A Probabilistic Autoencoder for Type Ia Supernovae Spectral Time Series
Abstract
We construct a physically-parameterized probabilistic autoencoder (PAE) to learn the intrinsic diversity of type Ia supernovae (SNe Ia) from a sparse set of spectral time series. The PAE is a two-stage generative model, composed of an Auto-Encoder (AE) which is interpreted probabilistically after training using a Normalizing Flow (NF). We demonstrate that the PAE learns a low-dimensional latent space that captures the nonlinear range of features that exists within the population, and can accurately model the spectral evolution of SNe Ia across the full range of wavelength and observation times directly from the data. By introducing a correlation penalty term and multi-stage training setup alongside our physically-parameterized network we show that intrinsic and extrinsic modes of variability can be separated during training, removing the need for the additional models to perform magnitude standardization. We then use our PAE in a number of downstream tasks on SNe Ia for increasingly precise cosmological analyses, including automatic detection of SN outliers, the generation of samples consistent with the data distribution, and solving the inverse problem in the presence of noisy and incomplete data to constrain cosmological distance measurements. We find that the optimal number of intrinsic model parameters appears to be three, in line with previous studies, and show that we can standardize our test sample of SNe Ia with an RMS of mag, which corresponds to mag if peculiar velocity contributions are removed. Trained models and codes are released at \href{https://github.com/georgestein/suPAErnova}{github.com/georgestein/suPAErnova}
Keywords
Cite
@article{arxiv.2207.07645,
title = {A Probabilistic Autoencoder for Type Ia Supernovae Spectral Time Series},
author = {George Stein and Uros Seljak and Vanessa Bohm and G. Aldering and P. Antilogus and C. Aragon and S. Bailey and C. Baltay and S. Bongard and K. Boone and C. Buton and Y. Copin and S. Dixon and D. Fouchez and E. Gangler and R. Gupta and B. Hayden and W. Hillebrandt and M. Karmen and A. G. Kim and M. Kowalski and D. Kusters and P. F. Leget and F. Mondon and J. Nordin and R. Pain and E. Pecontal and R. Pereira and S. Perlmutter and K. A. Ponder and D. Rabinowitz and M. Rigault and D. Rubin and K. Runge and C. Saunders and G. Smadja and N. Suzuki and C. Tao and R. C. Thomas and M. Vincenzi},
journal= {arXiv preprint arXiv:2207.07645},
year = {2022}
}
Comments
23 pages, 8 Figures, 1 Table. Accepted to ApJ