Diagnosing drivers of PM<sub>2.5</sub> simulation biases in China from meteorology, chemical composition, and emission sources using an efficient machine learning method

zu Verbundenen Objekten

Abstract 2.5). In this study, an efficient method with high speed and a low computational resource requirement based on the tree-based machine learning (ML) method, the light gradient boosting machine (LightGBM), was designed to diagnose CTM simulation biases. The drivers of the Community Multiscale Air Quality (CMAQ) model biases are compared to observations obtained by simulating PM2.5 concentrations from the perspectives of meteorology, chemical composition, and emission sources. The source-oriented CMAQ was used to diagnose the influences of different emission sources on PM2.5 biases. The model can capture the complex relationship between input variables and simulation bias well; meteorology, PM2.5 components, and source sectors can partially explain the simulation bias. The CMAQ model underestimates PM2.5 by - - µ g m - 3 in 2019, especially in winter and spring and during high-PM2.5 events. Secondary organic components showed the largest contribution to the PM2.5 simulation bias for different regions and seasons (13.8 %–22.6 %) of all components. Relative humidity, cloud cover, and soil surface moisture were the main meteorological factors contributing to PM2.5 bias in the North China Plain, Pearl River Delta, and northwestern China, respectively. Primary and secondary inorganic components from residential sources showed the two largest contributions to this bias (12.05 % and 12.78 %), implying large uncertainties in this sector. The ML-based methods provide valuable complements to traditional-mechanism-based methods for model improvement, with high efficiency and low reliance on prior information.

Standort
Deutsche Nationalbibliothek Frankfurt am Main
Umfang
Online-Ressource
Sprache
Englisch

Erschienen in
Diagnosing drivers of PM2.5 simulation biases in China from meteorology, chemical composition, and emission sources using an efficient machine learning method ; volume:17 ; number:9 ; year:2024 ; pages:3617-3629 ; extent:13
Geoscientific model development ; 17, Heft 9 (2024), 3617-3629 (gesamt 13)

Urheber
Wang, Shuai
Zhang, Mengyuan
Gao, Yueqi
Wang, Peng
Fu, Qingyan
Zhang, Hongliang

DOI
10.5194/gmd-17-3617-2024
URN
urn:nbn:de:101:1-2405090429071.163120746959
Rechteinformation
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
Letzte Aktualisierung
14.08.2025, 11:01 MESZ

Datenpartner

Dieses Objekt wird bereitgestellt von:
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Original beim Datenpartner anzeigen

Beteiligte

  • Wang, Shuai
  • Zhang, Mengyuan
  • Gao, Yueqi
  • Wang, Peng
  • Fu, Qingyan
  • Zhang, Hongliang

Ähnliche Objekte (12)

Impact of Meteorology and Aerosol Sources on PM2.5 and Oxidative Potential Variability and Levels in China

Impact of Meteorology and Aerosol Sources on PM<sub>2.5</sub> and Oxidative Potential Variability and Levels in China

Contributions of meteorology and anthropogenic emissions to the trends in winter PM2.5 in eastern China 2013–2018

Contributions of meteorology and anthropogenic emissions to the trends in winter PM<sub>2.5</sub> in eastern China 2013–2018

Performance evaluation of MOMA &ndash; a remote network calibration technique for PM2.5 and PM10 sensors

Performance evaluation of MOMA &ndash; a remote network calibration technique for PM<sub>2.5</sub> and PM<sub>10</sub> sensors

Contributions of meteorology and anthropogenic emissions to the trends in winter PM2.5 in eastern China 2013&ndash;2018

Contributions of meteorology and anthropogenic emissions to the trends in winter PM<sub>2.5</sub> in eastern China 2013&ndash;2018

Strong inter-model differences and biases in CMIP6 simulations of PM2.5, aerosol optical depth, and precipitation over Africa

Strong inter-model differences and biases in CMIP6 simulations of PM<sub>2.5</sub>, aerosol optical depth, and precipitation over Africa

Simulated impacts of vertical distributions of black carbon aerosol on meteorology and PM2.5 concentrations in Beijing during severe haze events

Simulated impacts of vertical distributions of black carbon aerosol on meteorology and PM<sub>2.5</sub> concentrations in Beijing during severe haze events

Simulated impacts of vertical distributions of black carbon aerosol on meteorology and PM2.5 concentrations in Beijing during severe haze events

Simulated impacts of vertical distributions of black carbon aerosol on meteorology and PM<sub>2.5</sub> concentrations in Beijing during severe haze events

Measurement report: Evaluation of the TOF-ACSM-CV for PM1.0 and PM2.5 measurements during the RITA-2021 field campaign

Measurement report: Evaluation of the TOF-ACSM-CV for PM<sub>1.0</sub> and PM<sub>2.5</sub> measurements during the RITA-2021 field campaign

Measurement report: Evaluation of the TOF-ACSM-CV for PM1.0 and PM2.5 measurements during the RITA-2021 field campaign

Measurement report: Evaluation of the TOF-ACSM-CV for PM<sub>1.0</sub> and PM<sub>2.5</sub> measurements during the RITA-2021 field campaign

Emerging extreme Saharan-dust events expand northward over the Atlantic and Europe prompting record-breaking PM10 and PM2.5 episodes

Emerging extreme Saharan-dust events expand northward over the Atlantic and Europe prompting record-breaking PM<sub>10</sub> and PM<sub>2.5</sub> episodes

The spatiotemporal relationship between PM2.5 and AOD in China: Influencing factors and Implications for satellite PM2.5 estimations by MAIAC AOD

The spatiotemporal relationship between PM<sub>2.5</sub> and AOD in China: Influencing factors and Implications for satellite PM<sub>2.5</sub> estimations by MAIAC AOD

Predicting gridded winter PM2.5 concentration in east of China

Predicting gridded winter PM<sub>2.5</sub> concentration in east of China

Verbundene Objekte