Articles | Volume 25, issue 21
https://doi.org/10.5194/acp-25-14643-2025
https://doi.org/10.5194/acp-25-14643-2025
Measurement report
 | 
04 Nov 2025
Measurement report |  | 04 Nov 2025

Measurement report: Unraveling PM10 sources and oxidative potential across Chinese regions based on CNN-LSTM data preprocessing and receptor model

Qinghe Cai, Dongqing Fang, Junli Jin, Xiaoyu Hu, Yuxuan Cao, Tianyi Zhao, Yang Bai, and Yang Zhang

Data sets

Measurement report: Unraveling PM10 Sources and Oxidative Potential Across Chinese Regions Insights Analysis Based on CNN-LSTM and Receptor Model Qinghe Cai et al. https://doi.org/10.5281/zenodo.15420768

Download
Short summary
This study analyzed PM10 and oxidative potential (OP) in 12 Chinese regions (Jun 2022-May 2023) via Convolutional Neural Networks and Long Short-Term Memory networks (CNN-LSTM) and Positive Matrix Factorization (PMF) at 4 representative sites. PM10 was higher in the northwest, lower in the northeast; urban areas had higher OP. Most sites showed peak PM10 and OP in winter, lowest in summer. Traffic, biomass burning, and coal combustion were major OP contributors.
Share
Altmetrics
Final-revised paper
Preprint