View in EDS

High‐Resolution Mapping of Regional NMVOCs Using the Fast Space‐Time Light Gradient Boosting Machine (LightGBM).

Saved in:
Bibliographic Details
Title: High‐Resolution Mapping of Regional NMVOCs Using the Fast Space‐Time Light Gradient Boosting Machine (LightGBM).
Authors: Lu, Bingqing1 (AUTHOR), Liu, Chao1 (AUTHOR), Meng, Xue1 (AUTHOR), Zhang, Zekun1 (AUTHOR), Herrmann, Hartmut2 (AUTHOR), Li, Xiang1,3 (AUTHOR) lixiang@fudan.edu.cn
Source: Journal of Geophysical Research. Atmospheres. 11/27/2023, Vol. 128 Issue 22, p1-16. 16p.
Subject Terms: *Air pollutants, *Air pollution, *Volatile organic compounds, Machine learning, Spacetime, Spatial resolution
Geographic Terms: Shanghai (China)
Abstract: Accurate spatiotemporal estimation of non‐methane volatile organic compounds (NMVOCs) plays a pivotal role in establishing sophisticated early warning systems and formulating strategies to combat air pollution. Despite these critical applications, robust estimation of high spatiotemporal resolution NMVOCs concentrations remains a challenge. In this study, we develop a space‐time Light Gradient Boosting Machine (STLGB) model, which successfully renders hourly maps of NMVOCs concentrations across Shanghai from 2019 to 2022 by integrating spatiotemporal information. After extensive training, the STLGB model demonstrates remarkable estimation performance for NMVOCs, accounting for multiple spatiotemporal variables (R2 = 0.92, RMSE = 34.52 ppb). With the developed model, we provide first high‐resolution (1 km) hourly NMVOCs concentration maps, uncovering previously overlooked spatiotemporal variations. Further, SHapley Additive exPlanation (SHAP) regression values reveal significant local interpretation capabilities of the STLGB model, emphasizing the strong influence of emissions on NMVOCs estimation, whilst acknowledging the important contribution of space and time term. Our study of the pandemic lockdown further showcases the model's adaptability to unique events influenced by policy changes. The superior performance of the STLGB model, with its minimal computational memory requirements and faster speed, makes it an ideal tool for air pollutant estimation, adaptable to any region with NMVOCs monitoring capabilities. Plain Language Summary: Non‐methane Volatile organic compounds (NMVOCs) are significant air pollutants that have severe effects on health and the environment. Despite the availability of VOCs monitoring stations that can provide data with good temporal resolution, the low spatial resolution of these stations remains a challenge. Accurate estimation of NMVOCs concentrations requires new methods to address these spatial resolution issues. In recent years, machine learning‐based models have emerged as a promising alternative for air pollution estimations. However, research on high‐resolution mapping of NMVOCs concentrations using machine learning models is limited. This study provides the first predicted spatial distribution of hourly NMVOCs map deduced from sparse observations using the machine learning models. We developed a space‐time LightGBM model to estimate NMVOCs concentrations at 1 km spatial and hourly temporal resolution in Shanghai. Meanwhile, we use the shapely additive explanations to quantify and visualize the complex relationships between the input variables in the model. Moreover, we also offers an alternative solution to air pollution modeling with regard to unusual events (such as the COVID‐19 lockdown). Key Points: A space‐time LightGBM (STLGB) model in machine learning is used to estimate NMVOCs reliablyHourly NMVOCs maps were produced at 1 km resolution by the STLGB modelThe STLGB model shows good performance with cross‐validation R2 of 0.92 [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: 173893492
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: High‐Resolution Mapping of Regional NMVOCs Using the Fast Space‐Time Light Gradient Boosting Machine (LightGBM).
