Photometric Data-driven Classification of Type Ia Supernovae in the Open Supernova Catalog

TL;DR

This paper presents a machine learning method for classifying Type Ia supernovae using only real photometric data, demonstrating effectiveness despite limited training samples and highlighting challenges in transferring models between simulated and real data.

Contribution

The study introduces a novel photometric classification approach trained solely on real observational data, and investigates transferability issues between simulated and real datasets.

Findings

Method achieves good classification results on real data.

Transfer performance drops significantly between simulated and real data.

Highlights differences between simulated and observational supernova data.

Abstract

We propose a novel approach for a machine-learning-based detection of the type Ia supernovae using photometric information. Unlike other approaches, only real observation data is used during training. Despite being trained on a relatively small sample, the method shows good results on real data from the Open Supernovae Catalog. We also investigate model transfer from the PLAsTiCC simulations train dataset to real data application, and the reverse, and find the performance significantly decreases in both cases, highlighting the existing differences between simulated and real data.