Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Perspective
  • Published:

The automation of optical transient discovery and classification in Rubin-era time-domain astronomy

Nature Astronomy volume 9, pages 1764–1769 (2025)Cite this article

Subjects

Abstract

Robotic wide-field time-domain surveys, such as the Zwicky Transient Facility and the Asteroid Terrestrial-impact Last Alert System, capture dozens of transients each night. The workflows for discovering and classifying transients in survey data streams have become increasingly automated over decades of development. The recent integration of machine learning and artificial intelligence tools has produced major milestones, including the fully automated end-to-end discovery and classification of an optical transient, and has enabled automated rapid-response space-based follow-up. The now-operational Vera C. Rubin Observatory and its Legacy Survey of Space and Time are accelerating the rate of transient discovery and producing large volumes of data at incredible rates. Given the expected order-of-magnitude increase in transient discoveries, one promising path forwards for optical time-domain astronomy is heavily investing in accelerating the automation of our workflows. Here we review the current paradigm of real-time transient workflows, project their evolution during the Rubin era and present recommendations for accelerating transient astronomy with automation.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: The fully automated BTS discovery and classification workflow.

Similar content being viewed by others

Data availability

The data used to write this Perspective are available from the corresponding author upon request.

References

  1. Bellm, E. C. et al. The Zwicky Transient Facility: system overview, performance, and first results. Publ. Astron. Soc. Pac. 131, 018002 (2019).

    Article  Google Scholar 

  2. Tonry, J. L. et al. ATLAS: a high-cadence all-sky survey system. Publ. Astron. Soc. Pac. 130, 064505 (2018).

    Article  Google Scholar 

  3. Smith, K. W. et al. Design and operation of the ATLAS transient science server. Publ. Astron. Soc. Pac. 132, 085002 (2020).

    Article  Google Scholar 

  4. Ivezić, Žea LSST: from science drivers to reference design and anticipated data products. Astrophys. J. 873, 111 (2019).

    Article  Google Scholar 

  5. Bloom, J. S. et al. Automating discovery and classification of transients and variable stars in the synoptic survey era. Publ. Astron. Soc. Pac. 124, 1175 (2012).

    Article  Google Scholar 

  6. Brink, H. et al. Using machine learning for discovery in synoptic survey imaging data. Mon. Not. R. Astron. Soc. 435, 1047–1060 (2013).

    Article  Google Scholar 

  7. Wright, D. E. et al. Machine learning for transient discovery in Pan-STARRS1 difference imaging. Mon. Not. R. Astron. Soc. 449, 451–466 (2015).

    Article  Google Scholar 

  8. Goldstein, D. A. et al. Automated transient identification in the Dark Energy Survey. Astron. J. 150, 82 (2015).

    Article  Google Scholar 

  9. Duev, D. A. et al. Real-bogus classification for the Zwicky Transient Facility using deep learning. Mon. Not. R. Astron. Soc. 489, 3582–3590 (2019).

    Article  Google Scholar 

  10. Ayyar, V., Knop, R., Awbrey, A., Andersen, A. & Nugent, P. Identifying transient candidates in the Dark Energy Survey using convolutional neural networks. Publ. Astron. Soc. Pac. 134, 094501 (2022).

    Article  Google Scholar 

  11. Chen, Z. et al. TransientViT: a novel CNN-vision transformer hybrid real/bogus transient classifier for the Kilodegree Automatic Transient Survey. Preprint at https://arxiv.org/abs/2309.09937 (2023).

  12. Kim, D.-W., Yeo, D., Bailer-Jones, C. A. L. & Lee, G. Deep transfer learning for the classification of variable sources. Astron. Astrophys. 653, A22 (2021).

    Article  Google Scholar 

  13. Cabrera-Vives, G. et al. Domain adaptation via minimax entropy for real/bogus classification of astronomical alerts. Preprint at https://arxiv.org/abs/2308.07538 (2023).

  14. Gupta, R., Muthukrishna, D., Rehemtulla, N. & Shah, V. Transfer learning for transient classification: from simulations to real data and ZTF to LSST. Mon. Not. R. Astron. Soc. 542, L132–L138 (2025).

    Article  Google Scholar 

  15. Moreno-Cartagena, D. et al. Leveraging pre-trained visual transformers for multi-band photometric light curve classification. Preprint at https://arxiv.org/abs/2502.20479 (2025).

  16. Akeson, R. et al. The Wide Field Infrared Survey Telescope: 100 Hubbles for the 2020s. Preprint at https://arxiv.org/abs/1902.05569 (2019).

