CCChenzhou Cui

Chenzhou Cui

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Chenzhou Cui has a total of 761 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Making Euclid VIS Imaging AI-ready: A Scalable Pipeline for Morphology, Anomaly Detection, and Similarity Search

    by Jinhui Xie, Yunfei Xu, Zhen Zhang, Lang Chen, Chenzhou Cui

    The Euclid mission is delivering an unprecedented volume of high-resolution galaxy imaging, posing new challenges for standardized and reproducible reuse across morphological analyses. We present a scalable pipeline that converts released VIS cutouts into standardized 224 × 224 model inputs and uses a pretrained DINOv2 ViT-S/14 feature extractor to construct a 365,513-row, 384-dimensional cutout-and-embedding product from the Galaxy Zoo Euclid (Q1) catalog. Initial production of the 365,513 released cutouts required approximately 48 hr, corresponding to an estimated end-to-end rate of 2.12 cutouts s −1 . The service supports batch task management, while persistent reuse of generated products avoids repeating mosaic extraction for matching requests; together with released-scale production, these mechanisms define the operational scalability considered here. The representation is evaluated with held-out regression, few-label classification, anomaly candidate prioritization, and similarity retrieval. Held-out ridge probes yield R 2 = 0.377–0.596 across four catalog quantities. Under a 1% total labeled budget that includes validation, frozen MLP macro-F1 is 0.802–0.861 for three tasks but 0.484 for the strongly imbalanced spiral task; limited final-block fine-tuning gives 0.810–0.850 for those three tasks and 0.520 for spiral. The historical anomaly workflow identifies 1681 configuration-dependent candidates, and the displayed examples illustrate image-quality failures without estimating their prevalence. These results show that a standardized image interface and a reusable pretrained embedding can support several downstream analyses at the scale of the released Euclid Q1 sample, while the quantitative performance and interpretation remain task dependent under the declared input and evaluation contracts.

  • Open Access

    Ellipsoidal modulation and multi-wavelength activity in the pre-cataclysmic binary RX J1553.0+4457

    by S.-Y. Wu, M. Gritsevich, Q.-H. Lao, A. J. Castro-Tirado, Z. Li, Y.-D. Hu, I. Pérez-García, R. Sánchez-Ramírez, N. Castro-Segura, E. J. Fernández-García, et al.

    Context. RX J1553.0+4457 (TMTS J15530469+4457458) is a detached post-common-envelope binary with a cool white dwarf and an active late-type companion. The origins of its optical modulation, rapid activity, and ultraviolet-to-mid-infrared spectral energy distribution (SED) remain unclear. Aims. We tested whether the dominant long-baseline Transiting Exoplanet Survey Satellite (TESS) waveform is ellipsoidal, characterised the rapid optical activity, and determined whether the SED requires a non-stellar component. Methods. We combined high-cadence Burst Observer and Optical Transient Exploring System (BOOTES) photometry, six sectors of TESS, Einstein Probe X-ray data, optical spectroscopy, and archival photometry to analyse orbital and flare variability, test timing significance with red-noise simulations and a moving-block bootstrap, fit the X-ray spectra, and model the SED. Results. BOOTES detected two optical flares separated by 3 h, with amplitudes of roughly 1–1.5 mag and faster decay at shorter wavelengths. The dominant TESS signal occurs at 2 f orb and yields P phot = 0.16756417 ± 0.00000118 d, consistent with spectroscopy. Its double-wave morphology identifies ellipsoidal modulation from a tidally distorted companion. We identify 19 conservative TESS flares, 14 of which exceed the 80% recovery-completeness threshold of 38.36 s in equivalent duration. Above this threshold, the calibrated bolometric energies span 2.2 × 10 33 − 2.8 × 10 34 erg, consistent with energetic flares from active M dwarfs. The Einstein Probe/Follow-up X-ray Telescope spectra show an approximately four-fold decline in the 0.3–10 keV flux, driven mainly by decreasing emission measures. The two stellar photospheres reproduce the SED without a hot-continuum or mid-infrared excess. A steady optically thick disc must have Ṁ ≲ 2 × 10 −12 M ⊙ yr −1 to remain hidden. Conclusions. RX J1553.0+4457 is a near-Roche-lobe-filling pre-cataclysmic binary with a stable optical waveform dominated by ellipsoidal modulation and rapid flares mainly tracing magnetic activity on the late-type companion. Weak wind-fed or intermittent accretion cannot be excluded, but the data do not require sustained Roche-lobe overflow, a luminous accretion disc, or an irradiation-powered optical component.

