人为排放及气象因素对空气质量影响的定量分析——以疫情期间邢台市为例

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1336 KB) HTML (0 KB)
输出: BibTeX | EndNote (RIS)

摘要选择河北省邢台市作为研究对象，将2020疫情作为一个极限管控措施下的极限减排实验情景，把2021疫情作为未来常态化疫情防控实验分析情景.与疫情前期对比，两次疫情期间臭氧浓度均有提升且2021疫情时期颗粒物浓度同样有提高，2020疫情时期其他污染物浓度均有不同程度的改善，而与2019历史同期相比，两次疫情期间臭氧浓度同样有升高现象，除此以外，2021疫情时期污染物改善较好.利用长短期记忆网络（LSTM）算法和空气质量预报模式系统（WRF-CMAQ）量化了两次疫情时期气象因素对于污染物浓度变化的影响，根据空气质量模拟法反推了不同污染物受人为影响的浓度变化.实验结果表明，LSTM算法在两次疫情期间的模拟均显示人为影响对污染物产生了负影响（降低了污染物浓度）且在总变化影响中占比较高，而CMAQ模式模拟结果中的气象因素影响占比远高于LSTM算法.CMAQ模式在两次疫情模拟中表现出了不同的结果，在2020疫情中人为影响占据了主导，而在2021疫情中，相比较2020疫情时期，除NO₂外，人类活动对其他污染物的影响均为正值（促进了污染物浓度升高）.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	亓浩雲
	王晓琦
	程水源

关键词 ：机器学习算法, 空气质量模型, 新冠肺炎, 邢台市, PM_2.5

Abstract：Meteorological and human factors during the specific epidemic are critical for effectively evaluating the causes of air quality changes in different areas. This study selected Xingtai City, Hebei Province as the research object, took 2020 epidemic situation as an experimental scenario of extreme emission reduction under the extreme control measures, and 2021 epidemic situation as an experimental analysis scenario of future normalized epidemic prevention and control. Compared with the period prior to the epidemic, the ozone concentration during the two epidemics increased, and the particle concentration during the 2021 epidemic also increased. The concentration of other pollutants during the 2020 epidemic decreased to varying degrees. Compared with the same period in 2019, the ozone concentration during the two epidemics also increased. In addition, the pollutant concentration during the 2021 epidemic declined more. Using LSTM algorithm and WRF-CMAQ model to quantify impacts of meteorological factors on the changes in pollutant concentration during the two epidemic periods. The human-induced changes in different pollutant concentrations were deduced as indicated by the results from the air quality simulation. The simulation of LSTM algorithm during the two outbreaks shows that human being had a negative impact on pollutants (reducing their concentration) and accounted for a high proportion in the total change, while the influence of meteorological factors simulated with CMAQ model was much higher than that with LSTM algorithm. Anthropogenic influences dominated during the 2020 epidemic period, while compared to that during the 2020 epidemic period, the impact of anthropogenic activities on pollutants (except NO₂) was positive (promoting an increase in pollutant concentration) during the 2021 epidemic period.

Key words： machine learning algorithm air quality model COVID-19 Xingtai City PM_2.5

收稿日期: 2022-01-28

PACS:

X511

基金资助:国家自然科学基金资助项目（51638001）

通讯作者: 程水源,教授,chengsy@bjut.edu.cn E-mail: chengsy@bjut.edu.cn

作者简介: 亓浩雲(1995-),男,山东威海人,北京工业大学博士研究生,主要研究方向为大气污染数值模型及优化调控.发表论文7篇.

引用本文:

亓浩雲, 王晓琦, 程水源. 人为排放及气象因素对空气质量影响的定量分析——以疫情期间邢台市为例[J]. 中国环境科学, 2022, 42(8): 3512-3521. QI Hao-yun, WANG Xiao-qi, CHENG Shui-yuan. Quantitative analysis of the impact of anthropogenic emissions and meteorological factors on air quality: Cases during the epidemic in Xingtai City. CHINA ENVIRONMENTAL SCIENCECE, 2022, 42(8): 3512-3521.