  17. Miller, A. A. et al. The La Silla Schmidt Southern Survey. Publ. Astron. Soc. Pac. 137, 094204 (2025).

    Article  Google Scholar 

  18. Förster, F. et al. The Automatic Learning for the Rapid Classification of Events (ALeRCE) alert broker. Astron. J. 161, 242 (2021).

    Article  Google Scholar 

  19. Möller, A. et al. FINK, a new generation of broker for the LSST community. Mon. Not. R. Astron. Soc. 501, 3272–3288 (2021).

    Article  Google Scholar 

  20. Fraga, B. M. O. et al. Transient classifiers for Fink: benchmarks for LSST. Astron. Astrophys. 692, A208 (2024).

    Article  Google Scholar 

  21. Matheson, T. et al. The ANTARES astronomical time-domain event broker. Astron. J. 161, 107 (2021).

    Article  Google Scholar 

  22. Nordin, J. et al. Transient processing and analysis using AMPEL: alert management, photometry, and evaluation of light curves. Astron. Astrophys. 631, A147 (2019).

    Article  MathSciNet  Google Scholar 

  23. Williams, R. D. et al. Enabling science from the Rubin alert stream with Lasair. RAS Technol. Instrum. 3, 362–371 (2024).

    Article  Google Scholar 

  24. Tachibana, Y. & Miller, A. A. A morphological classification model to identify unresolved PanSTARRS1 sources: application in the ZTF real-time pipeline. Publ. Astron. Soc. Pac. 130, 128001 (2018).

    Article  Google Scholar 

  25. Andreoni, I. et al. Fast-transient searches in real time with ZTFReST: identification of three optically discovered gamma-ray burst afterglows and new constraints on the kilonova rate. Astrophys. J. 918, 63 (2021).

    Article  Google Scholar 

  26. Smith, K. W. et al. Lasair: the transient alert broker for LSST:UK. Res. Notes Am. Astron. Soc. 3, 26 (2019).

    Google Scholar 

  27. Street, R. A., Bowman, M., Saunders, E. S. & Boroson, T. General-purpose software for managing astronomical observing programs in the LSST era. Proc. SPIE 10707, 1070711 (2018).

  28. Coulter, D. A. et al. YSE-PZ: a transient survey management platform that empowers the human-in-the-loop. Publ. Astron. Soc. Pac. 135, 064501 (2023).

    Article  Google Scholar 

  29. van der Walt, S. J., Crellin-Quick, A. & Bloom, J. S. SkyPortal: an astronomical data platform. J. Open Source Softw. 4, 1247 (2019).

    Article  Google Scholar 

  30. Coughlin, M. W. et al. A data science platform to enable time-domain astronomy. Astrophys. J. Suppl. Ser. 267, 31 (2023).

    Article  Google Scholar 

  31. Gomez, S. et al. FLEET: a redshift-agnostic machine learning pipeline to rapidly identify hydrogen-poor superluminous supernovae. Astrophys. J. 904, 74 (2020).

    Article  Google Scholar 

  32. Gomez, S. et al. Identifying tidal disruption events with an expansion of the FLEET machine-learning algorithm. Astrophys. J. 949, 113 (2023).

    Article  Google Scholar 

  33. Stein, R. et al. tdescore: an accurate photometric classifier for tidal disruption events. Astrophys. J. Lett. 965, L14 (2024).

    Article  Google Scholar 

  34. Sheng, X. et al. NEural Engine for Discovering Luminous Events (NEEDLE): identifying rare transient candidates in real time from host galaxy images. Mon. Not. R. Astron. Soc. 531, 2474–2492 (2024).

    Article  Google Scholar 

  35. Stevance, H. F. et al. The ATLAS virtual research assistant. Astrophys. J. 990, 201 (2025).

    Article  Google Scholar 

  36. Rehemtulla, N. et al. The Zwicky Transient Facility Bright Transient Survey. III. BTSbot: automated identification and follow-up of bright transients with deep learning. Astrophys. J. 972, 7 (2024).

    Article  Google Scholar 

  37. Steeghs, D. et al. The Gravitational-wave Optical Transient Observer (GOTO): prototype performance and prospects for transient science. Mon. Not. R. Astron. Soc. 511, 2405–2422 (2022).

    Article  Google Scholar 

  38. Killestein, T. L. et al. Kilonova seekers: the GOTO project for real-time citizen science in time-domain astrophysics. Mon. Not. R. Astron. Soc. 533, 2113–2132 (2024).

