ParSNIP: Generative Models of Transient Light Curves with Physics-Enabled Deep Learning

Abstract

We present a novel method to produce empirical generative models of all kinds of astronomical transients from datasets of unlabeled light curves. Our hybrid model, that we call ParSNIP, uses a neural network to model the unknown intrinsic diversity of different transients and an explicit physics-based model of how light from the transient propagates through the universe and is observed. The ParSNIP model predicts the time-varying spectra of transients despite only being trained on photometric observations. With a three-dimensional intrinsic model, we are able to fit out-of-sample multiband light curves of many different kinds of transients with model uncertainties of 0.04-0.06 mag. The representation learned by the ParSNIP model is invariant to redshift, so it can be used to perform photometric classification of transients even with heavily biased training sets. Our classification techniques significantly outperform state-of-the-art methods on both simulated (PLAsTiCC) and real (PS1) datasets with 2.3× and 2× less contamination respectively for classification of Type Ia supernovae. We demonstrate how our model can identify previously-unobserved kinds of transients and produce a sample that is 90% pure. The ParSNIP model can also estimate distances to Type Ia supernovae in the PS1 dataset with an RMS of 0.150 ± 0.007 mag compared to 0.155 ± 0.008 mag for the SALT2 model on the same sample. We discuss how our model could be used to produce distance estimates for supernova cosmology without the need for explicit classification.

Predicting resolved galaxy properties from photometric images using convolutional neural networks

“…Xu et al 2013;Kamdar et al 2016), inferred the halo mass distribution function (Charnock et al 2020) or predicted the galaxy-halo connection (Agarwal et al 2018;Jo & Kim 2019) using ML techniques. Finally, using ML cosmological parameters could be derived from redshift surveys (Ramanah et al 2019;Ntampaka et al 2020), supernova data (Escamilla-Rivera et al 2020;Wang et al 2020;Boone 2021) or maps of e.g. gas and stars (Villaescusa-Navarro et al 2021).…”