Supernova Light Curves Approximation based on Neural Network Models

TL;DR

This paper explores neural network models like MLP, BNN, and NF to approximate supernova light curves, improving classification accuracy and speed over traditional Gaussian process methods in astronomical data analysis.

Contribution

It introduces the application of advanced neural network models for light curve approximation, outperforming Gaussian processes in accuracy and efficiency for supernova classification.

Findings

Normalizing Flows outperform Gaussian processes in approximation quality.

MLP matches Gaussian process quality with increased speed.

Proposed methods enhance real-time supernova classification.

Abstract

Photometric data-driven classification of supernovae becomes a challenge due to the appearance of real-time processing of big data in astronomy. Recent studies have demonstrated the superior quality of solutions based on various machine learning models. These models learn to classify supernova types using their light curves as inputs. Preprocessing these curves is a crucial step that significantly affects the final quality. In this talk, we study the application of multilayer perceptron (MLP), bayesian neural network (BNN), and normalizing flows (NF) to approximate observations for a single light curve. We use these approximations as inputs for supernovae classification models and demonstrate that the proposed methods outperform the state-of-the-art based on Gaussian processes applying to the Zwicky Transient Facility Bright Transient Survey light curves. MLP demonstrates similar quality as Gaussian processes and speed increase. Normalizing Flows exceeds Gaussian processes in terms of approximation quality as well.