Deep Learning and LLM-based Methods Applied to Stellar Lightcurve Classification
arXiv:2404.10757 · doi:10.34133/icomputing.0110
Abstract
Light curves serve as a valuable source of information on stellar formation and evolution. With the rapid advancement of machine learning techniques, it can be effectively processed to extract astronomical patterns and information. In this study, we present a comprehensive evaluation of deep-learning and large language model (LLM) based models for the automatic classification of variable star light curves, based on large datasets from the Kepler and K2 missions. Special emphasis is placed on Cepheids, RR Lyrae, and eclipsing binaries, examining the influence of observational cadence and phase distribution on classification precision. Employing AutoDL optimization, we achieve striking performance with the 1D-Convolution+BiLSTM architecture and the Swin Transformer, hitting accuracies of 94\% and 99\% correspondingly, with the latter demonstrating a notable 83\% accuracy in discerning the elusive Type II Cepheids-comprising merely 0.02\% of the total dataset.We unveil StarWhisper LightCurve (LC), an innovative Series comprising three LLM-based models: LLM, multimodal large language model (MLLM), and Large Audio Language Model (LALM). Each model is fine-tuned with strategic prompt engineering and customized training methods to explore the emergent abilities of these models for astronomical data. Remarkably, StarWhisper LC Series exhibit high accuracies around 90\%, significantly reducing the need for explicit feature engineering, thereby paving the way for streamlined parallel data processing and the progression of multifaceted multimodal models in astronomical applications. The study furnishes two detailed catalogs illustrating the impacts of phase and sampling intervals on deep learning classification accuracy, showing that a substantial decrease of up to 14\% in observation duration and 21\% in sampling points can be realized without compromising accuracy by more than 10\%.
35 pages, 20 figures
References in corpus (30)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Practical Bayesian Optimization of Machine Learning Algorithms
- LoRA: Low-Rank Adaptation of Large Language Models
- A Critical Review of Recurrent Neural Networks for Sequence Learning
- Understanding the Lomb-Scargle Periodogram
- EfficientNetV2: Smaller Models and Faster Training
- Kepler Eclipsing Binary Stars. I. Catalog and Principal Characterization of 1879 Eclipsing Binaries in the First Data Release
- QLoRA: Efficient Finetuning of Quantized LLMs
- Kepler Eclipsing Binary Stars. VII. The Catalog of Eclipsing Binaries Found in the Entire Kepler Data-Set
- Kepler Eclipsing Binary Stars. II. 2165 Eclipsing Binaries in the Second Data Release
- Kepler Eclipsing Binary Stars. III. Classification of Kepler Eclipsing Binary Light Curves with Locally Linear Embedding
- Kepler Eclipsing Binary Stars. IV. Precise Eclipse Times for Close Binaries and Identification of Candidate Three-Body Systems
- Machine Learning for the Zwicky Transient Facility
- The flare catalog and the flare activity in the Kepler mission
- One Fits All:Power General Time Series Analysis by Pretrained LM
- Deep Recurrent Neural Networks for Supernovae Classification
- Results of a Search for gamma Dor and delta Sct Stars with the Kepler Spacecraft
- Machine Learning Techniques for Stellar Light Curve Classification
- DeepSeek-VL: Towards Real-World Vision-Language Understanding
- Kepler Eclipsing Binary Stars. VIII. Identification of False Positive Eclipsing Binaries and Re-extraction of New Light Curves
- Gaia luminosities of pulsating A-F stars in the Kepler field
- Efficient scheduling of astronomical observations. Application to the CARMENES radial-velocity survey
- Real-Time Detection of Anomalies in Large-Scale Transient Surveys
- Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
- Kepler Eclipsing Binary Stars. V. Identification of 31 Eclipsing Binaries in the K2 Engineering Data-set
- Distinguishing a planetary transit from false positives: a Transformer-based classification for planetary transit signals
- LightCurve MoE: A Dynamic Sparse Routing Mixture-of-Experts Architecture for Efficient Stellar Light Curve Classification
- InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning
- Statistical Learning from Biased Training Samples