JSJinghang Shi

Jinghang Shi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jinghang Shi has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    AstroMMBench: A Benchmark for Evaluating Multimodal Large Language Model Capabilities in Astronomy

    by Jinghang Shi, Xiaoyu Tang, Yang Huang, Yuyang Li, Yanxia Zhang, Xiao Kong, Caizhan Yue, A-Li Luo

    Astronomical image interpretation requires not only visual perception, but also familiarity with domain-specific representations, observational conventions, and astrophysical reasoning. Although recent multimodal large language models (MLLMs) have shown strong general visual–language capabilities, their performance on specialized astronomical figures remains insufficiently evaluated. To address this gap, we introduce AstroMMBench, an astronomy-specific benchmark for evaluating MLLMs on figure-associated astronomical multiple-choice questions. AstroMMBench contains 592 expert-screened multiple-choice questions covering six major astrophysical subfields: Astrophysics of Galaxies, Cosmology and Extragalactic Astrophysics, Earth and Planetary Astrophysics, High Energy Astrophysical Phenomena, Instrumentation and Methods for Astrophysics, and Solar and Stellar Astrophysics. The questions were generated from astronomical figures and associated textual context through an automated pipeline, followed by multi-stage filtering and expert review to assess scientific correctness, image–question alignment, and answer uniqueness. Using AstroMMBench, we evaluated 25 selected MLLMs, including 22 open-source and 3 closed-source models. The results show substantial performance differences across models and astrophysical subfields. Ovis2-34B achieved the highest point-estimate overall accuracy of 71.3%, with performance comparable to strong closed-source models such as ChatGPT-4o and Doubao-1.5-vision-pro. Subfield-level analysis shows the lowest mean point-estimate performance in cosmology, whereas high-energy astrophysics exhibits substantial between-model variability rather than uniformly low performance. Question-only results on the 592 benchmark questions yielded 27.53% for Qwen2.5-VL-7B and 24.83% for InternVL3-38B, compared with image-present accuracies of 58.11% and 68.24%, respectively. These descriptive comparisons suggest a substantial contribution from visual input in the two models. AstroMMBench provides a structured and extensible resource for comparing model behavior on figure-associated astronomical questions.


  • Open Access

    Unveiling Quasars in Gaia DR3: Multimodal Classification and Redshift Estimation of BP/RP Sources with Deep Learning

    by Jing-Hang Shi, Yanxia Zhang, Changhua Li, Jingyi Zhang, Zihan Kang, Shirui Wei, Yuming Fu, Xue-Bing Wu, Xiao Kong, Ali Luo, et al.

    We present a multimodal deep learning framework that classifies stars, galaxies, and quasars and accurately estimates quasar redshifts using Gaia DR3’s low-resolution BP/RP (XP) spectra, alongside astrometric, photometric, and CatWISE mid-infrared data. Our hierarchical classification model achieves an overall accuracy of 99.90%. Evaluating class-specific performance under a one-versus-rest framework, a precision of 99.61% and a recall of 99.83% are achieved for quasars. Furthermore, our spectral redshift regression model, SpecNet-Z, attains an rms error of 0.0682, a normalized median absolute deviation ( σ NMAD ) of 0.0048, and a catastrophic outlier rate of only 0.42%, demonstrating superior performance in the template-fitting approach in Gaia DR3. Applying this framework to the 219 million sources with public XP spectra, we produce the XP-Quasars catalog, containing 123,342 high-purity quasar candidates. This catalog includes 3763 new candidates not listed in the official GDR3 QSO catalog. Our work provides a robust and scalable method that serves as a valuable resource for current active galactic nuclei and cosmological studies and as a vital precursor for the analysis of the complete XP spectra dataset anticipated in Gaia DR4. The XP-Quasar catalog and associated source code are publicly available via Zenodo ( https://doi.org/10.5281/zenodo.17960118 ) and GitHub ( https://github.com/Shijinghang/xp-quasars ).


