Classifying High-Energy Celestial Objects with Machine Learning Methods

TL;DR

This paper evaluates machine learning techniques, including tree-based models and RNNs, for classifying celestial objects like pulsars and black holes based on photometric and raw signal data.

Contribution

It compares traditional tree-based models with RNNs for celestial object classification, highlighting the potential of deep learning for real-time astronomical data analysis.

Findings

Tree-based models perform well on photometric data.

RNNs show promise for real-time classification.

Deep learning enhances celestial object discrimination.

Abstract

Machine learning is a field that has been growing in importance since the early 2010s due to the increasing accuracy of classification models and hardware advances that have enabled faster training on large datasets. In the field of astronomy, tree-based models and simple neural networks have recently garnered attention as a means of classifying celestial objects based on photometric data. We apply common tree-based models to assess performance of these models for discriminating objects with similar photometric signals, pulsars and black holes. We also train a RNN on a downsampled and normalized version of the raw signal data to examine its potential as a model capable of object discrimination and classification in real-time.