PhDLspec: physical-prior embedded deep learning method for spectroscopic determination of stellar labels in high-dimensional parameter space
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911624846114816 |
|---|---|
| author | Wu, Tianmin Xiang, Maosheng Shi, Jianrong Zhang, Meng Mou, Lanya Yan, Hong-Liang Luo, A-Li |
| author_facet | Wu, Tianmin Xiang, Maosheng Shi, Jianrong Zhang, Meng Mou, Lanya Yan, Hong-Liang Luo, A-Li |
| contents | Unlocking the full physical information encoded in low-resolution spectra poses a significant challenge for astronomical survey analysis. Such a task demands modeling spectra and optimizing astrophysical parameters in high-dimensional space, as a consequence of line blending. Here we present PhDLspec -- a deep learning framework embedded with physical priors for stellar spectra modeling and analysis. By imposing differential spectra derived from ab initio stellar atmospheric model calculation on a transformer framework, PhDLspec can rigorously and precisely model stellar spectra by simultaneously taking into account more than 30 physical parameters, at a computational speed hundreds of times faster than ab initio model calculation. With such a flexible stellar modeling approach, PhDLspec can effectively derive ~30 stellar labels from a low-resolution spectrum using affordable optimization techniques. Application to LAMOST spectra (R~1800) yields stellar elemental abundances in good agreement with high-resolution spectroscopic surveys, following essential calibrations to correct systematic biases in elemental abundance estimates using wide binaries and reference high-resolution datasets. We provide a catalog of 25 elemental abundances for 116,611 subgiant stars with precise age estimates. The successful application of PhDLspec to LAMOST spectra for high-dimensional parameter determination sheds light on similar challenges faced by other surveys and disciplines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02730 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PhDLspec: physical-prior embedded deep learning method for spectroscopic determination of stellar labels in high-dimensional parameter space Wu, Tianmin Xiang, Maosheng Shi, Jianrong Zhang, Meng Mou, Lanya Yan, Hong-Liang Luo, A-Li Astrophysics of Galaxies Solar and Stellar Astrophysics Unlocking the full physical information encoded in low-resolution spectra poses a significant challenge for astronomical survey analysis. Such a task demands modeling spectra and optimizing astrophysical parameters in high-dimensional space, as a consequence of line blending. Here we present PhDLspec -- a deep learning framework embedded with physical priors for stellar spectra modeling and analysis. By imposing differential spectra derived from ab initio stellar atmospheric model calculation on a transformer framework, PhDLspec can rigorously and precisely model stellar spectra by simultaneously taking into account more than 30 physical parameters, at a computational speed hundreds of times faster than ab initio model calculation. With such a flexible stellar modeling approach, PhDLspec can effectively derive ~30 stellar labels from a low-resolution spectrum using affordable optimization techniques. Application to LAMOST spectra (R~1800) yields stellar elemental abundances in good agreement with high-resolution spectroscopic surveys, following essential calibrations to correct systematic biases in elemental abundance estimates using wide binaries and reference high-resolution datasets. We provide a catalog of 25 elemental abundances for 116,611 subgiant stars with precise age estimates. The successful application of PhDLspec to LAMOST spectra for high-dimensional parameter determination sheds light on similar challenges faced by other surveys and disciplines. |
| title | PhDLspec: physical-prior embedded deep learning method for spectroscopic determination of stellar labels in high-dimensional parameter space |
| topic | Astrophysics of Galaxies Solar and Stellar Astrophysics |
| url | https://arxiv.org/abs/2604.02730 |