View in EDS

Optimizing Source Apportionment of OVOCs With Machine Learning‐Enhanced Photochemical Models.

Saved in:
Bibliographic Details
Title: Optimizing Source Apportionment of OVOCs With Machine Learning‐Enhanced Photochemical Models.
Authors: Zou, Y.1,2 (AUTHOR), Guan, X. H.2 (AUTHOR) guanxh@gdsdxy.cn, Flores, R. M.3 (AUTHOR), Yan, X. L.4 (AUTHOR), Liang, X. J.5 (AUTHOR), Fan, L. Y.2 (AUTHOR), Deng, T.1 (AUTHOR), Deng, X. J.1 (AUTHOR), Ye, D. Q.2 (AUTHOR) cedqye@scut.edu.cn, Doskey, P. V.6 (AUTHOR)
Source: Journal of Geophysical Research. Atmospheres. 5/28/2025, Vol. 130 Issue 10, p1-20. 20p.
Subject Terms: *Volatile organic compounds, *Carbon monoxide, Spring, Chemical amplification, Machine learning
Abstract: The photochemical age parameterization model is widely used to analyze primary and secondary sources of oxygenated volatile organic compounds (OVOCs). However, a key challenge lies in selecting appropriate tracers chemicals used to estimate contributions from different emission sources. Accurate tracer selection is crucial for improving source apportionment accuracy, yet it is often constrained by local emission inventories and may not fully capture rapid atmospheric chemical transformations introducing uncertainty in OVOC apportionment. This study presents a novel approach integrating eight different machine learning methods to identify optimal tracers for OVOCs during extreme summer temperatures (experimental group) and average spring temperatures (control group). Our results demonstrated notable differences in tracer effectiveness between these two groups. In the spring, toluene and carbon monoxide (CO) were identified as the most effective tracers for OVOCs with high and low reactivity, respectively. In the summer, acetylene or CO were better suited for moderate and low reactivity OVOCs. By incorporating machine learning for tracer selection, we significantly improved the accuracy of the photochemical age parameterization model. The machine learning outputs correlated well with the model's performance particularly in terms of fitting accuracy of OVOCs. However, extremely high temperatures during summer disrupted the usual patterns of OVOC production and removal, which led to inconsistencies in matching high reactivity OVOCs with their tracers. Future research involves collecting more data on OVOC behavior under high‐temperature conditions and applying Fourier transformation techniques. This will help in identifying characteristic patterns and improving the dynamic accuracy of our model. Plain Language Summary: Our study examines oxygenated volatile organic compounds (OVOCs) in the air, focusing on where they come from and how they change. A key challenge is selecting the right chemical markers to track these changes. Finding the right chemicals is important for accurately identifying these sources. This is difficult because available air pollution data are limited, and air chemistry changes quickly. To address this, we tested eight advanced computational methods to find the best tracers for OVOCs during periods of high ozone, comparing extremely hot summer days (experimental group) with typical spring temperatures (control group). Our results show that the best tracers depend on temperature. In spring, toluene and carbon monoxide (CO) worked well reacting at different rates. In summer, acetylene or CO were more effective for OVOCs with moderate to low reactivity. Using these data‐driven techniques significantly improved our model's accuracy especially in tracking OVOCs. However, extremely high summer temperatures disrupted normal chemical reactions, making it harder to link highly reactive OVOCs to their tracers. Future research will use advanced mathematical analysis to better understand OVOC behavior in hot conditions and further refine our model. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Geophysical Research. Atmospheres is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: GreenFILE
FullText Text:
  Availability: 0
Header DbId: 8gh
DbLabel: GreenFILE
An: 185490203
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Optimizing Source Apportionment of OVOCs With Machine Learning‐Enhanced Photochemical Models.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Zou%2C+Y%2E%22">Zou, Y.</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Guan%2C+X%2E+H%2E%22">Guan, X. H.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> guanxh@gdsdxy.cn</i><br /><searchLink fieldCode="AR" term="%22Flores%2C+R%2E+M%2E%22">Flores, R. M.</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yan%2C+X%2E+L%2E%22">Yan, X. L.</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liang%2C+X%2E+J%2E%22">Liang, X. J.</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Fan%2C+L%2E+Y%2E%22">Fan, L. Y.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Deng%2C+T%2E%22">Deng, T.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Deng%2C+X%2E+J%2E%22">Deng, X. J.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ye%2C+D%2E+Q%2E%22">Ye, D. Q.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> cedqye@scut.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Doskey%2C+P%2E+V%2E%22">Doskey, P. V.</searchLink><relatesTo>6</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Geophysical+Research%2E+Atmospheres%22">Journal of Geophysical Research. Atmospheres</searchLink>. 