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

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.

Accepted by MNRAS, 11 figures, 18 pages

References in corpus (8)

• A systematic search for close supermassive black hole binaries in the Catalina Real-Time Transient Survey
• Automated supervised classification of variable stars I. Methodology
• Automated Transient Identification in the Dark Energy Survey
• Cosmological performance of SKA HI galaxy surveys
• Variable stars across the observational HR diagram
• Machine learning for transient discovery in Pan-STARRS1 difference imaging
• Photometric redshift estimation based on data mining with PhotoRApToR
• Data challenges of time domain astronomy

Cited by in corpus (30)

• The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
• Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
• Machine-learning Approaches to Exoplanet Transit Detection and Candidate Validation in Wide-field Ground-based Surveys
• Anomaly detection in the Zwicky Transient Facility DR3
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• Return of the features. Efficient feature selection and interpretation for photometric redshifts
• Star Formation Rates for photometric samples of galaxies using machine learning methods
• Predicting star formation properties of galaxies using deep learning
• {\sc mirkwood:} Fast and Accurate SED Modeling Using Machine Learning
• Euclid: Superluminous supernovae in the Deep Survey
• The search for galaxy cluster members with deep learning of panchromatic HST imaging and extensive spectroscopy
• Photometric redshifts with machine learning, lights and shadows on a complex data science use case
• Data preparation for asteroseismology with TESS
• Classifying Image Sequences of Astronomical Transients with Deep Neural Networks
• Identifying Tidal Disruption Events via Prior Photometric Selection of Their Preferred Hosts
• Machine-z: Rapid Machine Learned Redshift Indicator for Swift Gamma-ray Bursts
• Sacrificing information for the greater good: how to select photometric bands for optimal accuracy
• MANTRA: A Machine Learning reference lightcurve dataset for astronomical transient event recognition
• ULISSE: A Tool for One-shot Sky Exploration and its Application to Active Galactic Nuclei Detection
• Discriminating among cosmological models by data-driven methods
• SNAD Transient Miner: Finding Missed Transient Events in ZTF DR4 using k-D trees
• Astroinformatics based search for globular clusters in the Fornax Deep Survey
• Variable Star Classification Using Multi-View Metric Learning
• Forecasting Supernova Observations with the CSST: I. Photometric Samples
• Automated algorithms to build Active Galactic Nuclei classifiers
• Statistical characterization and classification of astronomical transients with Machine Learning in the era of the Vera C. Rubin Observatory
• Neural Gas based classification of Globular Clusters
• Advanced Astroinformatics for Variable Star Classification
• The largest ground-based catalogue of M-dwarf flares
• Astrophysical Data Analytics based on Neural Gas Models, using the Classification of Globular Clusters as Playground