Search

White dwarfs represent the end stage for 97% of stars, making precise parameter measurement crucial for understanding stellar evolution. Traditional estimation methods involve fitting spectra or photometry, which require high-quality data. In recent years, machine learning has played a crucial role in processing spectral data due to its speed, automation, and accuracy. However, two common issues have been identified. First, most studies rely on data with high signal-to-noise ratios (SNR > 10), leaving many poor-quality datasets underutilized. Second, existing machine learning models, primarily based on convolutional networks, recurrent networks, and their variants, cannot simultaneously capture both the spatial and sequential information of spectra. To address these challenges, we designed the Estimator Network (EstNet), an advanced algorithm integrating multiple techniques, including Residual Networks, Squeeze and Excitation Attention, Gated Recurrent Units, Adaptive Loss, and Monte-Carlo Dropout Layers. We conducted parameter estimation on 5,965 poor-quality white dwarf spectra (R~1800, SNR~1.17), achieving average percentage errors of 14.86% for effective temperature and 3.97% for surface gravity. These results are significantly superior to other mainstream algorithms and consistent with the outcomes of traditional theoretical spectrum fitting methods. In the future, our algorithms will be applied for large-scale parameter estimation on the Chinese Space Station Telescope and the Large Synoptic Survey Telescope.

The age and mass of red giants are essential for understanding the structure and evolution of the Milky Way. Traditional isochrone methods for these estimations are inherently limited due to overlapping isochrones in the Hertzsprung-Russell diagram, while asteroseismology, though more precise, requires high-precision, long-term observations. In response to these challenges, we developed a novel framework, Spectral Transformer (SPT), to predict the age and mass of red giants aligned with asteroseismology from their spectra. A key component of SPT, the Multi-head Hadamard Self-Attention mechanism, designed specifically for spectra, can capture complex relationships across different wavelength. Further, we introduced a Mahalanobis distance-based loss function to address scale imbalance and interaction mode loss, and incorporated Monte Carlo dropout for quantitative analysis of prediction uncertainty.Trained and tested on 3,880 red giant spectra from LAMOST, the SPT achieved remarkable age and mass estimations with average percentage errors of 17.64% and 6.61%, respectively, and provided uncertainties for each corresponding prediction. The results significantly outperform those of traditional machine learning algorithms and demonstrate a high level of consistency with asteroseismology methods and isochrone fitting techniques. In the future, our work will leverage datasets from the Chinese Space Station Telescope and the Large Synoptic Survey Telescope to enhance the precision of the model and broaden its applicability in the field of astronomy and astrophysics., Comment: Accepted by A&A

Low-surface-brightness galaxies (LSBGs), fainter members of the galaxy population, are thought to be numerous. However, due to their low surface brightness, the search for a wide-area sample of LSBGs is difficult, which in turn limits our ability to fully understand the formation and evolution of galaxies as well as galaxy relationships. Edge-on LSBGs, due to their unique orientation, offer an excellent opportunity to study galaxy structure and galaxy components. In this work, we utilize the You Only Look Once object detection algorithm to construct an edge-on LSBG detection model by training on 281 edge-on LSBGs in Sloan Digital Sky Survey (SDSS) $gri$-band composite images. This model achieved a recall of 94.64% and a purity of 95.38% on the test set. We searched across 938,046 $gri$-band images from SDSS Data Release 16 and found 52,293 candidate LSBGs. To enhance the purity of the candidate LSBGs and reduce contamination, we employed the Deep Support Vector Data Description algorithm to identify anomalies within the candidate samples. Ultimately, we compiled a catalog containing 40,759 edge-on LSBG candidates. This sample has similar characteristics to the training data set, mainly composed of blue edge-on LSBG candidates. The catalog is available online at https://github.com/worldoutside/Edge-on_LSBG., Comment: 12 pages, 11 figures, accepted to be published on APJS

