Aerosols that absorb sunlight play key role in Earth's climate. To improve detection of light-absorbing aerosols measured by the Single Particle Soot Photometer, we explore unsupervised machine learning. Unlike earlier methods that require labeled training data, our approach learns patterns directly from unlabeled data. This makes it more applicable to atmospheric observations. We show this method can be used to quantify how similar aerosols are to one another and improve aerosol classification.