Identifying Light-curve Signals with a Deep Learning Based Object Detection Algorithm. II. A General Light Curve Classification Framework

Abstract

Vast amounts of astronomical photometric data are generated from various projects, requiring significant effort to identify variable stars and other object classes. In light of this, a general, widely applicable classification framework would simplify the process of designing specific classifiers for various astronomical objects. We present a novel deep learning framework for classifying light curves using a weakly supervised object detection model. Our framework identifies the optimal windows for both light curves and power spectra automatically, and zooms in on their corresponding data. This allows for automatic feature extraction from both time and frequency domains, enabling our model to handle data across different scales and sampling intervals. We train our model on data sets obtained from Kepler, TESS, and Zwicky Transient Facility multiband observations of variable stars and transients. We achieve an accuracy of 87% for combined variables and transient events, which is comparable to the performance of previous feature-based models. Our trained model can be utilized directly for other missions, such as the All-sky Automated Survey for Supernovae, without requiring any retraining or fine-tuning. To address known issues with miscalibrated predictive probabilities, we apply conformal prediction to generate robust predictive sets that guarantee true-label coverage with a given probability. Additionally, we incorporate various anomaly detection algorithms to empower our model with the ability to identify out-of-distribution objects. Our framework is implemented in the Deep-LC toolkit, which is an open-source Python package hosted on Github (https://github.com/ckm3/Deep-LC) and PyPI.

arXiv comment26 pages, 19 figures, 6 tables. Published on ApJS. Code is available on https://github.com/ckm3/Deep-LC

References in corpus (57)

• Array Programming with NumPy
• Astropy: A Community Python Package for Astronomy
• The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
• The Astropy Project: Sustaining and Growing a Community-oriented Open-source Project and the Latest Major Release (v5.0) of the Core Package
• The Transiting Exoplanet Survey Satellite
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• The Man Behind the Curtain: X-rays Drive the UV through NIR Variability in the 2013 AGN Outburst in NGC 2617
• The K2 Mission: Characterization and Early results
• Kepler Presearch Data Conditioning II - A Bayesian Approach to Systematic Error Correction
• Kepler Eclipsing Binary Stars. I. Catalog and Principal Characterization of 1879 Eclipsing Binaries in the First Data Release
• Assessing statistical significance of periodogram peaks
• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• Kepler Data Validation I -- Architecture, Diagnostic Tests, and Data Products for Vetting Transiting Planet Candidates
• Systematic evaluation of CNN advances on the ImageNet
• Planet Hunters X. KIC 8462852 - Where's the Flux?
• Periodograms for Multiband Astronomical Time Series
• The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
• 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)
• Gaia Data Release 2: Variable stars in the colour-absolute magnitude diagram
• Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
• A recurrent neural network for classification of unevenly sampled variable stars
• K2 Variable Catalogue II: Machine Learning Classification of Variable Stars and Eclipsing Binaries in K2 Fields 0-4
• Deep Recurrent Neural Networks for Supernovae Classification
• Gaia Data Release 2: The first Gaia catalogue of long-period variable candidates
• K2 Variable Catalogue: Variable Stars and Eclipsing Binaries in K2 Campaigns 1 and 0
• ExoMiner: A Highly Accurate and Explainable Deep Learning Classifier that Validates 301 New Exoplanets
• Deep Learning Classification in Asteroseismology Using an Improved Neural Network: Results on 15000 Kepler Red Giants and Applications to K2 and TESS Data
• Identifying Exoplanets with Deep Learning III: Automated Triage and Vetting of TESS Candidates
• Supernova Photometric Classification Pipelines Trained on Spectroscopically Classified Supernovae from the Pan-STARRS1 Medium-Deep Survey
• Systematic search for stellar pulsators in the eclipsing binaries observed by Kepler
• The ASAS-SN Catalog of Variable Stars X: Discovery of 116,000 New Variable Stars Using g-band Photometry
• Anomaly detection in the Zwicky Transient Facility DR3
• Machine Learning Techniques for Stellar Light Curve Classification
• 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
• A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients
• Recovery of TESS Stellar Rotation Periods Using Deep Learning
• Deep Learning for Image Sequence Classification of Astronomical Events
• Kepler Eclipsing Binary Stars. VIII. Identification of False Positive Eclipsing Binaries and Re-extraction of New Light Curves
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• Anomaly Detection in the Open Supernova Catalog
• ASTROMER: A transformer-based embedding for the representation of light curves
• Detecting Solar-like Oscillations in Red Giants with Deep Learning
• Classifying Kepler light curves for 12,000 A and F stars using supervised feature-based machine learning
• TESS Data for Asteroseismology (T'DA) Stellar Variability Classification Pipeline: Set-Up and Application to the Kepler Q9 Data
• Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves
• A method for finding anomalous astronomical light curves and their analogs
• Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data
• Persistent and occasional: searching for the variable population of the ZTF/4MOST sky using ZTF data release 11
• Identify Light-Curve Signals with Deep Learning Based Object Detection Algorithm. I. Transit Detection
• Accurate and Robust Stellar Rotation Periods catalog for 82771 Kepler stars using deep learning
• Density Based Outlier Scoring on Kepler Data
• Astroconformer: The Prospects of Analyzing Stellar Light Curves with Transformer-Based Deep Learning Models
• Long rotation period main-sequence stars from Kepler SAP light curves

Cited by in corpus (3)

• FALCO: a Foundation model of Astronomical Light Curves for time dOmain astronomy
• Heartbeat Stars Recognition Based on Recurrent Neural Networks: Method and Validation
• Predicting Stellar Parameters of Massive Stars from Light Curves with Machine Learning