Very metal-poor (VMP, [Fe/H]<-2.0) stars offer a wealth of information on the nature and evolution of elemental production in the early galaxy and universe. The upcoming China Space Station Telescope (CSST) will provide us with a large amount of spectroscopic data that may contain plenty of VMP stars, and thus it is crucial to determine the stellar atmospheric parameters ($T_{eff}$, $\log g$, and [Fe/H]) for low-resolution spectra similar to the CSST spectra (R~200). In this paper, a two-dimensional Convolutional Neural Network (CNN) model with three convolutional layers and two fully connected layers is constructed. The principal aim of this work is to measure the ability of this model to estimate stellar parameters on low-resolution (R~200) spectra and to identify VMP stars so that we can better search for VMP stars in the spectra observed by CSST.We mainly use 10,008 observed spectra of VMP stars from LAMOST DR3, and 16,638 spectra of common stars ([Fe/H]>-2.0) from LAMOST DR8 for the experiment and make comparisons. All spectra are reduced to R~200 to match the resolution of the CSST and are preprocessed and collapsed into two-dimensional spectra for input to the CNN model. The results show that the MAE values are 99.40 K for $T_{eff}$, 0.22 dex for $\log g$, 0.14 dex for [Fe/H], and 0.26 dex for [C/Fe], respectively. Besides, the CNN model efficiently identifies VMP stars with a precision of 94.77%. The validation and practicality of this model are also tested on the MARCS synthetic spectra. This paper powerfully demonstrates the effectiveness of the proposed CNN model in estimating stellar parameters for low-resolution spectra (R~200) and recognizing VMP stars that are of interest for stellar population and galactic evolution work., Comment: 13 pages, 9 figures

Hot subdwarf stars are very important for understanding stellar evolution, stellar astrophysics, and binary star systems. Identifying more such stars can help us better understand their statistical distribution, properties, and evolution. In this paper, we present a new method to search for hot subdwarf stars in photometric data (b, y, g, r, i, z) using a machine learning algorithm, graph neural network, and Gaussian mixture model. We use a Gaussian mixture model and Markov distance to build the graph structure, and on the graph structure, we use a graph neural network to identify hot subdwarf stars from 86 084 stars, when the recall, precision, and f1 score are maximized on the original, weight and synthetic minority oversampling technique datasets. Finally, from 21 885 candidates, we selected approximately 6 000 stars that were the most similar to the hot subdwarf star.

Barium stars are chemically peculiar stars that exhibit enhancement of s-process elements. Chemical abundance analysis of barium stars can provide crucial clues for the study of the chemical evolution of the Galaxy. The Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) has released more than 6 million low-resolution spectra of FGK-type stars by Data Release 9 (DR9), which can significantly increase the sample size of barium stars. In this paper, we used machine learning algorithms to search for barium stars from low-resolution spectra of LAMOST. We have applied the Light Gradient Boosting Machine (LGBM) algorithm to build classifiers of barium stars based on different features, and build predictors for determining [Ba/Fe] and [Sr/Fe] of barium candidates. The classification with features in the whole spectrum performs best: for the sample with strontium enhancement, Precision = 97.81%, and Recall = 96.05%; for the sample with barium enhancement, Precision = 96.03% and Recall = 97.70%. In prediction, [Ba/Fe] estimated from BaII line at 4554 \r{A} has smaller dispersion than that from BaII line at 4934 \r{A}: MAE$_{4554 \r{A}}$ = 0.07, $\sigma_{4554 \r{A}}$ = 0.12. [Sr/Fe] estimated from SrII line at 4077 \r{A} performs better than that from SrII line at 4215 \r{A}: MAE$_{4077 \r{A}}$ = 0.09, $\sigma_{4077 \r{A}}$ = 0.16. A comparison of the LGBM and other popular algorithms shows that LGBM is accurate and efficient in classifying barium stars. This work demonstrated that machine learning can be used as an effective means to identify chemically peculiar stars and determine their elemental abundance., Comment: 13 pages, 6 figures

