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 $0.091\pm 0.010$ mag, which corresponds to $0.074\pm 0.010$ mag if peculiar velocity contributions are removed. Trained models and codes are released at \href{https://github.com/georgestein/suPAErnova}{github.com/georgestein/suPAErnova}

23 pages, 8 Figures, 1 Table. Accepted to ApJ

References in corpus (14)

• Improved Distances to Type Ia Supernovae with Multicolor Light Curve Shapes: MLCS2k2
• The Spectroscopic Diversity of Type Ia Supernovae
• TensorFlow Distributions
• Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences
• Evidence for Two Distinct Populations of Type Ia Supernovae
• Optical Spectroscopy of Type Ia Supernovae
• Investigating the Diversity of Type Ia Supernova Spectra with the Open-Source Relational Database Kaepora
• Berkeley Supernova Ia Program: Data Release of 637 Spectra from 247 Type Ia Supernovae
• Diversity of supernovae Ia determined using equivalent widths of Si II 4000
• A metric space for type Ia supernova spectra
• Uncertainty Quantification with Generative Models
• deepSIP: Linking Type Ia Supernova Spectra to Photometric Quantities with Deep Learning
• PCAAE: Principal Component Analysis Autoencoder for organising the latent space of generative networks
• On the Time Variation of Dust Extinction and Gas Absorption for Type~Ia Supernovae Observed Through Non-uniform Interstellar Medium