Physics-guided Deep Learning for the Classification of Wolf–Rayet Stars in DESI
The Astrophysical Journal Supplement Series · 01.05.2026 · 284 (1) · 14
DOI: 10.3847/1538-4365/ae562a ↗Kurz gefasst
Fachartikel in der Zeitschrift The Astrophysical Journal Supplement Series, online erschienen am 24.04.2026. Verfasst von Haoran Liu und 3 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shenzhen Fundamental Research Program.
Abstract (Originalsprache)
Wolf–Rayet (W-R) stars, which represent a key evolutionary stage of massive stars, exhibit strong stellar winds and broad emission lines. These features serve as direct tracers of stellar feedback and chemical enrichment in star-forming regions. Utilizing the recently released Dark Energy Spectroscopic Instrument (DESI) Data Release 1, we conduct a systematic search for W-R stars. To enhance physical interpretability while achieving high performance in the survey data, we introduce an improved model, LPA-MLK-CNN, which combines two key innovations: (i) a line-prior attention (LPA) mechanism that emphasizes diagnostic W-R emission lines by embedding astrophysical priors within a data-driven framework; (ii) a multiscale large-kernel convolutional neural network (MLK-CNN) structure that captures diverse emission-line features across stellar types. Trained on spectra from a six-class dataset, the model achieves significantly improved performance compared to conventional machine learning and deep learning baselines. When applied to the DESI spectral data, LPA-MLK-CNN recovers two newly discovered W-R candidates, contributing to the expansion of the W-R star catalog.
Förderung
- Shenzhen Fundamental Research Program
Zitieren
APA
Liu, H., Li, H., Li, R., & Jiang, B. (2026). Physics-guided Deep Learning for the Classification of Wolf–Rayet Stars in DESI. The Astrophysical Journal Supplement Series, 284(1), 14. https://doi.org/10.3847/1538-4365/ae562a
Vancouver
Liu H, Li H, Li R, Jiang B. Physics-guided Deep Learning for the Classification of Wolf–Rayet Stars in DESI. The Astrophysical Journal Supplement Series. 2026;284(1):14. doi:10.3847/1538-4365/ae562a
BibTeX
@article{Liu2026,
author = {Liu, Haoran and Li, Hongtai and Li, Ruijie and Jiang, Bin},
title = {Physics-guided Deep Learning for the Classification of Wolf–Rayet Stars in DESI},
journal = {The Astrophysical Journal Supplement Series},
year = {2026},
volume = {284},
number = {1},
pages = {14},
doi = {10.3847/1538-4365/ae562a}
}
EUVIMED