Leveraging Distance Metrics for Machine Learning in Astronomy: DistClassiPy

With the launch of the Vera C. Rubin Observatory imminent, we will soon be moving to an era of big data in time-domain astrophysics. In the Legacy Survey of Space and Time (LSST), Rubin will observe over 37 billion objects - necessitating data science and machine learning as essential tools for astrophysics. As we design and adapt machine learning algorithms for LSST data, it is critical to consider interpretability, computational cost, and the adaptability of the method for specific scientific cases. Distance-based methods offer promising solutions on all these fronts, yet these approaches have not been extensively explored within the context of astrophysical classification. We recently developed a new classifier, DistClassiPy, and demonstrated its utility in the classification of variable stars. By exploring 18 distance metrics, we demonstrate that this classifier meets state-of-the-art performance while requiring lower computational resources and offering improved interpretability. To facilitate the application of DistClassiPy to transient science, we have also developed a custom feature extraction method utilizing autoencoders. Furthermore, we are in the process of extending DistClassiPy's capabilities to include anomaly detection.