SELDON: Supernova Explosions Learned by Deep ODE Networks

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.

• Publication year

  2026

• Venue

  Unknown venue

• Publication date

  2026-03-04

• Fields of study

  Physics, Computer Science

• Identifiers
  arXiv 2603.04392
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• ORACLE: A Real-time, Hierarchical, Deep Learning Photometric Classifier for the LSST

  2025cited by this paper
• torchode: A Parallel ODE Solver for PyTorch

  2022influential reference
• Optimization of the Observing Cadence for the Rubin Observatory Legacy Survey of Space and Time: A Pioneering Process of Community-focused Experimental Design

  2021cited by this paper
• AUTO-ENCODING VARIATIONAL BAYES

  2020cited by this paper
• RAPID: Early Classification of Explosive Transients Using Deep Learning

  2019cited by this paper
• PELICAN: deeP architecturE for the LIght Curve ANalysis

  2019cited by this paper
• SuperNNova: an open-source framework for Bayesian, neural network-based supernova classification

  2019cited by this paper
• GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series

  2019cited by this paper
• Latent ODEs for Irregularly-Sampled Time Series

  2019cited by this paper
• GP-VAE: Deep Probabilistic Time Series Imputation

  2019cited by this paper
• Autoregressive Times Series Methods for Time Domain Astronomy

  2018cited by this paper
• Neural Ordinary Differential Equations

  2018cited by this paper
• Deep Sets

  2017cited by this paper
• Structured Inference Networks for Nonlinear State Space Models

  2016cited by this paper
• Sequential Neural Models with Stochastic Layers

  2016cited by this paper
• A Recurrent Latent Variable Model for Sequential Data

  2015cited by this paper
• On the Properties of Neural Machine Translation: Encoder–Decoder Approaches

  2014cited by this paper
• Learning Stochastic Recurrent Networks

  2014cited by this paper
• FLEXIBLE AND SCALABLE METHODS FOR QUANTIFYING STOCHASTIC VARIABILITY IN THE ERA OF MASSIVE TIME-DOMAIN ASTRONOMICAL DATA SETS

  2014cited by this paper
• Optical design of the LSST camera

  2008cited by this paper
• Optical Spectra of Supernovae

  2001cited by this paper

• No citing papers are available for this paper.