SCONE: Supernova Classification with a Convolutional Neural Network

Abstract

We present a novel method of classifying Type Ia supernovae using convolutional neural networks, a neural network framework typically used for image recognition. Our model is trained on photometric information only, eliminating the need for accurate redshift data. Photometric data is pre-processed via 2D Gaussian process regression into two-dimensional images created from flux values at each location in wavelength-time space. These "flux heatmaps" of each supernova detection, along with "uncertainty heatmaps" of the Gaussian process uncertainty, constitute the dataset for our model. This preprocessing step not only smooths over irregular sampling rates between filters but also allows SCONE to be independent of the filter set on which it was trained. Our model has achieved impressive performance without redshift on the in-distribution SNIa classification problem: $99.73\pm 0.26$% test accuracy with no over/underfitting on a subset of supernovae from PLAsTiCC's unblinded test dataset. We have also achieved $98.18\pm 0.3$% test accuracy performing 6-way classification of supernovae by type. The out-of-distribution performance does not fully match the in-distribution results, suggesting that the detailed characteristics of the training sample in comparison to the test sample have a big impact on the performance. We discuss the implication and directions for future work. All of the data processing and model code developed for this paper can be found in the SCONE software package located at github.com/helenqu/scone.

arXiv commentAccepted to AJ, all code available at https://github.com/helenqu/scone

References in corpus (24)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Observational Evidence from Supernovae for an Accelerating Universe and a Cosmological Constant
• Measurements of Omega and Lambda from 42 High-Redshift Supernovae
• Improving neural networks by preventing co-adaptation of feature detectors
• The Pan-STARRS1 Surveys
• The Sloan Digital Sky Survey-II Supernova Survey: Technical Summary
• SNANA: A Public Software Package for Supernova Analysis
• Photometric Supernova Classification With Machine Learning
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• The Difference Imaging Pipeline for the Transient Search in the Dark Energy Survey
• Results from the Supernova Photometric Classification Challenge
• Photometric SN Ia Candidates from the Three-Year SDSS-II SN Survey Data
• Models and Simulations for the Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC)
• Cosmology with Photometrically-Classified Type Ia Supernovae from the SDSS-II Supernova Survey
• Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation
• Deep Recurrent Neural Networks for Supernovae Classification
• Photometric classification of type Ia supernovae in the SuperNova Legacy Survey with supervised learning
• Photometric selection of Type Ia supernovae in the Supernova Legacy Survey
• First Cosmology Results Using Type Ia Supernovae From the Dark Energy Survey: Survey Overview and Supernova Spectroscopy
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• Supernova Photometric Classification Challenge
• Photometric classification and redshift estimation of LSST Supernovae
• Improved Photometric Classification of Supernovae using Deep Learning
• Single-epoch supernova classification with deep convolutional neural networks

Cited by in corpus (8)

• The Young Supernova Experiment Data Release 1 (YSE DR1): Light Curves and Photometric Classification of 1975 Supernovae
• The Dark Energy Survey 5-year photometrically identified Type Ia Supernovae
• Photometric Classification of Early-Time Supernova Lightcurves with SCONE
• Pan-chromatic photometric classification of supernovae from multiple surveys and transfer learning for future surveys
• Classifying Astronomical Transients Using Only Host Galaxy Photometry
• The Simulated Catalogue of Optical Transients and Correlated Hosts (SCOTCH)
• Searching for Anomalies in the ZTF Catalog of Periodic Variable Stars
• Understanding of the properties of neural network approaches for transient light curve approximations