机器学习耦合受体模型揭示驱动因素对PM2.5的影响

PM_2.5主要受排放源、大气化学、气象条件等驱动因素的非线性影响，了解驱动因素对PM_2.5浓度的影响十分重要. 本研究基于南开大学大气环境综合观测超级站的逐时在线观测数据，耦合机器学习方法和受体模型，揭示了驱动因素的重要性以及对PM_2.5浓度的影响. 结果表明:① 2018年11月—2020年10月观测地点的PM_2.5浓度范围为3.21~291.80 μg/m3，采暖季PM_2.5浓度和化学组分均高于非采暖季. ②使用受体模型解析PM_2.5的来源及其贡献，发现观测期间二次源的贡献率(44.7%)最高，其他依次为燃煤源(23.6%)、机动车排放源(11.0%)、扬尘源(9.9%)、生物质燃烧源(7.2%)，工业源的贡献率(3.6%)最小. ③利用随机森林-SHAP模型量化排放源、大气氧化能力、气象条件等驱动因素对PM_2.5浓度的影响，发现观测期间排放源对PM_2.5浓度的影响程度为54.3%，高于其他驱动因素；气象条件对PM_2.5浓度的影响程度次之，为32.4%；大气氧化能力对PM_2.5浓度的影响程度相对较低，为13.3%. 在采暖季和非采暖季，各驱动因素对PM_2.5浓度的重要性在排序上没有变化，然而驱动因素对PM_2.5浓度的影响程度有所不同. 采暖季排放源对PM_2.5浓度的影响程度高于非采暖季，采暖季大气压对PM_2.5浓度的影响程度低于非采暖季. 研究显示，排放源对PM_2.5的影响相对较大,气象条件和大气氧化能力对PM_2.5浓度的影响也不容忽视. 

Machine Learning Coupled with Receptor Model to Reveal the Effect of Driving Factors on PM2.5

There is a non-linear relationship between PM_2.5 and driving factors, such as emission sources, atmospheric chemistry, and meteorological conditions. Hence, it is important to understand the effects of driving factors on PM_2.5 concentration. Based on the hourly online observation data of the Atmospheric Environment Comprehensive Observation Superstation of Nankai University from November 2018 to October 2020, this study combined the machine learning method with the receptor model to reveal the importance of driving factors and their impact on PM_2.5 concentration. The results showed that: (1) PM_2.5 concentration was 3.21-291.80 μg/m3 at the observation site during the measurement campaign, and PM_2.5 concentration and chemical species in heating season were all higher than those in non-heating season. (2) The receptor model identified the source and contribution of PM_2.5, and the contribution of secondary sources during the observation period was the highest (44.7%), followed by coal-fired sources (23.6%), vehicle emission sources (11.0%), dust sources (9.9%), and biomass combustion (7.2%), and the contribution of industrial sources was the lowest (3.6%). (3) This paper also explored the effects of driving factors such as emission sources, atmospheric oxidation capacity, and meteorological conditions on PM_2.5 concentration through random foreat-SHAP model. The effect of emission sources was 54.3%, which was much higher than other factors during the measurement campaign, the effect of meteorological conditions was the second (32.4%), and the effect of atmospheric oxidation capacity was lowest (13.3%). In the heating season and non-heating season, the importance ranking of driving factors on PM_2.5 concentration didn't change, but the influence of the driving factors on PM_2.5 concentration changed significantly. The impact of emission sources on PM_2.5 in the heating season was significantly higher than that in the non-heating season, and the impact of atmospheric pressure on PM_2.5 in the heating season was lower than that in the non-heating season. The research shows that the emission sources have the most important impact on PM_2.5, and the impact of meteorological conditions and atmospheric oxidation capacity on PM_2.5 can′t be ignored.