Articles | Volume 25, issue 15
https://doi.org/10.5194/acp-25-8407-2025
https://doi.org/10.5194/acp-25-8407-2025
Research article
 | 
01 Aug 2025
Research article |  | 01 Aug 2025

Explainable ensemble machine learning revealing spatiotemporal heterogeneity in driving factors of particulate nitro-aromatic compounds in eastern China

Min Li, Xinfeng Wang, Tianshuai Li, Yujia Wang, Yueru Jiang, Yujiao Zhu, Wei Nie, Rui Li, Jian Gao, Likun Xue, Qingzhu Zhang, and Wenxing Wang

Data sets

Data of particulate nitro-aromatic compounds and other relevant parameters in eastern China Min Li and Xinfeng Wang https://doi.org/10.17632/fp9zkv28p2.2

Download
Short summary
By integrating field measurements with an interpretable ensemble machine learning framework, we comprehensively identified key driving factors of nitro-aromatic compounds (NACs), demonstrated complex interrelationships, and quantified their contributions across different locations. This work provides a reliable modeling approach for recognizing causes of NAC pollution, enhances our understanding of variations of atmospheric NACs, and highlights the necessity of strengthening emission controls.
Share
Altmetrics
Final-revised paper
Preprint