Imperial College London
Portrait Picture

ProfessorMajidEzzati

Faculty of Medicine, School of Public Health

Chair in Global Environmental Health
 
 
 
//

Contact

 

majid.ezzati Website

 
 
//

Location

 

Sir Michael Uren HubWhite City Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Suel:2022:10.3390/rs14143429,
author = {Suel, E and Sorek-Hamer, M and Moise, I and Von, Pohle M and Sahasrabhojanee, A and Asanjan, AA and Arku, RE and Alli, AS and Barratt, B and Clark, SN and Middel, A and Deardorff, E and Lingenfelter, V and Oza, NC and Yadav, N and Ezzati, M and Brauer, M},
doi = {10.3390/rs14143429},
journal = {Remote Sensing},
title = {What you see is what you breathe? Estimating air pollution spatial variation using street level imagery},
url = {http://dx.doi.org/10.3390/rs14143429},
volume = {14},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - High spatial resolution information on urban air pollution levels is unavailable in many areas globally, partially due to high input data needs of existing estimation approaches. Here we introduce a computer vision method to estimate annual means for air pollution levels from street level images. We used annual mean estimates of NO2 and PM2.5 concentrations from locally calibrated models as labels from London, New York, and Vancouver to allow for compilation of a sufficiently large dataset (~250k images for each city). Our experimental setup is designed to quantify intra and intercity transferability of image-based model estimates. Performances were high and comparable to traditional land-use regression (LUR) and dispersion models when training and testing on images from the same city (R2 values between 0.51 and 0.95 when validated on data from ground monitoring stations). Like LUR models, transferability of models between cities in different geographies is more difficult. Specifically, transferability between the three cities i.e., London, New York, and Vancouver, which have similar pollution source profiles were moderately successful (R2 values between zero and 0.67). Comparatively, performances when transferring models trained on these cities with very different source profiles i.e., Accra in Ghana and Hong Kong were lower (R2 between zero and 0.21) suggesting the need for local calibration with local calibration using additional measurement data from cities that share similar source profiles.
AU  - Suel,E
AU  - Sorek-Hamer,M
AU  - Moise,I
AU  - Von,Pohle M
AU  - Sahasrabhojanee,A
AU  - Asanjan,AA
AU  - Arku,RE
AU  - Alli,AS
AU  - Barratt,B
AU  - Clark,SN
AU  - Middel,A
AU  - Deardorff,E
AU  - Lingenfelter,V
AU  - Oza,NC
AU  - Yadav,N
AU  - Ezzati,M
AU  - Brauer,M
DO  - 10.3390/rs14143429
PY  - 2022///
SN  - 2072-4292
TI  - What you see is what you breathe? Estimating air pollution spatial variation using street level imagery
T2  - Remote Sensing
UR  - http://dx.doi.org/10.3390/rs14143429
UR  - http://hdl.handle.net/10044/1/98325
VL  - 14
ER  -
Download