链接本文:

http://www.zghjkx.com.cn/CN/ 或 http://www.zghjkx.com.cn/CN/Y2022/V42/I8/3512

[1]	Huang C, Wang T, Niu T, et al. Study on the variation of air pollutant concentration and its formation mechanism during the COVID-19period in Wuhan[J]. Atmospheric Environment, 2021,251(12-14):118276.
[2]	Zhang M, Katiyar A, Zhu S, et al. Impact of reduced anthropogenic emissions during COVID-19 on air quality in India[J]. Atmospheric Chemistry and Physics, 2021,21(5):4025-4037.
[3]	Granella F, Aleluia Reis L, Bosetti V, et al. COVID-19 lockdown only partially alleviates health impacts of air pollution in Northern Italy[J]. Environmental Research Letters, 2021,16:0350123.
[4]	Lovrić M, Pavlović K, Vuković M, et al. Understanding the true effects of the COVID-19lockdown on air pollution by means of machine learning[J]. Environmental Pollution (1987), 2021,274:115900.
[5]	Chen Q X, Huang C L, Yuan Y, et al. Influence of COVID-19 event on air quality and their association in mainland China[J]. Aerosol and Air Quality Research, 2020,20(7):1541-1551.
[6]	Fu F, Purvisroberts K L, Williams B. Impact of the COVID-19pandemic lockdown on air pollution in 20 major cities around the world[J]. Atmosphere, 2020,11(11):1189.
[7]	Rudke A P, Martins J A, de Almeida D S, et al. How mobility restrictions policy and atmospheric conditions impacted air quality in the State of São Paulo during the COVID-19 outbreak[J]. Environmental Research. 2021,198:111255.
[8]	周永生.基于LSTM神经网络的PM2.5预测[D]. 长沙:湖南大学, 2018. Zhou Y S. Prediction of PM2.5 based on LSTM neural network[D]. Changsha:Hunan University, 2018.
[9]	张玉强.研究中国地面臭氧时空分布特征[D]. 北京:清华大学, 2011. Zhang Y Q. Seasonal and spatial variability of surface ozone over China[D]. Beijing:Tsinghua University, 2011.
[10]	聂滕,李璇,王雪松,等.北京市夏季臭氧前体物控制区的分布特征[J]. 北京大学学报(自然科学版), 2014,50(3):557-564. Nie T, Li X, Wang X S, et al. Characteristics of the spatial distributions of ozone-precursor sensitivity regimes in summer over Beijing[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2014,50(3):557-564.
[11]	Grange S K, Carslaw D C, Lewis A C, et al. Random forest meteorological normalisation models for Swiss PM10 trend analysis[J]. Atmospheric Chemistry and Physics, 2018,18(9):6223-6239.
[12]	代兴良,宋国君,姜晓群,等.新冠肺炎疫情对咸阳市空气质量的影响[J]. 中国环境科学, 2021,41(7):3106-3114. Dai X L, Song G J, Jiang X Q, et al. The impact of the COVID-19pandemic on air quality in Xianyang[J]. China Environmental Science, 2021,41(7):3106-3114.
[13]	Bengio, Y, Simard, et al. Learning long-term dependencies with gradient descent is difficult[J]. Neural Networks IEEE Transactions on, 1994,5(2):157-166.
[14]	Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997,9(8):1735-1780.
[15]	张宇,张鹏远,颜永红.基于注意力LSTM和多任务学习的远场语音识别[J]. 清华大学学报(自然科学版), 2018,58(3):249-253. Zhang Y, Zhang P Y, Han Y H. Long short-term memory with attention and multitask learning for distant speech recognition[J]. Journal of Tsinghua University (Science and Technology), 2018, 58(3):249-253.
[16]	Graves A, Mohamed A R, Hinton G. Speech recognition with deep recurrent neural networks[C]. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2013:6645-6649.
