Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

  1. Home
  3. Machine Learning-based Quantification And Separation Of Emissions And Meteorological Effects On Pm2.5 In Greater Bangkok.
  1. Home
  3. Machine Learning-based Quantification And Separation Of Emissions And Meteorological Effects On Pm2.5 In Greater Bangkok.

Related Experiment Video

Measuring Sub-23 Nanometer Real Driving Particle Number Emissions Using the Portable DownToTen Sampling System
08:59

Measuring Sub-23 Nanometer Real Driving Particle Number Emissions Using the Portable DownToTen Sampling System

Published on: May 22, 2020

5.4K

Machine learning-based quantification and separation of emissions and meteorological effects on PM2.5 in Greater

Nishit Aman1, Sirima Panyametheekul2,3, Ittipol Pawarmart4

  • 1Department of Environmental and Sustainable Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand.

Scientific Reports
|April 28, 2025

View abstract on PubMed

Summary
This summary is machine-generated.

Machine learning models successfully separated PM2.5 pollution into emission and meteorology effects in Greater Bangkok. Winter conditions and humidity significantly impact air quality, revealing limitations in current mitigation strategies.

Keywords:
Explainable machine learningHimawari-8Hurst exponentMeteorological normalizationPM2.5 mappingSHAP

More Related Videos

Additive Manufacturing-Enabled Low-Cost Particle Detector
06:05

Additive Manufacturing-Enabled Low-Cost Particle Detector

Published on: March 24, 2023

1.1K
Quantification of three DNA Lesions by Mass Spectrometry and Assessment of Their Levels in Tissues of Mice Exposed to Ambient Fine Particulate Matter
12:15

Quantification of three DNA Lesions by Mass Spectrometry and Assessment of Their Levels in Tissues of Mice Exposed to Ambient Fine Particulate Matter

Published on: May 29, 2019

8.5K

Related Experiment Videos

Measuring Sub-23 Nanometer Real Driving Particle Number Emissions Using the Portable DownToTen Sampling System
08:59

Measuring Sub-23 Nanometer Real Driving Particle Number Emissions Using the Portable DownToTen Sampling System

Published on: May 22, 2020

5.4K
Additive Manufacturing-Enabled Low-Cost Particle Detector
06:05

Additive Manufacturing-Enabled Low-Cost Particle Detector

Published on: March 24, 2023

1.1K
Quantification of three DNA Lesions by Mass Spectrometry and Assessment of Their Levels in Tissues of Mice Exposed to Ambient Fine Particulate Matter
12:15

Quantification of three DNA Lesions by Mass Spectrometry and Assessment of Their Levels in Tissues of Mice Exposed to Ambient Fine Particulate Matter

Published on: May 29, 2019

8.5K

Area of Science:

  • Environmental Science
  • Atmospheric Science
  • Data Science

Background:

  • Particulate Matter (PM2.5) pollution poses significant health risks.
  • Understanding the drivers of PM2.5 is crucial for effective air quality management.
  • Previous studies often struggled to disentangle meteorological influences from emission sources.

Purpose of the Study:

  • To apply machine learning for meteorological normalization of PM2.5 data.
  • To quantify and separate the contributions of emissions and meteorology to PM2.5 levels.
  • To identify key meteorological factors influencing PM2.5 in Greater Bangkok using SHAP analysis.

Main Methods:

  • Employed six machine learning models (RF, ADB, GB, XGB, LGBM, CB) for PM2.5 prediction.
  • Utilized meteorological factors, fire activity, land use, and socio-economic data as predictors.
  • Applied meteorological normalization and SHAP analysis to attribute PM2.5 to emissions and weather.

    • Main Results:

    • Light Gradient Boosting Machine (LGBM) achieved the highest prediction accuracy for PM2.5.
    • Meteorology significantly influences PM2.5 variability, especially during winter.
    • Relative humidity, boundary layer height, and wind speed were identified as key meteorological drivers.
    • Analysis revealed limitations in the effectiveness of current mitigation measures during certain seasons.

    Conclusions:

    • Machine learning provides a robust framework for understanding complex air pollution dynamics.
    • Meteorological conditions, particularly stagnant winter weather and high humidity, exacerbate PM2.5 pollution.
    • Policy recommendations are proposed based on the quantified impacts of emissions and meteorology.