Back to Search
Start Over
Predicting Daily PM 2.5 Exposure with Spatially Invariant Accuracy Using Co-Existing Pollutant Concentrations as Predictors.
- Source :
- Atmosphere; May2022, Vol. 13 Issue 5, p782, 12p
- Publication Year :
- 2022
-
Abstract
- The spatiotemporal variation of PM<subscript>2.5</subscript> should be accurately estimated for epidemiological studies. However, the accuracy of prediction models may change over geographical space, which is not conducive for proper exposure assessment. In this study, we developed a prediction model to estimate daily PM<subscript>2.5</subscript> concentrations from 2010 to 2017 in the Kansai region of Japan with co-existing pollutant concentrations as predictors. The overall objective was to obtain daily estimates over the study domain with spatially homogeneous accuracy. We used random forest algorithm to model the relationship between the daily PM<subscript>2.5</subscript> concentrations and various predictors. The model performance was evaluated via spatial and temporal cross-validation and the daily PM<subscript>2.5</subscript> surface was estimated from 2010 to 2017 at a 1 km × 1 km resolution. We achieved R<superscript>2</superscript> values of 0.91 and 0.92 for spatial and temporal cross-validation, respectively. The prediction accuracy for each monitoring site was found to be consistently high, regardless of the distance to the nearest monitoring location, up to 10 km. Even for distances greater than 10 km, the mean R<superscript>2</superscript> value was 0.88. Our approach yielded spatially homogeneous prediction accuracy, which is beneficial for epidemiological studies. The daily PM<subscript>2.5</subscript> estimates will be used in a related birth cohort study to evaluate the potential impact on human health. [ABSTRACT FROM AUTHOR]
- Subjects :
- RANDOM forest algorithms
POLLUTANTS
AIR pollutants
PREDICTION models
COHORT analysis
Subjects
Details
- Language :
- English
- ISSN :
- 20734433
- Volume :
- 13
- Issue :
- 5
- Database :
- Complementary Index
- Journal :
- Atmosphere
- Publication Type :
- Academic Journal
- Accession number :
- 157129176
- Full Text :
- https://doi.org/10.3390/atmos13050782