基于扫描核探针技术的大气气溶胶单颗粒物源识别与解析方法研究与应用

The source identification and apportionment of aerosol particles in the atmosphere by scanning nuclear microprobes

将高分辨、高灵敏的扫描核探针(SNM)技术与人工神经网络(ANN)模式识别方法相结合,以单个气溶胶颗粒物化学表征为基础,开展大气气溶胶源识别与解析的新方法研究。摸索出单颗粒气溶胶SNM靶样的制备方法。建立了SNM多站多参量分析模式的数据获取系统和分析条件。用SNM测定了单个大气气溶胶粒子的元素谱特征。基于标准的误差反向传输神经网络算法,建立ANN模式识别系统,直接对单个气溶胶粒子的SNM分析能谱模式进行识别,判别其来源,计算源的贡献率。将建立的方法初步应用于上海市大气PM10源识别与解析研究。结果表明该方法解析能力强,解析结果客观,具有查找未知污染源、解析低浓度污染源的特点。

A new method combining the scanning nuclear microprobe (SNM) with the pattern recognition of artificial neural network (ANN) was studied for the source identification and apportionment of aerosol particles. A technique of preparing of single aerosol particle sample was developed. A multi-station and multi-parameter data system for SNM was set up. A ANN program package was used for the source identification and apportionment of aerosol particles based on the Micro-PIXE spectra. The new method was preliminarily applied to the PM10 aerosol particles in the atmosphere of Shanghai city.