中文版 | English
题名

基于排放源的中国黑碳气溶胶浓度机器学习空间预测方法

姓名
姓名拼音
HUANG Kai
学号
12032374
学位类型
硕士
学位专业
0856 材料与化工
学科门类/专业学位类别
0856 材料与化工
导师
李莹
导师单位
海洋科学与工程系
外机构导师
刘婵芳
外机构导师单位
广东省深圳生态环境监测中心站
论文答辩日期
2022-05-10
论文提交日期
2022-06-16
学位授予单位
南方科技大学
学位授予地点
深圳
摘要

黑碳(BC)作为一种吸收性气溶胶,能够强烈吸收太阳辐射并加热周围大气,与气候变化、空气质量和人类健康都有重要影响。当前中国由于地基观测BC浓度成本高,站点少,因此高时空分辨率近地面BC浓度数据较为缺乏。机器学习方法在过去10年里迅速发展,在处理非线性问题上具有很好的效果。本研究第一次将机器学习方法与卫星遥感相结合对大范围内的BC浓度进行研究,提出了基于黑碳排放源,结合卫星遥感的气溶胶光学厚度、以及气象要素等辅助变量,使用随机森林这一机器学习模型预测中国大陆近地面BC浓度空间分布。对比了不同排放源在不同年份下的模型构建和预测BC浓度空间分布状况,发现所有模型都能达到较高的预测精度(日均:决定系数(R2)>0.73,RMSE约为1.8 μgm-3,MAE约为1.0 μgm-3),均优于当前卫星遥感反演BC浓度物理模型精度(日均:R2=0.545)。本研究将机器学习和卫星遥感的优势相结合在预测BC浓度的精度上取得了比现有物理模型更好的性能和精度,并且能覆盖大面积区域。本研究也可以获得较准确的近地面BC浓度空间分布数据集,这有利于实现对BC浓度的监测,并为大气污染防治以及碳中和碳达峰政策的落实提供数据支持和科学依据。

