Astrophysical Data Analytics based on Neural Gas Models, using the Classification of Globular Clusters as Playground

TL;DR

This paper evaluates neural gas models for classifying globular clusters in astrophysical data, demonstrating their effectiveness and comparing them with other machine learning methods to validate their potential for astrophysical data analysis.

Contribution

It introduces neural gas variants for globular cluster classification and compares their performance with other ML methods, validating their applicability in astrophysics.

Findings

Neural gas models achieve high purity and completeness in classification.

Supervised and unsupervised neural gas variants perform comparably to traditional ML methods.

The study provides a validated framework for applying neural gas models in astrophysical data analysis.

Abstract

In Astrophysics, the identification of candidate Globular Clusters through deep, wide-field, single band HST images, is a typical data analytics problem, where methods based on Machine Learning have revealed a high efficiency and reliability, demonstrating the capability to improve the traditional approaches. Here we experimented some variants of the known Neural Gas model, exploring both supervised and unsupervised paradigms of Machine Learning, on the classification of Globular Clusters, extracted from the NGC1399 HST data. Main focus of this work was to use a well-tested playground to scientifically validate such kind of models for further extended experiments in astrophysics and using other standard Machine Learning methods (for instance Random Forest and Multi Layer Perceptron neural network) for a comparison of performances in terms of purity and completeness.