Back to Search
Start Over
Mapping Seasonal High-Resolution PM 2.5 Concentrations with Spatiotemporal Bagged-Tree Model across China.
- Source :
- ISPRS International Journal of Geo-Information; Oct2021, Vol. 10 Issue 10, p676, 1p
- Publication Year :
- 2021
-
Abstract
- High concentrations of fine particulate matter (PM<subscript>2.5</subscript>) are well known to reduce environmental quality, visibility, atmospheric radiation, and damage the human respiratory system. Satellite-based aerosol retrievals are widely used to estimate surface PM<subscript>2.5</subscript> levels because satellite remote sensing can break through the spatial limitations caused by sparse observation stations. In this work, a spatiotemporal weighted bagged-tree remote sensing (STBT) model that simultaneously considers the effects of aerosol optical depth, meteorological parameters, and topographic factors was proposed to map PM<subscript>2.5</subscript> concentrations across China that occurred in 2018. The proposed model shows superior performance with the determination coefficient (R<superscript>2</superscript>) of 0.84, mean-absolute error (MAE) of 8.77 μg/m<superscript>3</superscript> and root-mean-squared error (RMSE) of 15.14 μg/m<superscript>3</superscript> when compared with the traditional multiple linear regression (R<superscript>2</superscript> = 0.38, MAE = 18.15 μg/m<superscript>3</superscript>, RMSE = 29.06 μg/m<superscript>3</superscript>) and linear mixed-effect (R<superscript>2</superscript> = 0.52, MAE = 15.43 μg/m<superscript>3</superscript>, RMSE = 25.41 μg/m<superscript>3</superscript>) models by the 10-fold cross-validation method. The results collectively demonstrate the superiority of the STBT model to other models for PM<subscript>2.5</subscript> concentration monitoring. Thus, this method may provide important data support for atmospheric environmental monitoring and epidemiological research. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 22209964
- Volume :
- 10
- Issue :
- 10
- Database :
- Complementary Index
- Journal :
- ISPRS International Journal of Geo-Information
- Publication Type :
- Academic Journal
- Accession number :
- 153290283
- Full Text :
- https://doi.org/10.3390/ijgi10100676