Research

SELDON: Supernova Explosions Learned by Deep ODE Networks

arXiv•March 4, 2026 ()•Jiezhong Wu, Jack O'Brien, Jennifer Li, M. S. Krafczyk, Ved G. Shah, Amanda R. Wasserman, Daniel W. Apley, Gautham Narayan, Noelle I. Samia

Professional Abstract

"The paper introduces SELDON, a novel continuous-time variational autoencoder designed to handle the challenges posed by the anticipated influx of optical transient alerts from the Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST). With projections estimating up to 10 million public alerts per night, traditional physics-based inference methods are at risk of being overwhelmed due to their slow processing times, often requiring hours for each object. SELDON aims to address this issue by providing millisecond-scale inference capabilities for thousands of astronomical objects daily. The core of SELDON's architecture is a masked GRU-ODE (Gated Recurrent Unit - Ordinary Differential Equation) encoder, which is adept at summarizing panels of sparse and irregularly sampled astrophysical light curves. These light curves are characterized by their nonstationary, heteroscedastic, and dependent nature, complicating traditional analysis methods. The encoder is designed to effectively learn from imbalanced and correlated data, even when only a limited number of observations are available. Following the encoding process, SELDON employs a neural ODE to propagate the learned hidden state forward in continuous time, allowing for the extrapolation of future observations that have not yet been recorded. This capability is crucial for timely decision-making in astrophysical surveys, where rapid follow-up observations can significantly enhance the understanding of transient phenomena. The extrapolated time series is subsequently encoded using deep sets, leading to a latent distribution that is decoded into a weighted sum of Gaussian basis functions. The parameters derived from this decoding process—such as rise time, decay rate, and peak flux—are not only interpretable but also physically meaningful, providing valuable insights for downstream tasks like prioritizing spectroscopic follow-ups. The implications of SELDON extend beyond astronomy, as its architecture offers a versatile framework for continuous-time sequence modeling applicable in various fields where data is multivariate, sparse, heteroscedastic, and irregularly spaced. This adaptability positions SELDON as a significant advancement in the field of machine learning and data analysis, promising to enhance the efficiency and effectiveness of data-driven decision-making in a range of scientific domains."

Technical Insights

1SELDON is designed to handle the anticipated 10 million optical transient alerts per night from the LSST, addressing the limitations of traditional physics-based inference pipelines.

2The model provides millisecond-scale inference capabilities, significantly improving processing speed compared to legacy MCMC codes that can take hours per object.

3The architecture incorporates a masked GRU-ODE encoder, which is effective at summarizing sparse and irregularly sampled astrophysical light curves.

4SELDON can learn from imbalanced and correlated data, even with limited observations, making it robust in real-world scenarios.

5A neural ODE is utilized to integrate the hidden state forward in continuous time, enabling the extrapolation of future unseen epochs.

6The model employs deep sets to encode the extrapolated time series into a latent distribution, enhancing the interpretability of the results.

7The decoding process results in a weighted sum of Gaussian basis functions, with parameters that are physically meaningful for astrophysical analysis.

8Key parameters such as rise time, decay rate, and peak flux directly inform the prioritization of spectroscopic follow-up observations.

9SELDON's architecture is applicable beyond astronomy, providing a generic framework for interpretable continuous-time sequence modeling in various scientific fields.