You are here

Comparing the estimated health impacts of long-term exposure to traffic-related air pollution using fixed-site, mobile, and deep learning models

Principal Investigator: 
,

McGill University

This study will evaluate health impacts of long-term exposures to traffic-related air pollution using exposure estimates from fixed-site and mobile measurement campaigns, as well as deep learning models, in Toronto and Montreal, Canada. The investigators will compare exposure estimates generated by these models to present-day and historical measurements, and to each other. 

Funded under
Status: 
Ongoing
Abstract

Scott Weichenthal1, Marianne Hatzopoulou2, Pedro Pinheiro3, Alexandra Schmidt1, Hong Chen4, Josh Apte5, Paul Villeneuve6, Eric Lavigne4, Lauren Pinault7, Michael Tjepkema7, Rick Burnett8

1McGill University, Montreal, QC, Canada; 2University of Toronto, ON, Canada; 3Element AI, Montreal, QC, Canada; 4Health Canada, Ottawa, ON, Canada; 5University of Texas at Austin, TX, USA; 6Carleton University, Ottawa, ON, Canada; 7Statistics Canada, Ottawa, ON, Canada; 8Consultant, Ottawa, ON, Canada

Background: Traffic pollutants such as ultrafine particles (<0.1 ┬Ám; UFPs) and black carbon (BC) vary greatly over small spatial gradients and it remains difficult to evaluate the long-term health impacts of these pollutants. Various exposure assessment methods have been applied to date, including models based on mobile and/or fixed-site monitoring data. However, it is not clear if models based on fixed-site and mobile monitoring data provide similar estimates of long-term spatial contrasts in exposures or if both methods result in comparable estimates of chronic health risks. Moreover, few studies have systematically evaluated the ability mobile and fixed-site models to capture past spatial gradients in traffic-related air pollutants. This is an important question as the validity of exposure models used to estimate long-term health risks relies in part on their ability to capture past exposures. In addition, given the large spatial variability of pollutants such as UFPs and BC, residential exposure estimates may not be optimal and alternative metrics that capture neighbourhood-level trends in population mobility may provide more reliable estimates of long-term exposures and associated health risks.

Methods: Our investigation will apply novel exposure measurement techniques and modelling approaches to address these important knowledge gaps. Specifically, Aim 1 will develop new exposure models for UFPs, BC, and NO2/O3 in Montreal and Toronto, Canada using both mobile and fixed-site monitoring campaigns. We will compare mobile models to long-term fixed-site measurements as well as models based on fixed-site monitoring data. Aim 2 will evaluate the ability of mobile and fixed-site models to estimate past exposures using historical monitoring data in each location. Moreover, using travel survey data, Aim 3 will develop mobility-weighted exposure surfaces that account for neighbourhood-level trends in population mobility as well as changes in mobility patterns over time. As a further innovation, Aim 4 will evaluate a novel exposure modelling approach using deep convolutional neural networks to estimate spatial variations in traffic-related air pollutants using digital images as input. This approach can be conceptualized as a modified version of traditional land use regression models whereby important land use features (captured in images) are learned automatically by the model without having to rely on geographic information system data. Finally, Aim 5 will apply these new exposure models to multiple cycles of the Canadian Census Health and Environment Cohort (1991, 1996, 2001, 2006) for Montreal and Toronto combined (2 million adults). This analysis will focus on non-accidental and cause-specific mortality and will evaluate how the magnitudes and shapes of concentration-response relationships are influenced by different exposure models for UFPs, BC, and NO2/O3 adjusted for PM2.5 mass concentrations and socioeconomic variables. Collectively, our proposed investigation will provide important information on how the choice of exposure model impacts estimates of long-term health risks for UFPs, BC, and NO2/O3.