A small fraction of giants possess photospheric lithium(Li) abundance higher than the value predicted by the standard stellar evolution models, and the detailed mechanisms of Li enhancement are complicated and lack a definite conclusion. In order to better understand the Li enhancement behaviors, a large and homogeneous Li-rich giants sample is needed. In this study, we designed a modified convolutional neural network model called Coord-DenseNet to determine the A(Li) of Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) low-resolution survey (LRS) giant spectra. The precision is good on the test set: MAE=0.15 dex, and {\sigma}=0.21 dex. We used this model to predict the Li abundance of more than 900,000 LAMOST DR8 LRS giant spectra and identified 7,768 Li-rich giants with Li abundances ranging from 2.0 to 5.4 dex, accounting for about 1.02% of all giants. We compared the Li abundance estimated by our work with those derived from high-resolution spectra. We found that the consistency was good if the overall deviation of 0.27 dex between them was not considered. The analysis shows that the difference is mainly due to the high A(Li) from the medium-resolution spectra in the training set. This sample of Li-rich giants dramatically expands the existing sample size of Li-rich giants and provides us with more samples to further study the formation and evolution of Li-rich giants., Comment: 14 pages,13 figures

Low surface brightness (LSB) galaxies are galaxies with central surface brightness fainter than the night sky. Due to the faint nature of LSB galaxies and the comparable sky background, it is difficult to search LSB galaxies automatically and efficiently from large sky survey. In this study, we established the Low Surface Brightness Galaxies Auto Detect model (LSBG-AD), which is a data-driven model for end-to-end detection of LSB galaxies from Sloan Digital Sky Survey (SDSS) images. Object detection techniques based on deep learning are applied to the SDSS field images to identify LSB galaxies and estimate their coordinates at the same time. Applying LSBG-AD to 1120 SDSS images, we detected 1197 LSB galaxy candidates, of which 1081 samples are already known and 116 samples are newly found candidates. The B-band central surface brightness of the candidates searched by the model ranges from 22 mag arcsec $^ {- 2} $ to 24 mag arcsec $^ {- 2} $, quite consistent with the surface brightness distribution of the standard sample. 96.46\% of LSB galaxy candidates have an axis ratio ($b/a$) greater than 0.3, and 92.04\% of them have $fracDev\_r$\textless 0.4, which is also consistent with the standard sample. The results show that the LSBG-AD model learns the features of LSB galaxies of the training samples well, and can be used to search LSB galaxies without using photometric parameters. Next, this method will be used to develop efficient algorithms to detect LSB galaxies from massive images of the next generation observatories., Comment: 11 pages, 9 figures,accepted to be published on MNRAS

We present a new moving group clustered in kinematics, spatial position and elemental abundances. Its spatial position is around the center of the Local Arm of the Milky Way. A convergent point method was taken to select candidate member stars.\textbf{ Among 206 candidate member stars, 74 are pre-main-sequence stars and some of them have stellar disks.} We presume those pre-main sequence stars belong to Orion nebula. We suggest this moving group is caused by density wave of the Local Arm passing by., Comment: accepted by AJ

We present chemical abundances of 15 stars in the {\gamma} Leo moving group based on high-resolution spectra with the Subaru High Dispersion Spectrograph. The sample was picked up by applying wavelet transform to UVW velocity compo- nents of stars in the solar neighbourhood. Both photometric and spectroscopic method have been used to determine the stellar parameters of stars. Abun- dances of 11 elements including Na, Mg, Al, Si, Ca, Ti, Cr, Fe, Ni, Y and Ba are measured. Our results show that the member stars display a wide metallicity distribution with abundance ratios similar to Milky way disk stars. We presume that the {\gamma} Leo moving group is originated from dynamical effects probably related to the Galactic spiral arms., Comment: 21 pages, 6 figures, apj in press