5/28/2025, Vol. 130 Issue 10, p1-20. 20p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Volatile+organic+compounds%22">Volatile organic compounds</searchLink><br />*<searchLink fieldCode="DE" term="%22Carbon+monoxide%22">Carbon monoxide</searchLink><br /><searchLink fieldCode="DE" term="%22Spring%22">Spring</searchLink><br /><searchLink fieldCode="DE" term="%22Chemical+amplification%22">Chemical amplification</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The photochemical age parameterization model is widely used to analyze primary and secondary sources of oxygenated volatile organic compounds (OVOCs). However, a key challenge lies in selecting appropriate tracers chemicals used to estimate contributions from different emission sources. Accurate tracer selection is crucial for improving source apportionment accuracy, yet it is often constrained by local emission inventories and may not fully capture rapid atmospheric chemical transformations introducing uncertainty in OVOC apportionment. This study presents a novel approach integrating eight different machine learning methods to identify optimal tracers for OVOCs during extreme summer temperatures (experimental group) and average spring temperatures (control group). Our results demonstrated notable differences in tracer effectiveness between these two groups. In the spring, toluene and carbon monoxide (CO) were identified as the most effective tracers for OVOCs with high and low reactivity, respectively. In the summer, acetylene or CO were better suited for moderate and low reactivity OVOCs. By incorporating machine learning for tracer selection, we significantly improved the accuracy of the photochemical age parameterization model. The machine learning outputs correlated well with the model's performance particularly in terms of fitting accuracy of OVOCs. However, extremely high temperatures during summer disrupted the usual patterns of OVOC production and removal, which led to inconsistencies in matching high reactivity OVOCs with their tracers. Future research involves collecting more data on OVOC behavior under high‐temperature conditions and applying Fourier transformation techniques. This will help in identifying characteristic patterns and improving the dynamic accuracy of our model. Plain Language Summary: Our study examines oxygenated volatile organic compounds (OVOCs) in the air, focusing on where they come from and how they change. A key challenge is selecting the right chemical markers to track these changes. Finding the right chemicals is important for accurately identifying these sources. This is difficult because available air pollution data are limited, and air chemistry changes quickly. To address this, we tested eight advanced computational methods to find the best tracers for OVOCs during periods of high ozone, comparing extremely hot summer days (experimental group) with typical spring temperatures (control group). Our results show that the best tracers depend on temperature. In spring, toluene and carbon monoxide (CO) worked well reacting at different rates. In summer, acetylene or CO were more effective for OVOCs with moderate to low reactivity. Using these data‐driven techniques significantly improved our model's accuracy especially in tracking OVOCs. However, extremely high summer temperatures disrupted normal chemical reactions, making it harder to link highly reactive OVOCs to their tracers. Future research will use advanced mathematical analysis to better understand OVOC behavior in hot conditions and further refine our model. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Geophysical Research. Atmospheres is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=8gh&AN=185490203
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1029/2024JD043080
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 20
        StartPage: 1
    Subjects:
      – SubjectFull: Volatile organic compounds
        Type: general
      – SubjectFull: Carbon monoxide
        Type: general
      – SubjectFull: Spring
        Type: general
      – SubjectFull: Chemical amplification
        Type: general
      – SubjectFull: Machine learning
        Type: general
    Titles:
      – TitleFull: Optimizing Source Apportionment of OVOCs With Machine Learning‐Enhanced Photochemical Models.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Zou, Y.
      – PersonEntity:
          Name:
            NameFull: Guan, X. H.
      – PersonEntity:
          Name:
            NameFull: Flores, R. M.
      – PersonEntity:
          Name:
            NameFull: Yan, X. L.
      – PersonEntity:
          Name:
            NameFull: Liang, X. J.
      – PersonEntity:
          Name:
            NameFull: Fan, L. Y.
      – PersonEntity:
          Name:
            NameFull: Deng, T.
      – PersonEntity:
          Name:
            NameFull: Deng, X. J.
      – PersonEntity:
          Name:
            NameFull: Ye, D. Q.
      – PersonEntity:
          Name:
            NameFull: Doskey, P. V.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 28
              M: 05
              Text: 5/28/2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 2169897X
          Numbering:
            – Type: volume
              Value: 130
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: Journal of Geophysical Research. Atmospheres
              Type: main
ResultId 1