关键词
语种
中文
培养类别
独立培养
入学年份
2020
学位授予年份
2022-06
参考文献列表

[1] 张华,王志立.黑碳气溶胶气候效应的研究进展[J].气候变化研究进展,2009,5(06):311-317.
[2] 蒋磊,汤莉莉,潘良宝,刘丹彤,花艳,张运江,周宏仓,崔玉航.南京冬季重污染过程中黑碳气溶胶的混合态及粒径分布[J].环境科学,2017,38(01):13-21.
[3] 陈琛,王娟,聂亚光,王希楠,许安.大气中黑碳的健康效应及机制研究进展[J].生态毒理学报,2018,13(01):31-39.
[4] 于勇,吴自越.浅析中国区域黑碳气溶胶的气候效应[J].科技风,2020(34):160-161.
[5] Jacobson, Mark Z. 2001. Strong radiative heating due to the mixing state of black carbon in atmospheric aerosols. Nature 409, no. 6821 (2001): 695-697695–697.
[6] Bond T C, Doherty S J, Fahey D W, et al. Bounding the role of black carbon in the climate system: A scientific assessment [J]. Journal of Geophysical Research: Atmospheres, 2013, 118(11): 5380-5552.
[7] Lelieveld, Jos, John S. Evans, et al. The contribution of outdoor air pollution sources to premature mortality on a global scale. Nature 525, no. 7569 (2015): 367-371.
[8] Anderson, Jonathan O., Josef G, et al. Clearing the air: a review of the effects of particulate matter air pollution on human health. Journal of Medical Toxicology, 8, no. 2 (2012): 166-175.
[9] Cape J N, Coyle M, Dumitrean P. The atmospheric lifetime of black carbon[J], Atmospheric Environment, 2012 59(7):256-263.
[10] Menon, Surabi, Hansen, J, et al. Climate effects of black carbon aerosols in China and India. Science, 297, no. 5590 (2002): 2250-2253.
[11] Cooke W F, Ramaswamy V, Kasibhatla P. A general circulation model study of the global carbonaceous aerosol distribution[J]. Journal of Geophysical Research Atmospheres, 2002,
[12] Yuan QQ, Shen HF, Li TW, et al. Deep learning in environmental remote sensing: Achievements and challenges. Remote Sensing of Environment 241 (2020): 111716.
[13] Zhao WZ, Du SH. Learning multiscale and deep representations for classifying remotely sensed imagery. ISPRS Journal of Photogrammetry and Remote Sensing 113 (2016): 155-165.
[14] Yang LQ, Jia K, Liang, SL, et al. A Robust Algorithm for Estimating Surface Fractional Vegetation Cover from Landsat Data. Remote Sensing 9, no. 8 (2017): 857.
[15] Qin WM, Wang LC, Lin AW, et al. Improving the Estimation of Daily Aerosol Optical Depth and Aerosol Radiative Effect Using an Optimized Artificial Neural Network. Remote Sensing 10, no. 7 (2018): 1022.
[16] Wen CC, Liu S, Yao XJ, et al. A novel spatiotemporal convolutional long short-term neural network for air pollution prediction. Science of The Total Environment 654 (2019): 1091-1099.
[17] Jiang H, Lu N, Qin J, et al. A deep learning algorithm to estimate hourly global solar radiation from geostationary satellite data. Renewable and Sustainable Energy Reviews 114 (2019): 109327.
[18] Qin DM, Yu J, Zou GJ, et al. A Novel Combined Prediction Scheme Based on CNN and LSTM for Urban PM2.5 Concentration. IEEE Access 7 (2019): 20050-20059.
[19] Xiao QY, Hu XF, Jessica H B, et al. Estimating PM2. 5 concentrations in the conterminous United States using the random forest approach. Environmental science & technology 51, no. 12 (2017): 6936-6944.
[20] Yeganeh, Bijan, Hewson M G, et al. A satellite-based model for estimating PM2.5 concentration in a sparsely populated environment using soft computing techniques. Environmental Modelling & Software 88 (2017): 84-92.
[21] Di Q, Amini H, Shi LH, et al. An ensemble-based model of PM2.5 concentration across the contiguous United States with high spatiotemporal resolution. Environment International 130 (2019): 104909.
[22] Wei J, Huang W, Li ZQ, et al. Estimating 1-km-resolution PM2.5 concentrations across China using the space-time random forest approach. Remote Sensing of Environment 231 (2019): 111221.
[23] Wei J, Li ZQ, Lyapustin A, et al. Reconstructing 1-km-resolution high-quality PM2.5 data records from 2000 to 2018 in China: spatiotemporal variations and policy implications. Remote Sensing of Environment 252 (2021): 112136.
[24] 许黎,王亚强,陈振林,等.黑碳气溶胶研究进展i:排放、清除和浓度m.地球科学进展,2006,21(4):352-360.
[25] Cooke W F, Wilson J J. A global black carbon aerosol model[J]. Journal of Geophysical Research Atmospheres, 1996, 101(D14):19395-19409.
[26] DahlkotterF, Gysel M, Sauer D, et al. The Pagami Creek smoke plume after long-range transport to the upper troposphere over Europe - aerosol properties and black carbon mixing state[J]. Atmospheric Chemistry & Physics, 2014,13(11):28751-28818.