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Lu%2C+Bingqing%22">Lu, Bingqing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Chao%22">Liu, Chao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Meng%2C+Xue%22">Meng, Xue</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Zekun%22">Zhang, Zekun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Herrmann%2C+Hartmut%22">Herrmann, Hartmut</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Xiang%22">Li, Xiang</searchLink><relatesTo>1,3</relatesTo> (AUTHOR)<i> lixiang@fudan.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Geophysical+Research%2E+Atmospheres%22">Journal of Geophysical Research. Atmospheres</searchLink>. 11/27/2023, Vol. 128 Issue 22, p1-16. 16p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Air+pollutants%22">Air pollutants</searchLink><br />*<searchLink fieldCode="DE" term="%22Air+pollution%22">Air pollution</searchLink><br />*<searchLink fieldCode="DE" term="%22Volatile+organic+compounds%22">Volatile organic compounds</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Spacetime%22">Spacetime</searchLink><br /><searchLink fieldCode="DE" term="%22Spatial+resolution%22">Spatial resolution</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Shanghai+%28China%29%22">Shanghai (China)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Accurate spatiotemporal estimation of non‐methane volatile organic compounds (NMVOCs) plays a pivotal role in establishing sophisticated early warning systems and formulating strategies to combat air pollution. Despite these critical applications, robust estimation of high spatiotemporal resolution NMVOCs concentrations remains a challenge. In this study, we develop a space‐time Light Gradient Boosting Machine (STLGB) model, which successfully renders hourly maps of NMVOCs concentrations across Shanghai from 2019 to 2022 by integrating spatiotemporal information. After extensive training, the STLGB model demonstrates remarkable estimation performance for NMVOCs, accounting for multiple spatiotemporal variables (R2 = 0.92, RMSE = 34.52 ppb). With the developed model, we provide first high‐resolution (1 km) hourly NMVOCs concentration maps, uncovering previously overlooked spatiotemporal variations. Further, SHapley Additive exPlanation (SHAP) regression values reveal significant local interpretation capabilities of the STLGB model, emphasizing the strong influence of emissions on NMVOCs estimation, whilst acknowledging the important contribution of space and time term. Our study of the pandemic lockdown further showcases the model's adaptability to unique events influenced by policy changes. The superior performance of the STLGB model, with its minimal computational memory requirements and faster speed, makes it an ideal tool for air pollutant estimation, adaptable to any region with NMVOCs monitoring capabilities. Plain Language Summary: Non‐methane Volatile organic compounds (NMVOCs) are significant air pollutants that have severe effects on health and the environment. Despite the availability of VOCs monitoring stations that can provide data with good temporal resolution, the low spatial resolution of these stations remains a challenge. Accurate estimation of NMVOCs concentrations requires new methods to address these spatial resolution issues. In recent years, machine learning‐based models have emerged as a promising alternative for air pollution estimations. However, research on high‐resolution mapping of NMVOCs concentrations using machine learning models is limited. This study provides the first predicted spatial distribution of hourly NMVOCs map deduced from sparse observations using the machine learning models. We developed a space‐time LightGBM model to estimate NMVOCs concentrations at 1 km spatial and hourly temporal resolution in Shanghai. Meanwhile, we use the shapely additive explanations to quantify and visualize the complex relationships between the input variables in the model. Moreover, we also offers an alternative solution to air pollution modeling with regard to unusual events (such as the COVID‐19 lockdown). Key Points: A space‐time LightGBM (STLGB) model in machine learning is used to estimate NMVOCs reliablyHourly NMVOCs maps were produced at 1 km resolution by the STLGB modelThe STLGB model shows good performance with cross‐validation R2 of 0.92 [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=173893492
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1029/2023JD039591
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 16
        StartPage: 1
    Subjects:
      – SubjectFull: Air pollutants
        Type: general
      – SubjectFull: Air pollution
        Type: general
      – SubjectFull: Volatile organic compounds
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Spacetime
        Type: general
      – SubjectFull: Spatial resolution
        Type: general
      – SubjectFull: Shanghai (China)
        Type: general
    Titles:
      – TitleFull: High‐Resolution Mapping of Regional NMVOCs Using the Fast Space‐Time Light Gradient Boosting Machine (LightGBM).
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Lu, Bingqing
      – PersonEntity:
          Name:
            NameFull: Liu, Chao
      – PersonEntity:
          Name:
            NameFull: Meng, Xue
      – PersonEntity:
          Name:
            NameFull: Zhang, Zekun
      – PersonEntity:
          Name:
            NameFull: Herrmann, Hartmut
      – PersonEntity:
          Name:
            NameFull: Li, Xiang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 27
              M: 11
              Text: 11/27/2023
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-print
              Value: 2169897X
          Numbering:
            – Type: volume
              Value: 128
            – Type: issue
              Value: 22
          Titles:
            – TitleFull: Journal of Geophysical Research. Atmospheres
              Type: main
ResultId 1