Identifying Light-curve Signals with a Deep-learning-based Object Detection Algorithm. II. A General Light-curve Classification Framework

• Published in: The Astrophysical journal. Supplement series Vol. 274; no. 2; pp. 29 - 52
• Main Authors: Cui, Kaiming, Armstrong, D. J., Feng, Fabo
• Format: Journal Article
• Language: English
• Published: Saskatoon The American Astronomical Society 01.10.2024; IOP Publishing
• Subjects: Algorithms; Anomalies; Astronomy data analysis; Celestial bodies; Classification; Convolutional neural networks; Deep learning; Feature extraction; Light curve; Light curve classification; Machine learning; Object recognition; Power spectra; Predictions; Sky surveys (astronomy); Space missions; Transient detection; Transients (astronomy); Variable stars
• ISSN: 0067-0049; 1538-4365; 1538-4365
• DOI: 10.3847/1538-4365/ad62fd

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 variable 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.