  • Open Access

    M-EPDet: Real-time Real–Bogus Classification and Transient Candidate Judgement for the EP-WXT Pipeline via Multimodal Data

    by Lang Chen, Yunfei Xu, Zhen Zhang, Dongyue Li, Hui Sun, Yuan Liu, Chenzhou Cui, Jinhui Xie, XiaoXiong Zuo, Shirui Wei, et al.

    The Wide-field X-ray Telescope (WXT) on board the Einstein Probe (EP) produces a large postdetection candidate stream in which genuine astrophysical sources coexist with instrumental artifacts and cosmic-ray events. We present M-EPDet, a three-step postdetection framework for real-time candidate vetting in EP-WXT lobster-eye micropore optics (MPO) data. The framework combines a ResNet-based arm filter, a dual-branch temporal–spectral cosmic-ray filter, and a background-aware Bayesian Blocks module for single-exposure variability screening. Using on-orbit EP-WXT observations, we report decoupled metrics for the cascading system. M-EPDet achieves a real–bogus recall of 98.31% (98.53% × 99.78%) for genuine astrophysical sources, together with rejection rates of 92.99% for instrumental artifacts and 98.18% for cosmic-ray events. In the final step, the Bayesian Blocks module flags 0.75% of the postfiltration observations, corresponding to a 99.25% reduction in candidate volume. The system is deployed in the EP-WXT pipeline as a lightweight real-time service, reducing the manual-inspection burden in candidate vetting.

  • Open Access

    A Value-added Physical Properties Catalog for Low-redshift Galaxies from DESI Legacy Imaging Surveys DR10

    by Shirui Wei, Changhua Li, Yanxia Zhang, Chenzhou Cui, Jinghang Shi, Wujun Shao, Zihan Kang, Yongheng Zhao, Maoyuan Huang

    Galaxy physical properties—such as star formation rate (SFR), stellar mass, and gas-phase metallicity—are essential for population studies and evolutionary analyses. Deriving these quantities for billions of galaxies in modern imaging surveys presents significant challenges due to limited spectroscopy and the computational costs associated with traditional spectral energy distribution fitting. As a result, many galaxies in large photometric surveys still lack homogeneous property estimates. This study introduces a multimodal deep learning model that integrates optical imaging with photometric catalog features to estimate SFR, stellar mass, and oxygen abundance in low-redshift galaxies. The model incorporates a ResNet-based convolutional neural network to extract spatial information from multiband images and a multilayer perceptron that processes catalog-level photometric features, leveraging complementary constraints from morphology, surface brightness, and broadband colors. Trained on reference measurements from the MPA-JHU DR8 catalog, the model is optimized for efficient large-scale estimation. When applied to the DESI Legacy Imaging Surveys (LS) DR10, the model generates a value-added catalog containing physical property estimates for approximately 547 million galaxies with redshifts z ≤ 0.5. Validation through comparisons with independent catalogs and exploration of key scaling relations demonstrates that while the derived properties are not intended for precision measurements of individual objects, they effectively capture the dominant astrophysical trends necessary for ensemble studies. This catalog represents the first homogeneous set of photometry-based SFR, stellar mass, and metallicity estimates for DESI LS DR10, providing a vital resource for statistical studies of galaxies in the local Universe and facilitating comparisons with current and future spectroscopic surveys.

  • Crafting and Deploying a Metaverse Curriculum Leveraging the WorldWide Telescope

    by Lei Liang, Yingchen Mao, Chenzhou Cui, Shanshan Li, Yuexin Wang, Xuemin Zhang

  • Open Access

    Extremely Luminous Optical Afterglow of an Energetic Gamma-Ray Burst GRB 230204B

    by Rahul Gupta, Judith Racusin, Vladimir Lipunov, Y.-D. Hu, Ashna Gulati, Alberto J. Castro-Tirado, Tara Murphy, Motoko Serino, Kirill Zhirkov, S. Shilling, et al.

