Surrogate models for type II supernovae: Probing low-energy explosions and interaction-free regimes

arXiv:2607.17488 · astro-ph.SR, astro-ph.HE, astro-ph.IM · Submitted 2026-07-20 · Read on arXiv

Zhengyang Zhang, Shuai Zha, Nikhil Sarin, Takashi J. Moriya, Chengyuan Wu, Bo Wang

astro-ph.SR, astro-ph.HE, astro-ph.IM

Submitted: 2026-07-20

Comments: 29 pages, 7 figures; accepted for publication in Physical Review D

DOI: 10.1103/hsms-7v8x36

Code: https://github.com/nikhil-sarin/redback

License: http://creativecommons.org/licenses/by/4.0/

The gist: To address the computational bottleneck of analyzing type II supernova samples from surveys such as the Legacy Survey of Space and Time, we present two STELLA-based neural-network surrogates: an

Terminology

Abstract

To address the computational bottleneck of analyzing type II supernova samples from surveys such as the Legacy Survey of Space and Time, we present two STELLA-based neural-network surrogates: an interaction model for low-energy explosions with possible circumstellar-material (CSM) interaction and a photospheric model for standard interaction-free SNe IIP. Each uses an autoencoder to compress spectral energy distributions and an emulator to map physical parameters to the latent space. Latent-mixup regularization improves latent-space continuity, with ResNet blocks used for the interaction model and 2D CNNs for the photospheric model. Their normalized test-set reconstruction MSEs are approximately 9.1e-5 and 1.0e-4, respectively. Applied to SN 2005cs, the interaction model favors a low-mass progenitor, M ZAMS = 10.40(+0.04/-0.05) M sun, and confined dense CSM, providing a scenario consistent with direct imaging and helping resolve the historical mass discrepancy. For SN 2012aw, it recovers M ZAMS = 11.05(+0.06/-0.06) M sun, consistent with previous studies. For SN 1999em, the photospheric model gives M ZAMS = 10.05(+0.07/-0.04) M sun, broadly consistent with preexplosion imaging limits without explicit CSM modeling. These surrogates reduce full Bayesian inference from days to minutes and enable rapid physical characterization of large supernova samples.

Sources

Related papers