Leveraging pre-trained vision Transformers for multi-band photometric light curve classification

Abstract

This study investigates the potential of a pre-trained vision Transformer (VT) model, specifically the Swin Transformer V2 (SwinV2), to classify photometric light curves without the need for feature extraction or multi-band preprocessing. The goal is to assess whether this image-based approach can accurately differentiate astronomical phenomena and serve as a viable option for working with multi-band photometric light curves. We transformed each multi-band light curve into an image. These images serve as input to the SwinV2 model, which is pre-trained on ImageNet-21K. The datasets employed include the public Catalog of Variable Stars from the Massive Compact Halo Object (MACHO) survey, using both one and two bands, and the first round of the recent Extended LSST Astronomical Time-Series Classification Challenge (ELAsTiCC), which includes six bands. The performance of the model was evaluated on six classes for the MACHO dataset and 20 distinct classes of variable stars and transient events for the ELAsTiCC dataset. The fine-tuned SwinV2 achieved better performance than models specifically designed for light curves, such as Astromer and the Astronomical Transformer for Time Series and Tabular Data (ATAT). When trained on the full MACHO dataset, it attained a macro F1-score of 80.2 and outperformed Astromer in single-band experiments. Incorporating a second band further improved performance, increasing the F1-score to 84.1. In the ELAsTiCC dataset, SwinV2 achieved a macro F1-score of 65.5, slightly surpassing ATAT by 1.3.

References in corpus (39)

• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The MACHO Project: Microlensing Results from 5.7 Years of LMC Observations
• On Machine-Learned Classification of Variable Stars with Sparse and Noisy Time-Series Data
• Photometric Supernova Classification With Machine Learning
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• RAPID: Early Classification of Explosive Transients using Deep Learning
• Models and Simulations for the Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC)
• Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
• A recurrent neural network for classification of unevenly sampled variable stars
• Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation
• Deep Recurrent Neural Networks for Supernovae Classification
• QSO Selection Algorithm Using Time Variability and Machine Learning: Selection of 1,620 QSO Candidates from MACHO LMC Database
• SuperRAENN: A Semi-supervised Supernova Photometric Classification Pipeline Trained on Pan-STARRS1 Medium Deep Survey Supernovae
• The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database
• A novel variability-based method for quasar selection: evidence for a rest frame ~54 day characteristic timescale
• The MACHO Project LMC Variable Star Inventory IV: Multimode RR Lyrae Stars, Distance to the LMC and Age of the Oldest Stars
• Deep learning Approach for Classifying, Detecting and Predicting Photometric Redshifts of Quasars in the Sloan Digital Sky Survey Stripe 82
• Supernova Photometric Classification Pipelines Trained on Spectroscopically Classified Supernovae from the Pan-STARRS1 Medium-Deep Survey
• A simple and robust method for automated photometric classification of supernovae using neural networks
• Deep-Learnt Classification of Light Curves
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• Deep Learning for Image Sequence Classification of Astronomical Events
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• The MACHO Project LMC Variable Star Inventory. VI. The Second-overtone Mode of Cepheid Pulsation From First/Second Overtone (FO/SO) Beat Cepheids
• ASTROMER: A transformer-based embedding for the representation of light curves
• An improved quasar detection method in EROS-2 and MACHO LMC datasets
• The MACHO Project LMC Variable Star Inventory: XII. Three Cepheid Variables in Eclipsing Binaries
• Feature Selection Strategies for Classifying High Dimensional Astronomical Data Sets
• Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves
• Classifying Image Sequences of Astronomical Transients with Deep Neural Networks
• Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data
• Photometric Classification of Early-Time Supernova Lightcurves with SCONE
• Variable star classification with a Multiple-Input Neural Network
• ATAT: Astronomical Transformer for time series And Tabular data
• The effect of phased recurrent units in the classification of multiple catalogs of astronomical lightcurves
• The Catalina Real-time Transient Survey
• Transient Classifiers for Fink: Benchmarks for LSST
• Application of Convolutional Neural Networks to time domain astrophysics. 2D image analysis of OGLE light curves

Cited by in corpus (2)

• The automation of optical transient discovery and classification in Rubin-era time-domain astronomy
• Multiband neural network classification of ZTF light curves as LSST proxies