An analysis of feature relevance in the classification of astronomical transients with machine learning methods

TL;DR

This paper evaluates the effectiveness of various machine learning algorithms in classifying astronomical transients, emphasizing the importance of feature selection using data from the CRTS survey.

Contribution

It systematically compares classification performance of Random Forest, MLPQNA, and KNN on CRTS data, highlighting the impact of feature selection in transient classification.

Findings

Random Forest achieved high accuracy in identifying cataclysmic variables.

Feature selection significantly improved classification results.

Different algorithms showed varying strengths depending on the classification task.

Abstract

The exploitation of present and future synoptic (multi-band and multi-epoch) surveys requires an extensive use of automatic methods for data processing and data interpretation. In this work, using data extracted from the Catalina Real Time Transient Survey (CRTS), we investigate the classification performance of some well tested methods: Random Forest, MLPQNA (Multi Layer Perceptron with Quasi Newton Algorithm) and K-Nearest Neighbors, paying special attention to the feature selection phase. In order to do so, several classification experiments were performed. Namely: identification of cataclysmic variables, separation between galactic and extra-galactic objects and identification of supernovae.