Unsupervised classification of absorbing aerosols detected by the Single Particle Soot Photometer

<p>The Single Particle Soot Photometer (SP2) detects refractory aerosol particle mass on a single-particle basis via laser-induced incandescence (L-II). While the SP2 has traditionally been used to quantify black carbon aerosol mass in the atmosphere, the instrument is increasingly being used to detect and quantify other types of absorbing aerosols, such as mineral dust or anthropogenically-sourced iron oxide aerosols. Quantifying the mass loadings and emission sources of absorbing aerosols in the atmosphere is important for understanding their role in the climate cycle. Supervised machine learning algorithms have shown potential to classify different types of aerosols from L-II signals, but these methods are sensitive to instrument configuration and require training datasets generated from laboratory samples, which do not generalize well to ambient atmospheric aerosols. Here we explore the effectiveness of unsupervised machine learning, including principal component analysis (PCA) and a variational autoencoder (VAE), applied directly to L-II signals from the SP2 in order to classify different types of absorbing aerosols. The VAE is a deep learning architecture that compresses L-II signals into a bottleneck latent representation and reconstructs an output as similar as possible to the input signal, thereby reducing dimensionality. We apply PCA and the VAE to a dataset comprised of laboratory samples of materials that show detectable incandescence in the SP2, including fullerene soot (as a proxy for black carbon), coated fullerene soot, coal fly ash, mineral dust, volcanic ash, hematite, and magnetite. We explore optimal latent representations of L-II signals to maximize separability of different aerosol classes by varying the size of the latent representation, and find that a latent representation of 3 allows us to capture the majority of the information in the L-II signals relevant for identifying different types of absorbing aerosols. We demonstrate that unsupervised machine learning is a promising method for identifying distinct populations of aerosols detected by the SP2 and for quantifying the similarity of different types of aerosols in terms of their response in the SP2.</p>