# A CNN adapted to time series for the classification of Supernovae

## TL;DR

This paper introduces two CNN-based methods for classifying supernovae from light-curve data, outperforming existing models by directly analyzing time series without extensive feature extraction.

## Contribution

It presents two novel CNN architectures tailored for supernovae light-curve classification, including a time series adapted CNN and a Siamese CNN for sparse, limited data.

## Key findings

- Both CNNs outperform current state-of-the-art methods.
- The time series CNN effectively handles supernova light-curves.
- The Siamese CNN addresses data sparsity and small dataset challenges.

## Abstract

Cosmologists are facing the problem of the analysis of a huge quantity of data when observing the sky. The methods used in cosmology are, for the most of them, relying on astrophysical models, and thus, for the classification, they usually use a machine learning approach in two-steps, which consists in, first, extracting features, and second, using a classifier. In this paper, we are specifically studying the supernovae phenomenon and especially the binary classification "I.a supernovae versus not-I.a supernovae". We present two Convolutional Neural Networks (CNNs) defeating the current state-of-the-art. The first one is adapted to time series and thus to the treatment of supernovae light-curves. The second one is based on a Siamese CNN and is suited to the nature of data, i.e. their sparsity and their weak quantity (small learning database).