Department of Epidemiology, Biostatistics, and Occupational Health, McGill University, Montreal, Québec H3A 1G1, Canada.
Department of Civil and Mineral Engineering, University of Toronto, Toronto, Ontario M5S 1A4, Canada.
Environ Int. 2023 Aug;178:108106. doi: 10.1016/j.envint.2023.108106. Epub 2023 Jul 22.
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, 33.7 nm, and 1225 ng/m, respectively. In Montreal, the median observed UFP concentration, UFP size, and BC concentration values were 14,702pt/cm, 29.7 nm, and 1060 ng/m, respectively. For all pollutants in both cities, the proportion of spatial variation explained (i.e., R) was slightly greater (1-2 percentage points) for the combined models than the generalized additive models and a greater (approximately 10 percentage points) than the deep CNN models. The Toronto combined model R values in the test set were 0.73, 0.55, and 0.61 for UFP concentrations, UFP size, and BC concentration, respectively. The Montreal combined model R values were 0.60, 0.49, and 0.60 for UFP concentration, UFP size, and BC concentration models respectively. For each pollutant, predictions from the combined, deep CNN, and generalized additive models were highly correlated with each other and differences between models were explored in sensitivity analyses.
Predictions from these models are available to support future epidemiological research examining long-term health impacts of outdoor UFPs and BC.
城市内的室外超细颗粒物（UFP；<0.1μm）和黑碳（BC）浓度差异较大，长期暴露于这些污染物与多种不良健康结果有关。
本研究综合多种方法，建立新模型以估计加拿大两个最大城市蒙特利尔和多伦多的城市内年度中值（即平均）户外 UFP 和 BC 浓度以及 UFP 平均粒径的空间变化。
我们在每个城市进行了为期一年的移动监测活动，包括晚上和周末。我们开发了基于土地利用参数的广义加性模型和基于卫星图像的深度卷积神经网络（CNN）模型。使用这些模型的预测值，我们开发了最终的综合模型。
在多伦多，观测到的 UFP 浓度中位数、UFP 粒径中位数和 BC 浓度中位数分别为 16172pt/cm、33.7nm 和 1225ng/m。在蒙特利尔，观测到的 UFP 浓度中位数、UFP 粒径中位数和 BC 浓度中位数分别为 14702pt/cm、29.7nm 和 1060ng/m。对于两个城市的所有污染物，综合模型解释的空间变化比例（即 R）略高于（1-2 个百分点）广义加性模型，高于深度 CNN 模型（约 10 个百分点）。多伦多综合模型在测试集中的 R 值分别为 0.73、0.55 和 0.61，用于 UFP 浓度、UFP 粒径和 BC 浓度。蒙特利尔综合模型的 R 值分别为 0.60、0.49 和 0.60，用于 UFP 浓度、UFP 粒径和 BC 浓度模型。对于每种污染物，综合模型、深度 CNN 模型和广义加性模型的预测结果彼此高度相关，并且在敏感性分析中探讨了模型之间的差异。
这些模型的预测结果可用于支持未来研究户外 UFP 和 BC 对长期健康影响的流行病学研究。
