DOI: 10.1016/j.atmosenv.2019.117065
论文题名: Excitation emission matrix fluorescence spectroscopy for combustion generated particulate matter source identification
作者: Rutherford J.W. ; Dawson-Elli N. ; Manicone A.M. ; Korshin G.V. ; Novosselov I.V. ; Seto E. ; Posner J.D.
刊名: Atmospheric Environment
ISSN: 1352-2310
出版年: 2020
卷: 220 语种: 英语
英文关键词: Combustion
; Deforestation
; Diesel engines
; Fluorescence
; Fluorescence spectroscopy
; Health risks
; Learning algorithms
; Machine learning
; Matrix algebra
; Neural networks
; Pulmonary diseases
; Tobacco
; Convolutional neural network
; Diesel
; Excitation-emission matrix fluorescence spectroscopies
; Excitation-emission matrix fluorescences
; Particulate Matter
; Source apportionment
; Source identification
; Woodsmoke
; Particles (particulate matter)
; cyclohexane
; politef
; polycyclic aromatic hydrocarbon
; air sampling
; anthropogenic source
; artificial neural network
; diesel
; health risk
; life expectancy
; particulate matter
; source apportionment
; source identification
; spectroscopy
; air monitoring
; air sampling
; algorithm
; Article
; asthma
; burn
; chemical composition
; combustion
; convolutional neural network
; diagnostic accuracy
; excitation emission matrix spectrofluorometry
; exhaust gas
; limit of detection
; machine learning
; particulate matter
; personal monitoring
; priority journal
; sensitivity and specificity
; spectrofluorometry
学科: Diesel
; Fluorescence
; Neural network
; Particulate matter
; Source apportionment
; Woodsmoke
中文摘要: The inhalation of particulate matter (PM) is a significant health risk associated with reduced life expectancy due to increased cardio-pulmonary disease and exacerbation of respiratory diseases such as asthma and pneumonia. PM originates from natural and anthropogenic sources including combustion engines, cigarettes, agricultural burning, and forest fires. Identifying the source of PM can inform effective mitigation strategies and policies, but this is difficult to do using current techniques. Here we present a method for identifying PM source using excitation emission matrix (EEM) fluorescence spectroscopy and a machine learning algorithm. We collected combustion generated PM2.5 from wood burning, diesel exhaust, and cigarettes using filters. Filters were weighted to determine mass concentration followed by extraction into cyclohexane and analysis by EEM fluorescence spectroscopy. Spectra obtained from each source served as training data for a convolutional neural network (CNN) used for source identification in mixed samples. This method can predict the presence or absence of the three laboratory sources with an overall accuracy of 89% when the threshold for classifying a source as present is 1.1 μg/m3 in air over a 24-h sampling time. The limit of detection for cigarette, diesel and wood are 0.7, 2.6, 0.9 μg/m3, respectively, in air assuming a 24-h sampling time at an air sampling rate of 1.8 L per minute. We applied the CNN algorithm developed using the laboratory training data to a small set of field samples and found the algorithm was effective in some cases but would require a training data set containing more samples to be more broadly applicable. © 2019 Elsevier Ltd Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/160672
Appears in Collections: 气候变化与战略
There are no files associated with this item.
作者单位: Department of Chemical Engineering, University of Washington, United States; Department of Mechanical Engineering, University of Washington, United States; Department of Family Medicine, University of Washington, United States; Environmental and Occupational Health Sciences, University of Washington, United States; Department of Medicine: Pulmonary, Critical Care and Sleep Medicine, University of Washington, United States
Recommended Citation:
Rutherford J.W.,Dawson-Elli N.,Manicone A.M.,et al. Excitation emission matrix fluorescence spectroscopy for combustion generated particulate matter source identification[J]. Atmospheric Environment,2020-01-01,220