Measurement Report: Unraveling PM₁₀ Sources and Oxidative Potential Across Chinese Regions: Insights Analysis Based on CNN-LSTM and Receptor Model

Abstract. The oxidative potential (OP) of particulate matter is a key driver of PM₁₀-induced adverse health effects, triggering oxidative stress and inflammatory responses that increase respiratory and cardiovascular disease risks. To evaluate PM₁₀ and its OP characteristics across China, samples were collected from twelve representative monitoring stations from June 2022 to May 2023. A deep learning model combining Convolutional Neural Networks and Long Short-Term Memory networks (CNN-LSTM) was employed to reconstruct anomalous PM₁₀ data, achieving R² values of 0.967 and 0.884 for training and test sets, respectively. Significant spatial variations in PM₁₀ were observed, with highest concentrations in the northwestern regions (Xi'an: 98.20 ± 52.92 μg·m^-3, Dunhuang: 90.36 ± 54.72 μg·m^-3), the lowest in the northeast (Longfengshan: 40.04 ± 24.04 μg·m-3, Dalian: 40.35 ± 15.66 μg·m^-3), and elevated levels in suburban areas (average: 85.43 ± 46.69 μg·m^-3). Urban sites showed the highest OP values, with significantly higher PM₁₀ concentrations in northern regions compared to southern ones (p<0.05). Most sites exhibited peak PM₁₀ and OP levels in winter and lowest in summer. Source apportionment using Positive Matrix Factorization (PMF) revealed dust (13.2–27.4 %), biomass burning (9.5–39.3 %), traffic (16.6–21.4 %), and agricultural activities (13–22 %) as main contributors to PM₁₀. PMF analysis identified traffic as the primary OP contributor (24–48 %) across sites, with regional variations in biomass burning (57 % in Nanning), agricultural activities (37 % in Zhengzhou), and dust (22–23 % in Gucheng and Longfengshan). These findings highlight the need to control traffic emissions and other major sources to reduce OP and protect public health.