  • Open Access

    Closing the Final Mile in Data-Driven Discovery: Interpreting Uncharted Celestial Sources with Large Language Models Across Multimodal Data

    by Yanxia Zhang, Zihan Kang, Jingyi Zhang, Jinghang Shi, Changhua Li

    For decades, astronomers have anticipated that vast data archives hold the potential for serendipitous discoveries, promising to reveal novel phenomena. However, the rapid growth of these datasets now risks outpacing our capacity for analysis, potentially burying intriguing ``known unknowns’’ and even ``unknown unknowns’’ beneath a deluge of numbers. This challenge has given rise to a data-driven research paradigm, which is aimed at uncovering potential patterns and anomalies within data that may lead to novel scientific discoveries. Although machine learning algorithms have proven highly effective in identifying patterns and anomalous candidates from these data, the critical final step of determining their physical nature from a diverse array of possibilities remains a formidable bottleneck. The sheer breadth of modern astrophysics exceeds the expertise of any individual, or any single team, especially when the focus of data-driven researchers is always directed at the data and algorithms themselves. The advent of large language models (LLMs), with their unprecedented breadth of knowledge, offers a transformative solution. In this study, we present a novel framework that leverages LLMs to interpret the nature of unusual sources. Our investigation commenced with anomalous sources identified by machine learning algorithms through the analysis of NEOWISE infrared light curves. We provided the models with both the light curves and spectral energy distributions (SEDs) of these objects, tasking them with describing the data and inferring the underlying physical nature and source type. We validated the reasonableness of the model's inferences using a curated set of well-studied rare variable sources. Subsequently, we applied the same methodology to previously unclassified sources absent from the SIMBAD database, successfully identified dozens of objects with high scientific potential and generated AI-proposed follow-up observation plans. Although the computational cost of running LLMs is often nontrivial, this framework, which focuses on a small subset of algorithmically preselected anomalies, remains computationally tractable. We argue that this methodology is not confined to time-domain and SED data but can be readily extended to other data modalities, including images and spectra, paving the way for accelerated discovery in the era of future large-scale sky surveys.

  • Stellar classification with convolutional neural networks and photometric images: a new catalogue of 50 million SDSS stars without spectra

    by Jing-Hang Shi, Bo Qiu, A-Li Luo, Zhen-Dong He, Xiao Kong, Xia Jiang

    Stellar classification is a central topic in astronomical research that relies mostly on the use of spectra. However, with the development of large sky surveys, spectra are becoming increasingly scarce compared to photometric images. Numerous observed stars lack spectral types. In Sloan Digital Sky Survey (SDSS), there are more than hundreds of millions of such stars. In this paper, we propose a convolutional neural network-based stellar classification network (SCNet) in an attempt to solve the stellar classification task from photometric images alone, distinguishing between seven classes, i.e. O, B, A, F, G, K, and M. A total of 46 245 identified stellar objects were collected from the SDSS as the training samples for our network. Compared to many typical classification networks in deep learning, SCNet achieves the best classification accuracy of 0.861. When we allow an error to be within three neighbouring subtypes for SCNet, the accuracy even reaches 0.907. We apply the final SCNet model to 50 245 638 SDSS stars without corresponding spectra and present a new star classification catalogue, containing 7438 O-type stars, 31 433 B-type stars, 201 189 A-type stars, 910 007 F-type stars, 10 986 055 G-type stars, 18 941 155 K-type stars, and 19 168 361 M-type stars.


  • Unsupervised clustering and analysis of WISE spiral galaxies

    by Xiaoyu Guo, Cuixiang Liu, Bo Qiu, A-Li Luo, Xia Jiang, Jinghang Shi, Xiaotong Li, Linqian Wang

    The Wide-Field Infrared Explorer (WISE) survey captured massive amounts of infrared astronomical object data, and different astronomical objects will show different characteristics. Especially spiral galaxies that are richer in colour than other astronomical objects. In addition, the Sloan Digital Sky Survey (SDSS) has obtained a large number of visible light images and their parameter. So this paper mainly explores the colour characteristics of WISE spiral galaxies, and uses SDSS, 2MASS, WISE, and MANGA parameters to analyse the differences between different classes and the commonality of the same class, so that provides help for astronomers to study infrared spiral galaxies. First, the RA and Dec. of the spiral galaxy samples were crossed in GalaxyZoo2. The flux data of w1, w2, and w3 bands in WISE were crossed for image synthesis. The Bootstrap Your Own Latent contrastive learning framework and K-means clustering were used to unsupervised classify the infrared spiral galaxy images. After multiple experiments, five classes of images were selected by referring to the best clustering results. Finally, the parameter of galaxies in SDSS, 2MASS, WISE, and MANGA catalogues were crossed, including redshift, 12 magnitudes that from visible light band to mid-infrared band, stellar formation rate, stellar metallicity, stellar velocity dispersion, etc. These parameters were qualitatively and quantitatively analyzed. The effectiveness of unsupervised clustering algorithms for handling unlabeled data is demonstrated and two special classes of galaxies are found. The analysis result shows that the distribution characteristics of different parameters of different classes of infrared spiral galaxies are different.