    Article  Google Scholar 

  39. Guidorzi, C. et al. The automatic real-time gamma-ray burst pipeline of the 2 m Liverpool Telescope. Publ. Astron. Soc. Pac. 118, 288–296 (2006).

    Article  Google Scholar 

  40. Cenko, S. B. et al. The automated Palomar 60 inch telescope. Publ. Astron. Soc. Pac. 118, 1396–1406 (2006).

    Article  Google Scholar 

  41. Miranda, N. et al. SNGuess: a method for the selection of young extragalactic transients. Astron. Astrophys. 665, A99 (2022).

    Article  Google Scholar 

  42. Rehemtulla, N. et al. The BTSbot-nearby discovery of SN 2024jlf: rapid, autonomous follow-up probes interaction in an 18.5 Mpc type IIP supernova. Astrophys. J. 985, 241 (2025).

    Article  Google Scholar 

  43. Gehrels, N. et al. The Swift gamma-ray burst mission. Astrophys. J. 611, 1005–1020 (2004).

    Article  Google Scholar 

  44. Soumagnac, M. T. et al. The MOST hosts survey: spectroscopic observation of the host galaxies of ~40,000 transients Using DESI. Astrophys. J. Suppl. Ser. 275, 22 (2024).

    Article  Google Scholar 

  45. Frohmaier, C. et al. Tides: The 4MOST time domain extragalactic survey. Astrophys. J. 992, 158 (2025).

    Article  Google Scholar 

  46. DESI Collaboration et al. The DESI Experiment part I: science, targeting, and survey design. Preprint at https://arxiv.org/abs/1611.00036 (2016).

  47. de Jong, R. S. et al. 4MOST: project overview and information for the first call for proposals. Messenger 175, 3–11 (2019).

    Google Scholar 

  48. Boone, K. Avocado: photometric classification of astronomical transients with Gaussian process augmentation. Astron. J. 158, 257 (2019).

    Article  Google Scholar 

  49. Muthukrishna, D., Narayan, G., Mandel, K. S., Biswas, R. & Hložek, R. RAPID: early classification of explosive transients using deep learning. Publ. Astron. Soc. Pac. 131, 118002 (2019).

    Article  Google Scholar 

  50. Villar, V. A. et al. SuperRAENN: a semisupervised supernova photometric classification pipeline trained on Pan-STARRS1 medium-deep survey supernovae. Astrophys. J. 905, 94 (2020).

    Article  Google Scholar 

  51. Qu, H., Sako, M., Möller, A. & Doux, C. SCONE: supernova classification with a convolutional neural network. Astron. J. 162, 67 (2021).

    Article  Google Scholar 

  52. Gagliano, A., Contardo, G., Foreman-Mackey, D., Malz, A. I. & Aleo, P. D. First impressions: early-time classification of supernovae using host-galaxy information and shallow learning. Astrophys. J. 954, 6 (2023).

    Article  Google Scholar 

  53. Shah, V. G., Gagliano, A., Malanchev, K., Narayan, G. & The LSST Dark Energy Science Collaboration. ORACLE: a real-time, hierarchical, deep-learning photometric classifier for the LSST. Preprint at https://arxiv.org/abs/2501.01496 (2025).

  54. Möller, A. & de Boissière, T. SuperNNova: an open-source framework for Bayesian, neural network-based supernova classification. Mon. Not. R. Astron. Soc. 491, 4277–4293 (2020).

    Article  Google Scholar 

  55. Möller, A. et al. The Dark Energy Survey 5-yr photometrically classified type Ia supernovae without host-galaxy redshifts. Mon. Not. R. Astron. Soc. 533, 2073–2088 (2024).

    Article  Google Scholar 

  56. The PLAsTiCC team et al. The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC): data set. Preprint at https://arxiv.org/abs/1810.00001 (2018).

  57. Kessler, R. et al. Models and Simulations for the Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC). Publ. Astron. Soc. Pac. 131, 094501 (2019).

    Article  Google Scholar 

  58. Narayan, G. & ELAsTiCC Team. The Extended LSST Astronomical Time-series Classification Challenge (ELAsTiCC). In American Astronomical Society Meeting Abstracts Vol. 241, 117.01 (The American Astronomical Society, 2023).

  59. Li, W. et al. StarEmbed: benchmarking time series foundation models on astronomical observations of variable stars. Preprint at https://arxiv.org/abs/2510.06200 (2025).