[27] Ramachandran S, Rajesh TA, Cherian R. Black carbon aerosols over source vs. background region: Atmospheric boundary layer influence, potential source regions, and model comparison. Atmospheric Research 256 (2021): 105573.
[28] Wang R, Tao S, Wang WT, et al. Black Carbon Emissions in China from 1949 to 2050. Environ. Sci. Technol. 46, no. 14 (2012): 7595-7603.
[29] Wang R, Tao S, Shen HZ, et al. Trend in Global Black Carbon Emissions from 1960 to 2007. Environ. Sci. Technol. 48, no. 12 (2014): 6780-6787.
[30] Zheng H, Kong SF, Zheng MM, et al. A 5.5-year observations of black carbon aerosol at a megacity in Central China: Levels, sources, and variation trends. Atmospheric Environment 232 (2020): 117581.
[31] Singh N, Mhawish A, Banerjee T, et al. Association of aerosols, trace gases and black carbon with mortality in an urban pollution hotspot over central Indo-Gangetic Plain. Atmospheric Environment 246 (2021): 118088.
[32] Wu Y, Cheng TH, Liu DT, et al. Light Absorption Enhancement of Black Carbon Aerosol Constrained by Particle Morphology. Environ. Sci. Technol. 52, no. 12 (2018): 6912–6919.
[33] Kahnert, Michale, Kanngießer F. Modelling optical properties of atmospheric black carbon aerosols. Journal of Quantitative Spectroscopy and Radiative Transfer 244 (2020): 106849.
[34] Yang JH, Ji ZM, Kang SC, et al. Contribution of South Asian biomass burning to black carbon over the Tibetan Plateau and its climatic impact. Environmental Pollution 270 (2021): 116195.
[35] Peralta O, Ortínez-Alvarez A, Basaldud R, et al. Atmospheric black carbon concentrations in Mexico. Atmospheric Research 230 (2019): 104626.
[36] 马井会,郑有飞,张华.黑碳气溶胶光学厚度的全球分布及分析[J].气象科学,2007(05):549-556.
[37] Chung SH, Seinfeld J H. Global distribution and climate forcing of carbonaceous aerosols. Journal of Geophysical Research: Atmospheres, 2002. 107(D19): p. AAC 14-1-AAC 14-33.
[38] 杨晓玥. 中国东部地区2000-2016年黑碳气溶胶的时空分布特征研究[D].南京信息工程大学,2020.
[39] 曹阳,安欣欣,刘保献,景宽,王琴,罗霄旭.北京市黑碳气溶胶浓度特征及其主要影响因素[J].环境科学,2021,42(12):5633-5643.
[40] 王璐,袁亮,张小玲,贾月涛.成都地区黑碳气溶胶变化特征及其来源解析[J].环境科学,2020,41(04):1561-1572.
[41] Zhao JW, Liu YX, Shan M, et al. Characteristics, potential regional sources and health risk of black carbon based on ground observation and MERRA-2 reanalysis data in a coastal city, China. Atmospheric Research 256 (2021): 105563.
[42] Xiao HW, Mao DY, Huang LL, et al. Evaluation of black carbon source apportionment based on one year’s daily observations in Beijing. Science of The Total Environment 773 (2021): 145668.
[43] Zhang Q, Shen ZX, Zhang T, et al. Spatial distribution and sources of winter black carbon and brown carbon in six Chinese megacities. The Science of the total environment 762 (2021) 143075–143075.
[44] 张霞,余益军,解淑艳,孟晓艳,齐炜红,王帅,潘本锋.全国大气背景地区黑碳浓度特征[J].中国环境监测,2018,34(01):32-40.
[45] 刘立忠,王宇翔,么远,韩婧,李文韬,韩泽龙.西安市黑碳气溶胶浓度特征及与气象因素和常规污染物相关性[J].中国环境监测,2016,32(05):45-50.
[46] 井安康. 长三角地区黑碳的污染特征和来源分析[D].南京信息工程大学,2019.
[47] Cui FP, Pei SX, Chen MD, et al. Absorption enhancement of black carbon and the contribution of brown carbon to light absorption in the summer of Nanjing, China. Atmospheric Pollution Research 12, no. 2 (2021): 480–487.
[48] Wyche K P, Cordell R L, Smith M L, et al. The spatio-temporal evolution of black carbon in the North-West European ‘air pollution hotspot.’. Atmospheric Environment 243 (2020): 117874.
[49] Chen W, Wang Z, Zhao HM, et al. A novel way to calculate shortwave black carbon direct radiative effect. Science of The Total Environment 756 (2021): 142961.
[50] 王月华,汤莉莉,邹强,丁铭.黑碳气溶胶的测量方法对比研究[J].环境工程,2015,33(04):142-145+120.
[51] 屈文军,王亚强,王丹,盛立芳.简评碳气溶胶观测研究中的不确定性[J].气候与环境研究,2009,14(02):201-217.
[52] Schuster G L, Dubovik O, Holben B N, et al. Inferring black carbon content and specific absorption from Aerosol Robotic Network (AERONET) aerosol retrievals. Journal of Geophysical Research: Atmospheres 110, no. D10 (2005).
[53] Wang LL, Li ZQ, Tian QJ, et al. Estimate of aerosol absorbing components of black carbon, brown carbon, and dust from ground‐based remote sensing data of sun‐sky radiometers. Journal of Geophysical Research: Atmospheres, 118, no. 12 (2013) 6534-6543.
[54] 包方闻. 大气气溶胶光学特性及黑碳浓度卫星遥感反演研究[D].中国科学院大学(中国科学院遥感与数字地球研究所),2018.
[55] Bao FW., Cheng TH, Li Y, et al. Retrieval of black carbon aerosol surface concentration using satellite remote sensing observations. Remote Sensing of Environment 226 (2019): 93–108.
