Scholarlink

<p>This study presents an integrated machine learning framework for classifying PM<sub>2.5</sub> composition-based chemical regimes using the air quality management offices (AQMOs) database. By employing self-organizing maps (SOM) and K-means clustering, patterns in PM<sub>2.5</sub> composition were visualized by grouping observations with similar chemical characteristics. The identified regimes showed distinct composition-based features: urban and industrialized areas were associated with higher frequencies of industrial- and traffic-related chemical patterns, whereas coastal or island regions showed higher frequencies of sea-salt-related and background-like chemical regimes. Subsequently, the identified chemical regime labels were classified using a Random Forest model, achieving an overall accuracy of 0.921 and a macro F1-score of 0.843. The trained model was further applied to independent measurement sites (OS, HS, and GC) to evaluate cross-site applicability. The proposed framework provides a practical approach for characterizing PM<sub>2.5</sub> chemical regimes using multi-site observational data and may serve as a complementary preliminary diagnostic tool for small-scale studies or regions where detailed receptor-model results are not yet available.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Classification and cross-site prediction of PM2.5 chemical composition patterns using a machine learning framework

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月15日

查看全文
  • Hyemin Hwang,
  • Jaeseok Heo,
  • Mu Hyun Jung,
  • So Yeon Kim,
  • Jae Young Lee

摘要

This study presents an integrated machine learning framework for classifying PM2.5 composition-based chemical regimes using the air quality management offices (AQMOs) database. By employing self-organizing maps (SOM) and K-means clustering, patterns in PM2.5 composition were visualized by grouping observations with similar chemical characteristics. The identified regimes showed distinct composition-based features: urban and industrialized areas were associated with higher frequencies of industrial- and traffic-related chemical patterns, whereas coastal or island regions showed higher frequencies of sea-salt-related and background-like chemical regimes. Subsequently, the identified chemical regime labels were classified using a Random Forest model, achieving an overall accuracy of 0.921 and a macro F1-score of 0.843. The trained model was further applied to independent measurement sites (OS, HS, and GC) to evaluate cross-site applicability. The proposed framework provides a practical approach for characterizing PM2.5 chemical regimes using multi-site observational data and may serve as a complementary preliminary diagnostic tool for small-scale studies or regions where detailed receptor-model results are not yet available.