    Robotic telescope networks play an important role in capturing early and bright optical afterglows, providing critical insights into the energetics and emission mechanisms of GRBs. In this study, we analyze GRB 230204B, an exceptionally energetic and multipulsed long GRB, detected by the Fermi Gamma-ray Burst Monitor and MAXI detectors, with an isotropic equivalent gamma-ray energy exceeding 10 54 erg. Time-resolved spectral analysis reveals a transition in the prompt emission from hard (sub-photospheric-dominated) spectra during early pulses to softer (synchrotron-radiation-dominated) spectra in later pulses, indicative of a hybrid jet composition. We report the discovery and characterization of the optical afterglow using the Mobile Astronomical System of Telescope-Robots (MASTER) and Burst Observer and Optical Transient Exploring System (BOOTES) robotic telescope networks, which enabled rapid follow-up observations starting at ∼1.3 ks post-burst. The optical luminosity at this time was exceptionally high, surpassing that of many other optically bright GRBs, such as GRB 990123 and GRB 080319B. This places the burst among the most luminous optical GRBs observed to date. Long-term radio observations extending to 335 days post-burst were conducted with the Australia Telescope Compact Array. Multiwavelength modeling, incorporating data from MASTER, BOOTES, Devasthal Optical Telescope, Swift/XRT, and radio observations, was conducted using an external interstellar medium (ISM) forward-shock top-hat jet model with afterglowpy . The results reveal a narrow and highly collimated jet with a circumburst density of n 0 ∼ 28.12 cm −3 , kinetic energy E K ∼ 4.18 × 10 55 erg, and a relatively low value of ϵ B = 2.14 × 10 −6 , indicating shock-compression of the magnetic field in the surrounding ISM. We constrained a low radiative efficiency of ∼4.3%. This study highlights the indispensable contribution of robotic networks to early afterglow observations and advances our understanding of GRB 230204B unique characteristics and underlying jet physics.


  • Open Access

    Deep learning-based astronomical multimodal data fusion: A comprehensive review

    by Wujun Shao, Dongwei Fan, Chenzhou Cui, Yunfei Xu, Shirui Wei, Xin Lyu


  • Open Access

    FALCO: Foundation Model of Astronomical Light Curves for Time Domain Astronomy. Implementation and Applications on Kepler Data

    by Xiaoxiong Zuo, Yihan Tao, Yang Huang, Zhixuan Kang, Huaxi Chen, Chenzhou Cui, Jiashu Pan, Xiao Kong, Yuan-Sen Ting, Xiaoyu Tang, et al.

    Time-domain surveys have advanced astronomical research by revealing diverse variable phenomena, from stellar flares to transient events. The scale and complexity of survey data, along with the demand for rapid classification, present significant challenges for analysis. While machine learning offers solutions, most existing models are tailored to single tasks, struggle to generalize, and depend heavily on large, accurately labeled datasets. This paper presents an initial implementation of FALCO, a foundation model trained on Kepler light curves via self-supervised learning using a Transformer-based architecture. The model has been evaluated on Kepler data across three distinct light-curve analysis tasks, and it demonstrates robust performance in all tasks, achieving an accuracy of 95% for stellar variability classification across eight classes, an overall RMSE of 0.1305 dex in surface gravity estimation (with significantly improved precision of RMSE < 0.08 dex at the low-gravity end where log g < 1, and 0.02 dex near log g ≈ 3), and a precision of 87% in flare identification. These results highlight the versatility of the foundation model in extracting generalizable representations from light curves, enabling easy adaptation to diverse tasks and making it a promising tool for time-domain analysis. Further analysis of model scaling and input light-curve sequence length reveals that larger models and longer input sequences improve performance. We have also applied the model to produce a comprehensive catalog of surface gravity (log g ) measurements for 179,732 Kepler stellar targets, using their light curves.


  • Open Access

    Quasar Candidate Selection and Redshift Estimation Using J-PLUS DR3 Data

    by Xingyu Yang, Changhua Li, Yanxia Zhang, Chenzhou Cui, Ji Li, Jingyi Zhang, Shirui Wei, Chao Tang, Xue-Bing Wu

    A comprehensive and high-purity quasar candidate catalogue with precise redshift measurements is crucial for advancing quasar research and cosmology. In the era of extensive sky surveys, the efficient identification of quasars from large-scale datasets has become a significant challenge in modern astronomy. By cross-matching the J-PLUS DR3 dataset with unWISE and numerous spectroscopic datasets with accurate classifications, we compiled a known sample of 740 562 sources, including 338 456 stars, 320 606 galaxies, and 81 500 quasars. Subsequently, we developed several classification models employing XGBoost, CatBoost, and deep learning techniques. Through optimization of feature selection and hyperparameter tuning for each model, we derived an optimal classification model. This model achieved an accuracy of 99 per cent, with the Precision and Recall for quasar detection reaching 98.20 per cent and 99.39 per cent, respectively. In parallel, we utilized the known quasar sample to train an optimal model for redshift estimation, achieving a mean squared error (MSE) of 0.139. Finally, combining the optimal classification and regression models, we designed an efficient workflow for quasar candidate selection and redshift estimation. This process resulted in the identification of over 3 million quasar candidates with photometric redshifts from the J-PLUS DR3 dataset. These candidates provide an invaluable input catalogue for subsequent observations by large-scale spectroscopic surveys, such as LAMOST, SDSS, DESI, or other ongoing efforts in this field.