Britain.
- Source :
- Remote Sensing; Nov2020, Vol. 12 Issue 22, p3803, 1p
- Publication Year :
- 2020
-
Abstract
- 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 (PM<subscript>2.5</subscript>) 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-PM<subscript>2.5</subscript> series using co-located PM<subscript>10</subscript> 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 PM<subscript>2.5</subscript>. Stage-4 applies Stage-3 models to estimate daily PM<subscript>2.5</subscript> concentrations over a 1 km grid. The RF architecture performed well in all stages, with results from Stage-3 showing an average cross-validated R<superscript>2</superscript> 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 R<superscript>2</superscript> 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 PM<subscript>2.5</subscript>. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 20724292
- Volume :
- 12
- Issue :
- 22
- Database :
- Complementary Index
- Journal :
- Remote Sensing
- Publication Type :
- Academic Journal
- Accession number :
- 147277022
- Full Text :
- https://doi.org/10.3390/rs12223803