IRUS Total

What you see is what you breathe? Estimating air pollution spatial variation using street level imagery

File Description SizeFormat 
remotesensing-14-03429-v2.pdfPublished version6.47 MBAdobe PDFView/Open
Title: What you see is what you breathe? Estimating air pollution spatial variation using street level imagery
Authors: Suel, E
Sorek-Hamer, M
Moise, I
Von Pohle, M
Sahasrabhojanee, A
Asanjan, AA
Arku, RE
Alli, AS
Barratt, B
Clark, SN
Middel, A
Deardorff, E
Lingenfelter, V
Oza, NC
Yadav, N
Ezzati, M
Brauer, M
Item Type: Journal Article
Abstract: 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.
Issue Date: 17-Jul-2022
Date of Acceptance: 5-Jul-2022
URI: http://hdl.handle.net/10044/1/98325
DOI: 10.3390/rs14143429
ISSN: 2072-4292
Publisher: MDPI AG
Journal / Book Title: Remote Sensing
Volume: 14
Issue: 14
Copyright Statement: © 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/)
Sponsor/Funder: Medical Research Council (MRC)
Wellcome Trust
Funder's Grant Number: MR/S003983/1
Keywords: Science & Technology
Life Sciences & Biomedicine
Physical Sciences
Environmental Sciences
Geosciences, Multidisciplinary
Remote Sensing
Imaging Science & Photographic Technology
Environmental Sciences & Ecology
computer vision
deep learning
street images
air pollution
data science
urban pollution
0203 Classical Physics
0406 Physical Geography and Environmental Geoscience
0909 Geomatic Engineering
Publication Status: Published
Article Number: ARTN 3429
Appears in Collections:Faculty of Medicine
School of Public Health

This item is licensed under a Creative Commons License Creative Commons