[17]	Zhou P, Shi W, Tian J, et al. Attention-based bidirectional long short-term memory networks for relation classification[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2:Short Papers). 2016.
[18]	陈卫华.基于深度学习的上证综指波动率预测效果比较研究[J]. 统计与信息论坛, 2018,33(5):99-106. Chen W H. Forecasting volatility of shanghai composite index with deep learning[J]. Journal of Statistics and Information, 2018,33(5):99-106.
[19]	於雯,周武能.基于LSTM的商品评论情感分析[J]. 计算机系统应用, 2018,27(8):159-163. Yu W, Zhou W N. Sentiment analysis of commodity reviews based on LSTM[J]. Computer Systems & Applications, 2018,27(8):159-163.
[20]	Bo Z, Dan T, Meng L, et al. Trends in China's anthropogenic emissions since 2010as the consequence of clean air actions[J]. Atmospheric Chemistry & Physics Discussions, 2018,18(19):14095-14111.
[21]	关攀博.典型跨区域污染物传输规律及其主控因子识别研究[D]. 北京:北京工业大学, 2021. Guan P B. Study on the characteristics of inter-regional air pollutant transport and the chief control factors in typical urban agglomeration[D]. Beijing:Beijing University of Technology, 2021.
[22]	何哲祥,李雷.一种基于小波变换和LSTM的大气污染物浓度预测模型[J]. 环境工程, 2021,39(3):111-119. He Z X, Li L. An air pollutant concentration prediction model based on wavelet transform and LSTM[J]. Environmental Engineering, 2021,39(3):111-119.
[23]	Zhang Q, Xue D, Liu X, et al. Process analysis of PM2.5 pollution events in a coastal city of China using CMAQ[J]. Journal of Environmental Sciences, 2019,79(5):225-238.
[24]	Chen D, Liu Z, Fast J, et al. Simulations of sulfate-nitrate-ammonium (SNA) aerosols during the extreme haze events over northern China in October 2014[J]. Atmospheric Chemistry and Physics, 2016,16(16):10707-10724.
[25]	芦华,谢旻,吴钲,等.基于机器学习的成渝地区空气质量数值预报PM2.5订正方法研究[J]. 环境科学学报, 2020,40(12):4419-4431. Lu H, Xie M, Wu Z, et al. Adjusting PM2.5prediction of the numerical air quality forecast model based on machine learning methods in Chengyu region[J]. Acta Scientiae Circumstantiae, 2020,40(12):4419-4431.
[26]	Li L, Li Q, Huang L, et al. Air quality changes during the COVID-19lockdown over the Yangtze River Delta Region:An insight into the impact of human activity pattern changes on air pollution variation[J]. Science of the Total Environment, 2020,732:139282.
[27]	Lian X, Huang J, Huang R, et al. Impact of city lockdown on the air quality of COVID-19-hit of Wuhan city[J]. Science of the Total Environment, 2020,42:140556.
[28]	Wang S, Zhang Y, Ma J, et al. Responses of decline in air pollution and recovery associated with COVID-19lockdown in the Pearl River Delta[J]. Science of the Total Environment, 2020,756:143868.
[29]	Wang J, Xu X, Wang S, et al. Heterogeneous effects of COVID-19lockdown measures on air quality in Northern China[J]. Applied Energy, 2020,282:116179.
[30]	余益军,孟晓艳,王振,等.京津冀地区城市臭氧污染趋势及原因探讨[J]. 环境科学, 2020,41(1):106-114. Yu Y J, Meng X Y, Wang Z, et al. Driving factors of the significant increase in surface ozone in the Beijing-Tianjin-Hebei Region, China, during 2013~2018[J]. Environmental Science, 2020,41(1):106-114.
[31]	Aneja V P, Agarwal A, Roelle P A, et al. Measurements and analysis of criteria pollutants in New Delhi, India[J]. Environment International, 2002,27(1):35-42.