AI and the World's Hard Problems · Astronomy & space · arXiv · 2026-10-26
Quantitative modelling of type Ia supernovae spectral time series II: Exploring the diversity of thermonuclear explosion scenarios
Distinguishing explosion scenarios for Type Ia supernovae from spectra has been difficult, and qualitative comparison does not scale to large samples. The machine learning framework riddler combines neural-network emulators of radiative transfer with nested sampling to fit observed spectra and determine input parameters and scenario. It accurately recovered these for spectra not seen during training and was applied to SN 2011fe, SN 2005hk and SN 2018byg.