EUVIMEDEUVIMED entdecken
Crossref

SELDON: Supernova Explosions Learned by Deep ODE Networks

Jiezhong Wu, Jack O'Brien, Jennifer Li, M. S. Krafczyk, Ved G. Shah, Amanda R. Wasserman, Daniel W. Apley, Gautham Narayan, Noelle I. Samia

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (32) · 26922-26930

DOI: 10.1609/aaai.v40i32.39904 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jiezhong Wu und 8 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The discovery rate of optical transients will explode to 10 million public alerts per night once the Vera C. Rubin Observatory’s Legacy Survey of Space and Time comes online, overwhelming the traditional physics-based inference pipelines. A continuous-time forecasting AI model is of interest because it can deliver millisecond-scale inference for thousands of objects per day, whereas legacy MCMC codes need hours per object. In this paper, we propose SELDON, a new continuous-time variational autoencoder for panels of sparse and irregularly time-sampled (gappy) astrophysical light curves that are nonstationary, heteroscedastic, and inherently dependent. SELDON combines a masked GRU-ODE encoder with a latent neural ODE propagator and an interpretable Gaussian-basis decoder. The encoder learns to summarize panels of imbalanced and correlated data even when only a handful of points are observed. The neural ODE then integrates this hidden state forward in continuous time, extrapolating to future unseen epochs. This extrapolated time series is further encoded by deep sets to a latent distribution that is decoded to a weighted sum of Gaussian basis functions, the parameters of which are physically meaningful. Such parameters (e.g., rise time, decay rate, peak flux) directly drive downstream prioritization of spectroscopic follow-up for astrophysical surveys. Beyond astronomy, the architecture of SELDON offers a generic recipe for interpretable and continuous-time sequence modeling in any time domain where data are multivariate, sparse, heteroscedastic, and irregularly spaced.

Zitieren

APA

Wu, J., O'Brien, J., Li, J., Krafczyk, M. S., Shah, V. G., Wasserman, A. R., Apley, D. W., Narayan, G., & Samia, N. I. (2026). SELDON: Supernova Explosions Learned by Deep ODE Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 40(32), 26922-26930. https://doi.org/10.1609/aaai.v40i32.39904

Vancouver

Wu J, O'Brien J, Li J, Krafczyk MS, Shah VG, Wasserman AR, et al. SELDON: Supernova Explosions Learned by Deep ODE Networks. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(32):26922-26930. doi:10.1609/aaai.v40i32.39904

BibTeX
@article{Wu2026,
  author = {Wu, Jiezhong and O'Brien, Jack and Li, Jennifer and Krafczyk, M. S. and Shah, Ved G. and Wasserman, Amanda R. and Apley, Daniel W. and Narayan, Gautham and Samia, Noelle I.},
  title = {SELDON: Supernova Explosions Learned by Deep ODE Networks},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {32},
  pages = {26922--26930},
  doi = {10.1609/aaai.v40i32.39904}
}
Kostenlos starten →