Imperial College London
Portrait Picture

Prof Benjamin Barratt

Faculty of Medicine, School of Public Health

Professor in Environmental Exposures and Public Health
 
 
 
//

Contact

 

+44 (0)20 7594 2409b.barratt Website

 
 
//

Location

 

UREN.1023Sir Michael Uren HubWhite City Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Danesh:2020:10.3390/rs12060914,
author = {Danesh, Yazdi M and Kuang, Z and Dimakopoulou, K and Barratt, B and Suel, E and Amini, H and Lyapustin, A and Katsouyanni, K and Schwartz, J},
doi = {10.3390/rs12060914},
journal = {Remote Sensing},
pages = {1--18},
title = {Predicting fine particulate matter (PM2.5) in the Greater London area: an ensemble approach using machine learning methods},
url = {http://dx.doi.org/10.3390/rs12060914},
volume = {12},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Estimating air pollution exposure has long been a challenge for environmental health researchers. Technological advances and novel machine learning methods have allowed us to increase the geographic range and accuracy of exposure models, making them a valuable tool in conducting health studies and identifying hotspots of pollution. Here, we have created a prediction model for daily PM2.5 levels in the Greater London area from 1st January 2005 to 31st December 2013 using an ensemble machine learning approach incorporating satellite aerosol optical depth (AOD), land use, and meteorological data. The predictions were made on a 1 km × 1 km scale over 3960 grid cells. The ensemble included predictions from three different machine learners: a random forest (RF), a gradient boosting machine (GBM), and a k-nearest neighbor (KNN) approach. Our ensemble model performed very well, with a ten-fold cross-validated R2 of 0.828. Of the three machine learners, the random forest outperformed the GBM and KNN. Our model was particularly adept at predicting day-to-day changes in PM2.5 levels with an out-of-sample temporal R2 of 0.882. However, its ability to predict spatial variability was weaker, with a R2 of 0.396. We believe this to be due to the smaller spatial variation in pollutant levels in this area.
AU  - Danesh,Yazdi M
AU  - Kuang,Z
AU  - Dimakopoulou,K
AU  - Barratt,B
AU  - Suel,E
AU  - Amini,H
AU  - Lyapustin,A
AU  - Katsouyanni,K
AU  - Schwartz,J
DO  - 10.3390/rs12060914
EP  - 18
PY  - 2020///
SN  - 2072-4292
SP  - 1
TI  - Predicting fine particulate matter (PM2.5) in the Greater London area: an ensemble approach using machine learning methods
T2  - Remote Sensing
UR  - http://dx.doi.org/10.3390/rs12060914
UR  - https://www.mdpi.com/2072-4292/12/6/914
UR  - http://hdl.handle.net/10044/1/77666
VL  - 12
ER  -
Download