[56] Bao FW, Li Y, Cheng TH, et al. Estimating the Columnar Concentrations of Black Carbon Aerosols in China Using MODIS Products. Environ. Sci. Technol. 54, no. 18 (2020): 11025-11036.
[57] 杨怡敏.气候变化下的黑碳气溶胶分析与应对[J].生态经济,2014,30(02):37-40.
[58] Fung, Pak L, Martha.A, et al. Input-Adaptive Proxy for Black Carbon as a Virtual Sensor 20, no. 1 (2019): 182.
[59] Fung, Pak L, Martha A, et al. Evaluation of white-box versus black-box machine learning models in estimating ambient black carbon concentration. Journal of Aerosol Science 152 (2021): 105694.
[60] Zhang F, Cheng HR, Wang ZW, et al. Fine particles (PM2.5) at a CAWNET background site in Central China: Chemical compositions, seasonal variations and regional pollution events. Atmospheric environment 86 (2014): 193-202.
[61] 戴明明. 中国黑碳气溶胶时空分布及瓦里关站影响因素研究[D].南京信息工程大学,2021.
[62] Drinovec L, Močnik G, Zotter P, et al. The “dual-spot” Aethalometer: an improved measurement of aerosol black carbon with real-time loading compensation. Atmos. Meas. Tech. 8, no. 5 (2015): 1965–1979.
[63] 吴兑,毛节泰,邓雪娇,等.珠江三角洲黑碳气溶胶及其辐射特性的观测研究[J].中国科学,2009,39(11):1542-1553.
[64] Fu X, Wang T, Wang SX, et al. Anthropogenic Emissions of Hydrogen Chloride and Fine Particulate Chloride in China. Environmental Science & Technology 52, no. 3 (2018): 1644–1654.
[65] Li M, Zhang Q, Kurokawa J, et al. MIX: a mosaic Asian anthropogenic emission inventory under the international collaboration framework of the MICS-Asia and HTAP. Atmospheric Chemistry and Physics 17, no. 2 (2017): 935–963.
[66] Werf V D, Guido R, Randerson J T, et al. Global fire emissions and the contribution of deforestation, savanna, forest, agricultural, and peat fires (1997–2009). Atmospheric Chemistry and Physics 10, no. 23 (2010): 11707–11735.
[67] Wang R, Tao S, Ciais P, et al. High-resolution mapping of combustion processes and implications for CO2 emissions. Atmos. Chem. Phys. 13, no. 10 (2013): 5189–5203.
[68] Meng WJ, Zhong QR, Yun X, et al. Improvement of a Global High-Resolution Ammonia Emission Inventory for Combustion and Industrial Sources with New Data from the Residential and Transportation Sectors. Environ. Sci. Technol. 51, no. 5 (2017): 2821–2829.
[69] Pitchford M, Malm W, Schichtel B, et al. Revised algorithm for estimating light extinction from IMPROVE particle speciation data [J]. Journal of the Air Waste Management Association, 2007, 57(11);1326-1336.
[70] Bais A F, Kazantzidis A, Kazadzis S, et al. Deriving an effective aerosol single scattering albedo from spectral surface UV irradiance measurements. Atmospheric Environment 39, no. 6 (2005): 1093–1102.
[71] Lyapustin A, Wang Y, Laszlo I, et al. Multiangle implementation of atmospheric correction (MAIAC): 2. Aerosol algorithm. Journal of Geophysical Research: Atmospheres 116, no. D3 (2011).
[72] Lyapustin A, Wang Y, Korkin S, et al. MODIS Collection 6 MAIAC algorithm. Atmospheric Measurement Techniques 11, no. 10 (2018): 5741–5765.
[73] 孙嘉胤,吴晟,吴兑,李梅,邓涛,杨闻达,程鹏,梁粤,谭健,何国文,成春雷,李磊,周振.广州城区黑碳气溶胶吸光增强特性研究[J].中国环境科学,2020,40(10):4177-4189.
[74] 谭天怡,郭松,吴志军,何凌燕,黄晓锋,胡敏.老化过程对大气黑碳颗粒物性质及其气候效应的影响[J].科学通报,2020,65(36):4235-4250.
[75] Dee D P, Uppala S M, Simmons A J, et al. The ERA-Interim reanalysis: configuration and performance of the data assimilation system. Quarterly Journal of the Royal Meteorological Society 137, NO. 656 (2011): 553–597.
[76] 齐孟姚,王丽涛,张城瑜,马笑,赵乐,纪尚平,鲁晓晗,王雨.邯郸市黑碳气溶胶浓度变化及影响因素分析[J].环境科学学报,2018,38(05):1751-1758.
[77] Xiao QY, Chang HH, Geng GN, et al. An ensemble machinelLearning model to predict historical PM2.5 concentrations in China from satellite data. Environ. Sci. Technol. 52, NO. 22 (2018): 13260–13269.
[78] Breiman L. Random Forests. Machine Learning 45, no. 1 (2001): 5–32.钟杰,翟崇治,余家燕,许丽萍,彭超,陈丽.重庆市核心区黑碳气溶胶浓度特征以及影响因素分析[J].环境工程学报,2016,10(02):805-810.

所在学位评定分委会
海洋科学与工程系
国内图书分类号
X831
来源库
人工提交
成果类型学位论文
条目标识符http://sustech.caswiz.com/handle/2SGJ60CL/335847
专题工学院_海洋科学与工程系
推荐引用方式
GB/T 7714
黄锴. 基于排放源的中国黑碳气溶胶浓度机器学习空间预测方法[D]. 深圳. 南方科技大学,2022.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可 操作
12032374-黄锴-海洋科学与工程系(12502KB)----限制开放--请求全文
个性服务
原文链接
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
导出为Excel格式
导出为Csv格式
Altmetrics Score
谷歌学术
谷歌学术中相似的文章
[黄锴]的文章
百度学术
百度学术中相似的文章
[黄锴]的文章
必应学术
必应学术中相似的文章
[黄锴]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
[发表评论/异议/意见]
暂无评论

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。