  60. Fremling, C. et al. The Zwicky Transient Facility Bright Transient Survey. I. Spectroscopic classification and the redshift completeness of local galaxy catalogs. Astrophys. J. 895, 32 (2020).

    Article  Google Scholar 

  61. Perley, D. A. et al. The Zwicky Transient Facility Bright Transient Survey. II. A public statistical sample for exploring supernova demographics. Astrophys. J. 904, 35 (2020).

    Article  Google Scholar 

  62. Bellm, E. C. et al. The Zwicky Transient Facility: surveys and scheduler. Publ. Astron. Soc. Pac. 131, 068003 (2019).

    Article  Google Scholar 

  63. Masci, F. J. et al. The Zwicky Transient Facility: data processing, products, and archive. Publ. Astron. Soc. Pac. 131, 018003 (2019).

    Article  Google Scholar 

  64. Mahabal, A. et al. Machine learning for the Zwicky Transient Facility. Publ. Astron. Soc. Pac. 131, 038002 (2019).

    Article  Google Scholar 

  65. Patterson, M. T. et al. The Zwicky Transient Facility alert distribution system. Publ. Astron. Soc. Pac. 131, 018001 (2019).

    Article  Google Scholar 

  66. Ben-Ami, S. et al. The SED Machine: a dedicated transient IFU spectrograph. Proc. SPIE 8446, 844686 (2012).

  67. Blagorodnova, N. et al. The SED machine: a robotic spectrograph for fast transient classification. Publ. Astron. Soc. Pac. 130, 035003 (2018).

    Article  Google Scholar 

  68. Kim, Y. L. et al. New modules for the SEDMachine to remove contaminations from cosmic rays and non-target light: BYECR and CONTSEP. Publ. Astron. Soc. Pac. 134, 024505 (2022).

    Article  Google Scholar 

  69. Rigault, M. et al. Fully automated integral field spectrograph pipeline for the SEDMachine: pysedm. Astron. Astrophys. 627, A115 (2019).

    Article  Google Scholar 

  70. Fremling, C. et al. SNIascore: deep-learning classification of low-resolution supernova spectra. Astrophys. J. Lett. 917, L2 (2021).

    Article  Google Scholar 

  71. Chaudhary, S. S. et al. Low-latency gravitational wave alert products and their performance at the time of the fourth LIGO-Virgo-KAGRA observing run. Proc. Natl Acad. Sci. USA 121, e2316474121 (2024).

    Article  Google Scholar 

  72. Kiendrebeogo, R. W. et al. Updated observing scenarios and multimessenger implications for the international gravitational-wave networks O4 and O5. Astrophys. J. 958, 158 (2023).

    Article  Google Scholar 

  73. Coughlin, M. W. et al. Optimizing searches for electromagnetic counterparts of gravitational wave triggers. Mon. Not. R. Astron. Soc. 478, 692–702 (2018).

    Article  Google Scholar 

  74. Coughlin, M. W. Lessons from counterpart searches in LIGO and Virgo’s third observing campaign. Nat. Astron. 4, 550–552 (2020).

    Article  Google Scholar 

  75. Wyatt, S. D. et al. The gravitational wave treasure map: a tool to coordinate, visualize, and assess the electromagnetic follow-up of gravitational-wave events. Astrophys. J. 894, 127 (2020).

    Article  Google Scholar 

  76. Tartaglia, L. et al. The early detection and follow-up of the highly obscured type II supernova 2016ija/DLT16am. Astrophys. J. 853, 62 (2018).

    Article  Google Scholar 

  77. Shrestha, M. et al. Extended shock breakout and early circumstellar interaction in SN 2024ggi. Astrophys. J. Lett. 972, L15 (2024).

    Article  Google Scholar 

  78. Rehemtulla, N. et al. Swift/UVOT observations of SN 2025qtt 6 minutes after its automatic discovery by BTSbot-nearby. Transient Name Server AstroNote 209 (2025).

  79. Tohuvavohu, A. et al. Swiftly chasing gravitational waves across the sky in real time. Astrophys. J. Lett. 975, L19 (2024).

    Article  Google Scholar 

  80. Street, R. A. et al. The Astrophysical Events Observatories Network (AEON). Proc. SPIE 11449, 1144925 (2020).

  81. Brown, T. M. et al. Las Cumbres Observatory Global Telescope network. Publ. Astron. Soc. Pac. 125, 1031 (2013).

    Article  Google Scholar 

  82. Steele, I. A. et al. The Liverpool Telescope: performance and first results. Proc. SPIE 5489, 679–692 (2004).

  83. Kumar, H. et al. India’s first robotic eye for time-domain astrophysics: the GROWTH-India telescope. Astron. J. 164, 90 (2022).

