Application of Convolutional Neural Networks to time domain astrophysics. 2D image analysis of OGLE light curves

Abstract

In recent years the amount of publicly available astronomical data has increased exponentially, with a remarkable example being large scale multiepoch photometric surveys. This wealth of data poses challenges to the classical methodologies commonly employed in the study of variable objects. As a response, deep learning techniques are increasingly being explored to effectively classify, analyze, and interpret these large datasets. In this paper we use two-dimensional histograms to represent Optical Gravitational Lensing Experiment (OGLE) phasefolded light curves as images. We use a Convolutional Neural Network (CNN) to classify variable objects within eight different categories (from now on labels): Classical Cepheid (CEP), RR Lyrae (RR), Long Period Variable (LPV), Miras (M), Ellipsoidal Binary (ELL), Delta Scuti (DST), Eclipsing Binary (E), and spurious class with Incorrect Periods (Rndm). We set up different training sets to train the same CNN architecture in order to characterize the impact of the training. The training sets were built from the same source of labels but different filters and balancing techniques were applied. Namely: Undersampling (U), Data Augmentation (DA), and Batch Balancing (BB). The best performance was achieved with the BB approach and a training sample size of $\sim$370000 stars. Regarding computational performance, the image representation production rate is of $\sim$76 images per core per second, and the time to predict is $\sim$ 60$\mu \text{s}$ per star. The accuracy of the classification improves from $\sim$ 92%, when based only on the CNN, to $\sim$ 98% when the results of the CNN are combined with the period and amplitude features in a two step approach. This methodology achieves comparable results with previous studies but with two main advantages: the identification of miscalculated periods and the improvement in computational time cost.

accepted for publication in A&A

References in corpus (34)

• Gaia Data Release 2. Summary of the contents and survey properties
• The Wide-field Infrared Survey Explorer (WISE): Mission Description and Initial On-orbit Performance
• Gaia Data Release 3: Summary of the content and survey properties
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• A 2.4% Determination of the Local Value of the Hubble Constant
• Large Magellanic Cloud Cepheid Standards Provide a 1% Foundation for the Determination of the Hubble Constant and Stronger Evidence for Physics Beyond LambdaCDM
• A 3% Solution: Determination of the Hubble Constant with the Hubble Space Telescope and Wide Field Camera 3
• Accurate masses and radii of normal stars: modern results and applications
• Detection of Planetary Transits Across a Sun-like Star
• A method for optimal image subtraction
• VISTA Variables in the Via Lactea (VVV): The public ESO near-IR variability survey of the Milky Way
• A box-fitting algorithm in the search for periodic transits
• The MACHO Project LMC Microlensing Results from the First Two Years and the Nature of the Galactic Dark Halo
• Northern Sky Variability Survey (NSVS): Public data release
• Superflares on Solar Type Stars Observed with Kepler I. Statistical Properties of Superflares
• The Catalina Surveys Periodic Variable Star Catalog
• The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
• Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
• A recurrent neural network for classification of unevenly sampled variable stars
• A comparison of period finding algorithms
• A Package for the Automated Classification of Periodic Variable Stars
• Exoplanet detection capability of the COROT space mission
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• Deep multi-survey classification of variable stars
• Photometric segregation of dwarf and giant FGK stars using the SVO Filter Profile Service and photometric tools
• 15000 Ellipsoidal Binary Candidates in TESS: Orbital Periods, Binary Fraction, and Tertiary Companions
• ASTROMER: A transformer-based embedding for the representation of light curves
• An improved quasar detection method in EROS-2 and MACHO LMC datasets
• The period--luminosity relation for Mira variables in the Milky Way using Gaia DR3: a further distance anchor for $H_0$
• Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data
• The Carnegie RR Lyrae Program: Mid-infrared Period-Luminosity relations of RR Lyrae stars in Reticulum
• Classification of Periodic Variable Stars with Novel Cyclic-Permutation Invariant Neural Networks
• Variable star classification with a Multiple-Input Neural Network

Cited by in corpus (5)

• A statistical study of lopsided galaxies using random forest
• Leveraging pre-trained vision Transformers for multi-band photometric light curve classification
• 200,000+ Deep Learning-inferred Periods of Stellar Variability from the All-Sky Automated Survey for Supernovae
• Heartbeat Stars Recognition Based on Recurrent Neural Networks: Method and Validation
• The Variable Sky Through the OGLE Eye