基于机器学习算法的新冠疫情管控对河南省空气质量影响的模拟分析

全国各地为了减少新冠疫情对社会和人民生活的影响，采取了必要的防疫防控措施，这些措施对空气质量的变化产生了重要的影响，此外空气质量的变化与气象条件也存在很大的关系.通过对河南省疫情前（1月1~26日）和疫情管控期（1月27日~2月29日）这两阶段的空气质量分析对比发现，整个河南省除了O₃浓度上升了69.64%外，PM_2.5、PM₁₀、SO₂、CO和NO₂分别降低了36.89%、34.18%、19.43%、29.85%和58.51%；通过机器学习算法中的长短期记忆型网络（LSTM）模拟显示，气象条件引起污染物浓度的降幅大部分在15%~30%之间；人为排放减少引起的污染物浓度的降幅大部分在6%~40%之间.O₃在疫情期间上升过程中，气象条件和人为排放两种因素分别占了34.84%和34.81%.结果表明，疫情管控期间，河南省空气质量总体上有所改善，但是也有重污染发生，其中O₃的浓度对于疫情管控减排的影响不明显，呈负相关，需要进一步探索引起臭氧浓度上升的原因，以此帮助政府合理控制臭氧等前体污染物的减排比例.

Simulation Analysis of the Impact of COVID-19 Pandemic Control on Air Quality in Henan Province based on Machine Learning Algorithm

To reduce the risks of COVID-19 on society and the health of the general public, necessary prevention and control measures were implemented throughout China in 2020. Consequently, air quality was greatly improved due to lower emissions. However, the improvement of air quality could also be closely related to meteorological conditions. During quarantine (January 27 to February, 2020), reductions were observed in the concentration of all air pollutants in Henan Province (PM_2.5, PM₁₀, SO₂, CO, and NO₂ decreased by 36.89%, 34.18%, 19.43%, 29.85%, and 58.51%, respectively) relative to measurements taken from January 1 to 26, 2020. The only exception was for the concentration of O₃, which increased by 69.64%. This study evaluates the importance of meteorological conditions in air pollution, through simulation with a long-and-short-term memory network (LSTM) and a machine learning algorithm. Results show that meteorological conditions play a crucial role in air pollutant formation. Given favorable meteorological factors, the concentrations of pollutants could be reduced by 15%-30%, while the reduction due to anthropogenic emission control ranges from 6%-40%. During the epidemic, meteorological conditions and human emissions accounted for 34.84% and 34.81% of the increase in O₃ concentration, respectively. The results show that primary pollutant concentrations are more sensitive to the intensity of anthropogenic emissions. However, secondary pollutants are more dependent on meteorological factors. Furthermore, a nonlinear relationship has been identified between O₃ concentration and to emission intensity. Further investigation into the causes of the rise in O₃ concentration is necessary to gain a greater understanding and better control of particulate matter and O₃ pollution.