    Article  Google Scholar 

  84. Huppenkothen, D. et al. Constructing impactful machine learning research for astronomy: best practices for researchers and reviewers. Preprint at https://arxiv.org/abs/2310.12528 (2023).

Download references

Acknowledgements

We thank E. C. Bellm and Y. (Vic) Dong for their thoughtful comments. The ideas presented here have been improved through discussions at the Astroinformatics 2024 conference in Patagonia, Chile, and the 2025 Foundation Models for Astronomy Workshop at the Center for Computational Astrophysics of the Flatiron Institute. We thank the respective organizers and sponsors for providing rich discussion environments. Zwicky Transient Facility access for N.R. and A.A.M. was supported by Northwestern University and the Center for Interdisciplinary Exploration and Research in Astrophysics (CIERA). A.A.M. is supported by DoE award no. DE-SC0025599. A.A.M. is also supported by Cottrell Scholar award no. CS-CSA-2025-059 from the Research Corporation for Science Advancement. N.R. is supported by NSF award no. 2421845 and a Northwestern University Presidential Fellowship award. M.W.C. acknowledges support from the National Science Foundation under grant nos. PHY-2308862 and PHY-2117997. Based on observations obtained with the Samuel Oschin Telescope 48-inch and the 60-inch Telescope at the Palomar Observatory as part of the Zwicky Transient Facility project. ZTF is supported by the National Science Foundation under grant nos. AST-1440341 and AST-2034437 and currently award no. 2407588. ZTF receives additional funding from the ZTF partnership. Current members include Caltech, USA; Caltech/IPAC, USA; University of Maryland, USA; University of California, Berkeley, USA; University of Wisconsin at Milwaukee, USA; Cornell University, USA; Drexel University, USA; University of North Carolina at Chapel Hill, USA; Institute of Science and Technology, Austria; National Central University, Taiwan, and OKC, University of Stockholm, Sweden. Operations are conducted by Caltech’s Optical Observatory (COO), Caltech/IPAC and the University of Washington at Seattle, USA. SED Machine is based upon work supported by the National Science Foundation under grant no. 1106171. The Gordon and Betty Moore Foundation, through both the Data-Driven Investigator Program and a dedicated grant, provided critical funding for SkyPortal. This research has made use of NASA’s Astrophysics Data System.

Author information

Authors and Affiliations

  1. Department of Physics and Astronomy, Northwestern University, Evanston, IL, USA

    Nabeel Rehemtulla & Adam A. Miller

  2. Center for Interdisciplinary Exploration and Research in Astrophysics (CIERA), Evanston, IL, USA

    Nabeel Rehemtulla & Adam A. Miller

  3. NSF-Simons AI Institute for the Sky (SkAI), Chicago, IL, USA

    Nabeel Rehemtulla & Adam A. Miller

  4. School of Physics and Astronomy, University of Minnesota, Minneapolis, Minnesota, USA

    Michael W. Coughlin

  5. NSF Institute on Accelerated AI Algorithms for Data-Driven Discovery (A3D3) https://a3d3.ai/

    Michael W. Coughlin & Theophile Jegou du Laz

  6. Division of Physics, California Institute of Technology, Pasadena, CA, USA

    Theophile Jegou du Laz

Authors
  1. Nabeel Rehemtulla
    View author publications

    Search author on:PubMed Google Scholar

  2. Michael W. Coughlin
    View author publications

    Search author on:PubMed Google Scholar

  3. Adam A. Miller
    View author publications

    Search author on:PubMed Google Scholar

  4. Theophile Jegou du Laz
    View author publications

    Search author on:PubMed Google Scholar

Contributions

N.R. led the writing effort for all sections. M.W.C. wrote text in the main body and led the discussion of automation for multi-messenger astronomy. A.A.M. supported writing and copy-editing in all sections. T.J.d.L. provided consultation for technical details, wrote text in the main body and copy-edited. All authors jointly contributed to the conceptualizing the ideas presented here.

Corresponding author

Correspondence to Nabeel Rehemtulla.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Astronomy thanks Julien Peloton and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rehemtulla, N., Coughlin, M.W., Miller, A.A. et al. The automation of optical transient discovery and classification in Rubin-era time-domain astronomy. Nat Astron 9, 1764–1769 (2025). https://doi.org/10.1038/s41550-025-02720-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41550-025-02720-6

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing