Abstract. This study investigates long-term trends of criteria air pollutants, including NO2, CO, SO2, O3 and PM2.5, and Ox (meaning NO2+O3) measured in 10 Canadian cities during the last 2 to 3 decades. We also investigated associated driving forces in terms of emission reductions, perturbations due to varying weather conditions and large-scale wildfires, as well as changes in O3 sources and sinks. Two machine learning methods, the random forest algorithm and boosted regression trees, were used to extract deweathered mixing ratios (or mass concentrations) of the pollutants. The Mann–Kendall trend test of the deweathered and original annual average concentrations of the pollutants showed that, on the timescale of 20 years or longer, perturbation due to varying weather conditions on the decadal trends of the pollutants are minimal (within ±2 %) in about 70 % of the studied cases, although it might be larger (but at most 16 %) in the remaining cases. NO2, CO and SO2 showed decreasing trends in the last 2 to 3 decades in all the cities except CO in Montréal. O3 showed increasing trends in all the cities except Halifax, mainly due to weakened titration reaction between O3 and NO. Ox, however, showed decreasing trends in all the cities except Victoria, because the increase in O3 is much less than the decrease in NO2. In three of the five eastern Canadian cities, emission reductions dominated the decreasing trends in PM2.5, but no significant trends in PM2.5 were observed in the other two cites. In the five western Canadian cities, increasing or no significant trends in PM2.5 were observed, likely due to unpredictable large-scale wildfires overwhelming or balancing the impacts of emission reductions on PM2.5. In addition, despite improving air quality during the last 2 decades in most cities, an air quality health index of above 10 (representing a very high risk condition) still occasionally occurred after 2010 in western Canadian cities because of the increased large-scale wildfires.

中文翻译：

---

利用机器学习方法识别加拿大城市大气中标准空气污染物的去风化浓度的十年趋势


摘要。本研究调查了过去 2 至 3 年来在加拿大 10 个城市测量的标准空气污染物的长期趋势，包括 NO2、CO、SO2、O3 和 PM2.5 以及 Ox（即 NO2+O3）。我们还调查了减排、气候条件变化和大规模野火造成的扰动以及 O3 源和汇的变化等相关驱动力。使用随机森林算法和增强回归树这两种机器学习方法来提取污染物的去风化混合比（或质量浓度）。对污染物去风化浓度和原始年平均浓度的Mann-Kendall趋势检验表明，在20年或更长时间的时间尺度上，气候条件变化对污染物年代际趋势的扰动很小（±2 %以内）大约 70% 的研究案例，尽管在其余案例中该比例可能更大（但最多 16%）。过去 2 至 3 年间，除蒙特利尔的 CO 外，所有城市的 NO2、CO 和 SO2 均呈下降趋势。除哈利法克斯外，所有城市的O3均呈现增加趋势，这主要是由于O3与NO之间的滴定反应减弱所致。然而，除维多利亚州外，所有城市的 Ox 均呈下降趋势，因为 O3 的增加量远小于 NO2 的减少量。在加拿大东部五个城市中，有三个城市的PM2.5下降趋势主要是减排量，但其他两个城市没有观察到PM2.5的显着趋势。在加拿大西部的五个城市中，观察到 PM2.5 增加或没有显着趋势，这可能是由于不可预测的大规模野火压倒或平衡了减排对 PM2.5 的影响。 此外，尽管过去20年大多数城市的空气质量有所改善，但2010年之后，由于大规模山火的增加，加拿大西部城市的空气质量健康指数仍然偶尔出现在10以上（代表极高风险状况）。