Predicting spatial variations in annual average outdoor ultrafine particle concentrations in Montreal and Toronto, Canada: Integrating land use regression and deep learning models.


Journal

Environment international
ISSN: 1873-6750
Titre abrégé: Environ Int
Pays: Netherlands
ID NLM: 7807270

Informations de publication

Date de publication:
08 2023
Historique:
received: 08 02 2023
revised: 28 06 2023
accepted: 19 07 2023
medline: 21 8 2023
pubmed: 7 8 2023
entrez: 6 8 2023
Statut: ppublish

Résumé

Concentrations of outdoor ultrafine particles (UFP; <0.1 µm) and black carbon (BC) can vary greatly within cities and long-term exposures to these pollutants have been associated with a variety of adverse health outcomes. This study integrated multiple approaches to develop new models to estimate within-city spatial variations in annual median (i.e. average) outdoor UFP and BC concentrations as well as mean UFP size in Canada's two largest cities, Montreal and Toronto. We conducted year-long mobile monitoring campaigns in each city that included evenings and weekends. We developed generalized additive models trained on land use parameters and deep Convolutional Neural Network (CNN) models trained on satellite-view images. Using predictions from these models, we developed final combined models. In Toronto, the median observed UFP concentration, UFP size, and BC concentration values were 16,172pt/cm Predictions from these models are available to support future epidemiological research examining long-term health impacts of outdoor UFPs and BC.

Sections du résumé

BACKGROUND
Concentrations of outdoor ultrafine particles (UFP; <0.1 µm) and black carbon (BC) can vary greatly within cities and long-term exposures to these pollutants have been associated with a variety of adverse health outcomes.
OBJECTIVE
This study integrated multiple approaches to develop new models to estimate within-city spatial variations in annual median (i.e. average) outdoor UFP and BC concentrations as well as mean UFP size in Canada's two largest cities, Montreal and Toronto.
METHODS
We conducted year-long mobile monitoring campaigns in each city that included evenings and weekends. We developed generalized additive models trained on land use parameters and deep Convolutional Neural Network (CNN) models trained on satellite-view images. Using predictions from these models, we developed final combined models.
RESULTS
In Toronto, the median observed UFP concentration, UFP size, and BC concentration values were 16,172pt/cm
CONCLUSION
Predictions from these models are available to support future epidemiological research examining long-term health impacts of outdoor UFPs and BC.

Identifiants

pubmed: 37544265
pii: S0160-4120(23)00379-3
doi: 10.1016/j.envint.2023.108106
pii:
doi:

Substances chimiques

Particulate Matter 0
Air Pollutants 0
Environmental Pollutants 0
Soot 0

Types de publication

Journal Article Research Support, Non-U.S. Gov't Research Support, U.S. Gov't, Non-P.H.S.

Langues

eng

Sous-ensembles de citation

IM

Pagination

108106

Informations de copyright

Copyright © 2023 The Author(s). Published by Elsevier Ltd.. All rights reserved.

Déclaration de conflit d'intérêts

Declaration of Competing Interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Scott Weichenthal reports financial support was provided by Health Effects Institute.

Auteurs

Marshall Lloyd (M)

Department of Epidemiology, Biostatistics, and Occupational Health, McGill University, Montreal, Québec H3A 1G1, Canada. Electronic address: marshall.lloyd@mail.mcgill.ca.

Arman Ganji (A)

Department of Civil and Mineral Engineering, University of Toronto, Toronto, Ontario M5S 1A4, Canada. Electronic address: arman.ganji@utoronto.ca.

Junshi Xu (J)

Department of Civil and Mineral Engineering, University of Toronto, Toronto, Ontario M5S 1A4, Canada. Electronic address: junshi.xu@mail.utoronto.ca.

Alessya Venuta (A)

Department of Epidemiology, Biostatistics, and Occupational Health, McGill University, Montreal, Québec H3A 1G1, Canada. Electronic address: alessya.venuta@mail.mcgill.ca.

Leora Simon (L)

Department of Epidemiology, Biostatistics, and Occupational Health, McGill University, Montreal, Québec H3A 1G1, Canada. Electronic address: leora.simon@mail.mcgill.ca.

Mingqian Zhang (M)

Department of Civil and Mineral Engineering, University of Toronto, Toronto, Ontario M5S 1A4, Canada. Electronic address: mingqianz.zhang@utoronto.ca.

Milad Saeedi (M)

Department of Civil and Mineral Engineering, University of Toronto, Toronto, Ontario M5S 1A4, Canada. Electronic address: milad.saeedi@mail.utoronto.ca.

Shoma Yamanouchi (S)

Department of Civil and Mineral Engineering, University of Toronto, Toronto, Ontario M5S 1A4, Canada. Electronic address: shoma.yamanouchi@mail.utoronto.ca.

Joshua Apte (J)

Department of Civil and Environmental Engineering, University of California at Berkeley, Berkeley, CA 94720, United States; School of Public Health, University of California, Berkeley, CA 94720, United States. Electronic address: apte@berkeley.edu.

Kris Hong (K)

Department of Epidemiology, Biostatistics, and Occupational Health, McGill University, Montreal, Québec H3A 1G1, Canada. Electronic address: kris.hong@alumni.ubc.ca.

Marianne Hatzopoulou (M)

Department of Civil and Mineral Engineering, University of Toronto, Toronto, Ontario M5S 1A4, Canada. Electronic address: marianne.hatzopoulou@utoronto.ca.

Scott Weichenthal (S)

Department of Epidemiology, Biostatistics, and Occupational Health, McGill University, Montreal, Québec H3A 1G1, Canada. Electronic address: scottandrew.weichenthal@mcgill.ca.

Articles similaires

Databases, Protein Protein Domains Protein Folding Proteins Deep Learning
India Carbon Sequestration Environmental Monitoring Carbon Biomass
Rivers Turkey Biodiversity Environmental Monitoring Animals
1.00
Iran Environmental Monitoring Seasons Ecosystem Forests

Classifications MeSH