Statistical characterization and classification of astronomical transients with Machine Learning in the era of the Vera C. Rubin Observatory

TL;DR

This paper evaluates machine learning methods for classifying astronomical transients, especially supernovae, using simulated data to address challenges posed by large-scale surveys like LSST in the era of big data astronomy.

Contribution

It provides a comparative analysis of various machine learning algorithms for transient classification and discusses data quality issues relevant for upcoming large-scale surveys.

Findings

Machine learning algorithms show varying performance depending on data quality.

Critical data parameters significantly influence classification accuracy.

Insights into preparing for real data analysis in future astronomical surveys.

Abstract

Astronomy has entered the multi-messenger data era and Machine Learning has found widespread use in a large variety of applications. The exploitation of synoptic (multi-band and multi-epoch) surveys, like LSST (Legacy Survey of Space and Time), requires an extensive use of automatic methods for data processing and interpretation. With data volumes in the petabyte domain, the discrimination of time-critical information has already exceeded the capabilities of human operators and crowds of scientists have extreme difficulty to manage such amounts of data in multi-dimensional domains. This work is focused on an analysis of critical aspects related to the approach, based on Machine Learning, to variable sky sources classification, with special care to the various types of Supernovae, one of the most important subjects of Time Domain Astronomy, due to their crucial role in Cosmology. The work is based on a test campaign performed on simulated data. The classification was carried out by comparing the performances among several Machine Learning algorithms on statistical parameters extracted from the light curves. The results make in evidence some critical aspects related to the data quality and their parameter space characterization, propaedeutic to the preparation of processing machinery for the real data exploitation in the incoming decade.