  • A photometry pipeline for SDSS images based on convolutional neural networks

    by Jing-Hang Shi, Bo Qiu, A-Li Luo, Zhen-Dong He, Xiao Kong, Xia Jiang

    In this paper, we propose a convolutional neural network (CNN)-based photometric pipeline for the Sloan Digital Sky Survey (SDSS) images. The pipeline includes three main parts: the target source detection, the target source classification, and the photometric parameter measurement. The last part is completed using traditional methods. The paper mainly focuses on the first two parts and does not present the last. In the 1st part, a network named TSD-YOLOv4 is proposed to detect new sources missed by the SDSS photometric pipeline according to the PhotoObjAll catalogue of SDSS. In the second part, a target source classification network named TSCNet is constructed to classify sources into galaxies, quasars, and stars directly from photometric images. Experiments show that TSD-YOLOv4 outperforms other networks (Faster-RCNN, YOLOv4, YOLOX, etc.) in all metrics, with an accuracy of 0.988, a recall of 0.997, and an F1-score of 0.992, and TSCNet has good performance with a classification accuracy of 0.944 on the test set with 23 265 sources, and precision rates of 0.98, 0.908, and 0.918 for galaxies, quasars, and stars, respectively. On the other hand, the recall rates are 0.982, 0.903, and 0.921 for galaxies, quasars, and stars, respectively. The TSCNet has higher accuracy, fewer parameters, and faster inference speed than the leading astronomical photometric source classification network, the APSCNet model. In addition, the effect of magnitude distribution on the classification results is discussed in the experiments. The experiments prove that the proposed pipeline can be used as a powerful tool to supplement the SDSS photometric catalogue.


  • Deep learning applications based on SDSS photometric data: detection and classification of sources

    by Zhendong He, Bo Qiu, A-Li Luo, Jinghang Shi, Xiao Kong, Xia Jiang

    Most astronomical source classification algorithms based on photometric data struggle to classify sources as quasars, stars, and galaxies reliably. To achieve this goal and build a new Sloan Digital Sky Survey photometric catalogue in the future, we apply a deep learning source detection network built on YOLO v4 object detection framework to detect sources and design a new deep learning classification network named APSCnet (astronomy photometric source classification network) to classify sources. In addition, a photometric background image generation network is applied to generate background images in the process of data sets synthesis. Our detection network obtains a mean average precision score of 88.02 when IOU = 0.5. As for APSCnet, in a magnitude range with 14–25, we achieve a precision of 84.1 ${{\ \rm per\ cent}}$ at 93.2 ${{\ \rm per\ cent}}$ recall for quasars, a precision of 94.5 ${{\ \rm per\ cent}}$ at 84.6 ${{\ \rm per\ cent}}$ recall for stars, and a precision of 95.8 ${{\ \rm per\ cent}}$ at 95.1 ${{\ \rm per\ cent}}$ recall for galaxies; and in a magnitude range with less than 20, we achieve a precision of 96.6 ${{\ \rm per\ cent}}$ at 94.7${{\ \rm per\ cent}}$ recall for quasars, a precision of 95.7${{\ \rm per\ cent}}$ at 97.4${{\ \rm per\ cent}}$ recall for stars, and a precision of 98.9 ${{\ \rm per\ cent}}$ at 99.2 ${{\ \rm per\ cent}}$ recall for galaxies. We have proved the superiority of our algorithm in the classification of astronomical sources through comparative experiments between multiple sets of methods. In addition, we also analysed the impact of point spread function on the classification results. These technologies may be applied to data mining of the next generation sky surveys, such as LSST, WFIRST, and CSST etc.