The increasing size and complexity of data provided by both ongoing and planned galaxy surveys greatly contribute to our understanding of galaxy evolution. Deep learning methods are particularly well-suited for handling the complex and massive data. We train a convolutional neural network(CNN) to simultaneously predict the stellar populations in galaxies: age, metallicity, color excess E(B − V), and central velocity dispersion using spectra with redshift≤0.3 from the Sloan Digital Sky Survey. This is the first time to use spectra based on deep learning to derive the four galaxy properties. The testing results show that our CNN predictions of galaxy properties are in good consistent with values by the traditional stellar population synthesis method with little scatters(0.11 dex for age and metallicity, 0.018 mag for E(B − V), and 31 km s⁻¹ for velocity dispersion). In term of the computational time, our method reduces by more than 10 times compared to traditional method. We further evaluate the performance of our CNN prediction model using spectra with different signal-to-noise ratios(S/Ns), redshifts and spectral classes. We find that our model generally exhibits good performance although the errors at different S/Ns, redshifts and spectral classes vary slightly. The network architecture and related codes are publicly available on GitHub.

We first derive the stellar population properties: age and metallicity for ∼43,000 low redshift galaxies in the DR7 of the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) survey, which have no spectroscopic observations in the Sloan Digital Sky Survey (SDSS). We employ a fitting procedure based on the small-scale features of galaxy spectra so as to avoid possible biases from the uncertain flux calibration of the LAMOST spectroscopy. We show that our algorithm can successfully recover the average age and metallicity of the stellar populations of galaxies down to signal-to-noise ratio ≥5 through testing on both mock galaxies and real galaxies comprising LAMOST and their SDSS counterparts. We provide a catalog of the age and metallicity for ∼43,000 LAMOST galaxies online. As a demonstration of the scientific application of this catalog, we present the Holmberg effect on both age and metallicity of a sample of galaxies in galaxy pairs.

Rotation is a critical physical process operating in the formation of Am stars. There is a strong correlation between low-velocity rotation and chemical peculiarity. However, the existence of many non-chemical-peculiar slow rotators challenges the understanding of Am stars. The purpose of our work is to search for low-velocity rotating non-chemical-peculiar A-type stars and Am stars and to make a comparative analysis. In this paper, we pick out a sample from the LAMOST–Kepler project, including 21 Am stars, 125 non-chemical-peculiar slow rotators, and 53 non-chemical-peculiar fast rotators. We calculate the rotational frequencies through a periodic change of light curves caused by inhomogeneous stellar surfaces and then obtain the rotational velocities. For slow rotators, the age of Am stars is statistically younger than that of non-chemical-peculiar stars in the same temperature bin. In the comparison of the period, the average amplitude, and stellar mass of Am and non-chemical-peculiar stars, we discover that there is no difference in the photometric variability between Am and non-chemical-peculiar stars, which implies similar inhomogeneities on the surfaces. The average amplitude of non-chemical-peculiar stars has a downward trend with the increase of effective temperature and stellar mass, which is consistent with the theoretical prediction caused by weak dynamo-generated magnetic fields in A-type stars. In addition, we confirm four non-chemical-peculiar stars that have flares by checking field-of-view images, pixel images, and pixel-level light curves.

Aims. This study is aimed at deriving the age and metallicity of galaxies by proposing a novel multi-modal deep learning framework. This multi-modal framework integrates spectral and photometric data, offering advantages in cases where spectra are incomplete or unavailable. Methods. We propose a multi-modal learning method for estimating the age and metallicity of galaxies (MMLforGalAM). This method uses two modalities: spectra and photometric images as training samples. Its architecture consists of four models: a spectral feature extraction model (ℳ₁), a simulated spectral feature generation model (ℳ₂), an image feature extraction model (ℳ₃), and a multi-modal attention regression model (ℳ₄). Specifically, ℳ₁ extracts spectral features associated with age and metallicity from spectra observed by the Sloan Digital Sky Survey (SDSS). These features are then used as labels to train ℳ₂, which generates simulated spectral features for photometric images to address the challenge of missing observed spectra for some images. Overall, ℳ₁ and ℳ₂ provide a transformation from photometric to spectral features, with the goal of constructing a spectral representation of data pairs (photometric and spectral features) for multi-modal learning. Once ℳ₂ is trained, MMLforGalAM can then be applied to scenarios with only images, even in the absence of spectra. Then, ℳ₃ processes SDSS photometric images to extract features related to age and metallicity. Finally, ℳ₄ combines the simulated spectral features from ℳ₂ with the extracted image features from ℳ₃ to predict the age and metallicity of galaxies. Results. Trained on 36278 galaxies from SDSS, our model predicts the stellar age and metallicity, with a scatter of 1σ = 0.1506 dex for age and 1 σ = 0.1402 dex for metallicity. Compared to a single-modal model trained using only images, the multi-modal approach reduces the scatter by 27% for age and 15% for metallicity.

To enhance the efficiency, scalability, and cross-survey applicability of stellar parameter inference in large spectroscopic datasets, we present a modular, parallelized Python framework with automated error estimation, built on the LAMOST Atmospheric Parameter Pipeline (LASP) originally implemented in IDL. Rather than a direct code translation, this framework refactors LASP with two complementary modules: LASP-CurveFit, a new implementation of the LASP fitting procedure that runs on a CPU, preserving legacy logic while improving data I/O and multithreaded execution efficiency; and LASP-Adam-GPU, a GPU-accelerated method that introduces grouped optimization by constructing a joint residual function over multiple observed and model spectra, enabling high-throughput parameter inference across tens of millions of spectra. Applied to 10 million LAMOST spectra, the framework reduces runtime from 84 to 48 hr on the same CPU platform and to 7 hr on an NVIDIA A100 GPU, while producing results consistent with those from the original pipeline. The inferred errors agree well with the parameter variations from repeat observations of the same target (excluding radial velocities), while the official empirical errors used in LASP are more conservative. When applied to DESI DR1, our effective temperatures and surface gravities agree better with APOGEE than those from the DESI pipeline, particularly for cool giants, while the latter performs slightly better in radial velocity and metallicity. These results suggest that the framework delivers reliable accuracy, efficiency, and transferability, offering a practical approach to parameter inference in large spectroscopic surveys. The code and DESI-based catalog are available via DOI: 10.12149/101679 and DOI: 10.12149/101675 , respectively.