TY - JOUR
T1 - Source-apportionment and spatial distribution analysis of VOCs and their role in ozone formation using machine learning in central-west Taiwan
AU - Mishra, Manisha
AU - Chen, Pin Hsin
AU - Bisquera, Wilfredo
AU - Lin, Guan Yu
AU - Le, Thi Cuc
AU - Dejchanchaiwong, Racha
AU - Tekasakul, Perapong
AU - Jhang, Ciao Wei
AU - Wu, Ci Jhen
AU - Tsai, Chuen Jinn
N1 - Publisher Copyright:
© 2023 Elsevier Inc.
PY - 2023/9/1
Y1 - 2023/9/1
N2 - This study assessed the machine learning based sensitivity analysis coupled with source-apportionment of volatile organic carbons (VOCs) to look into new insights of O3 pollution in Yunlin County located in central-west region of Taiwan. One-year (Jan 1 to Dec 31, 2021) hourly mass concentrations data of 54 VOCs, NOX, and O3 from 10 photochemical assessment monitoring stations (PAMs) in and around the Yunlin County were analyzed. The novelty of the study lies in the utilization of artificial neural network (ANN) to evaluate the contribution of VOCs sources in O3 pollution in the region. Firstly, the station specific source-apportionment of VOCs were carried out using positive matrix factorization (PMF)—resolving six sources viz. AAM: aged air mass, CM: chemical manufacturing, IC: Industrial combustion, PP: petrochemical plants, SU: solvent use and VE: vehicular emissions. AAM, SU, and VE constituted cumulatively more than 65% of the total emission of VOCs across all 10 PAMs. Diurnal and spatial variability of source-segregated VOCs showed large variations across 10 PAMs, suggesting for distinctly different impact of contributing sources, photo-chemical reactivity, and/or dispersion due to land-sea breezes at the monitoring stations. Secondly, to understand the contribution of controllable factors governing the O3 pollution, the output of VOCs source-contributions from PMF model along with mass concentrations of NOX were standardized and first time used as input variables to ANN, a supervised machine learning algorithm. ANN analysis revealed following order of sensitivity in factors governing the O3 pollution: VOCs from IC > AAM > VE ≈ CM ≈ SU > PP ≈ NOX. The results indicated that VOCs associated with IC (VOCs-IC) being the most sensitive factor which need to be regulated more efficiently to quickly mitigate the O3 pollution across the Yunlin County.
AB - This study assessed the machine learning based sensitivity analysis coupled with source-apportionment of volatile organic carbons (VOCs) to look into new insights of O3 pollution in Yunlin County located in central-west region of Taiwan. One-year (Jan 1 to Dec 31, 2021) hourly mass concentrations data of 54 VOCs, NOX, and O3 from 10 photochemical assessment monitoring stations (PAMs) in and around the Yunlin County were analyzed. The novelty of the study lies in the utilization of artificial neural network (ANN) to evaluate the contribution of VOCs sources in O3 pollution in the region. Firstly, the station specific source-apportionment of VOCs were carried out using positive matrix factorization (PMF)—resolving six sources viz. AAM: aged air mass, CM: chemical manufacturing, IC: Industrial combustion, PP: petrochemical plants, SU: solvent use and VE: vehicular emissions. AAM, SU, and VE constituted cumulatively more than 65% of the total emission of VOCs across all 10 PAMs. Diurnal and spatial variability of source-segregated VOCs showed large variations across 10 PAMs, suggesting for distinctly different impact of contributing sources, photo-chemical reactivity, and/or dispersion due to land-sea breezes at the monitoring stations. Secondly, to understand the contribution of controllable factors governing the O3 pollution, the output of VOCs source-contributions from PMF model along with mass concentrations of NOX were standardized and first time used as input variables to ANN, a supervised machine learning algorithm. ANN analysis revealed following order of sensitivity in factors governing the O3 pollution: VOCs from IC > AAM > VE ≈ CM ≈ SU > PP ≈ NOX. The results indicated that VOCs associated with IC (VOCs-IC) being the most sensitive factor which need to be regulated more efficiently to quickly mitigate the O3 pollution across the Yunlin County.
KW - Artificial neural network (ANN)
KW - Ozone
KW - Positive matrix factorization (PMF)
KW - Source tracing
KW - Volatile organic compounds (VOCs)
UR - http://www.scopus.com/inward/record.url?scp=85161286603&partnerID=8YFLogxK
U2 - 10.1016/j.envres.2023.116329
DO - 10.1016/j.envres.2023.116329
M3 - Article
C2 - 37276975
AN - SCOPUS:85161286603
SN - 0013-9351
VL - 232
JO - Environmental Research
JF - Environmental Research
M1 - 116329
ER -