A simple and robust method for automated photometric classification of supernovae using neural networks
arXiv:1208.1264 · doi:10.1093/mnras/sts412
Abstract
A method is presented for automated photometric classification of supernovae (SNe) as Type-Ia or non-Ia. A two-step approach is adopted in which: (i) the SN lightcurve flux measurements in each observing filter are fitted separately; and (ii) the fitted function parameters and their associated uncertainties, along with the number of flux measurements, the maximum-likelihood value of the fit and Bayesian evidence for the model, are used as the input feature vector to a classification neural network (NN) that outputs the probability that the SN under consideration is of Type-Ia. The method is trained and tested using data released following the SuperNova Photometric Classification Challenge (SNPCC). We consider several random divisions of the data into training and testing sets: for instance, for our sample D_1 (D_4), a total of 10% (40%) of the data are involved in training the algorithm and the remainder used for blind testing of the resulting classifier; we make no selection cuts. Assigning a canonical threshold probability of p_th=0.5 on the NN output to classify a SN as Type-Ia, for the sample D_1 (D_4) we obtain a completeness of 0.78 (0.82), purity of 0.77 (0.82), and SNPCC figure-of-merit of 0.41 (0.50). Including the SN host-galaxy redshift and its uncertainty as additional inputs to the NN results in a modest 5-10% increase in these values. We find that the classification quality does not vary significantly with SN redshift. Moreover, our probabilistic classification method allows one to calculate the expected completeness, purity or other measures of classification quality as a function of the p_th, without knowing the true classes of the SNe in the testing sample. The method may thus be improved further by optimising p_th and can easily be extended to divide non-Ia SNe into their different classes.
arXiv comment8 pages, 4 figures. v3: Version accepted for publication in MNRAS; minor changes from previous version to address referees' comments
References in corpus (40)
- Observational Evidence from Supernovae for an Accelerating Universe and a Cosmological Constant
- Measurements of Omega and Lambda from 42 High-Redshift Supernovae
- MultiNest: an efficient and robust Bayesian inference tool for cosmology and particle physics
- Multimodal nested sampling: an efficient and robust alternative to MCMC methods for astronomical data analysis
- Type Ia Supernova Explosion Models
- The WiggleZ Dark Energy Survey: mapping the distance-redshift relation with baryon acoustic oscillations
- Supernova Constraints and Systematic Uncertainties from the First 3 Years of the Supernova Legacy Survey
- First-year Sloan Digital Sky Survey-II (SDSS-II) Supernova Results: Hubble Diagram and Cosmological Parameters
- SNLS3: Constraints on Dark Energy Combining the Supernova Legacy Survey Three Year Data with Other Probes
- The Observed Growth of Massive Galaxy Clusters I: Statistical Methods and Cosmological Constraints
- K-corrections and Extinction Corrections for Type Ia Supernovae
- The Sloan Digital Sky Survey-II Supernova Survey: Search Algorithm and Follow-up Observations
- Large Synoptic Survey Telescope: Overview
- Results from the Supernova Photometric Classification Challenge
- Photometric SN Ia Candidates from the Three-Year SDSS-II SN Survey Data
- The Core-collapse rate from the Supernova Legacy Survey
- Constraints on Type Ib/c and GRB Progenitors
- Photometric selection of high-redshift type Ia supernovae
- Improved constraints on cosmological parameters from SNIa data
- Constraining dark matter halo properties using lensed SNLS supernovae
- Not Color Blind: Using Multiband Photometry to Classify Supernovae
- Bayesian Estimation Applied to Multiple Species: Towards cosmology with a million supernovae
- Type II-P Supernovae from the SDSS-II Supernova Survey and the Standardized Candle Method
- A Fundamental Test of the Nature of Dark Matter
- Bayesian Single-Epoch Photometric Classification of Supernovae
- Gravitational Lensing of High Redshift Type Ia Supernova: A Probe of Medium Scale Structure
- Learning from the Scatter in Type Ia Supernovae
- Semi-supervised Learning for Photometric Supernova Classification
- A Probabilistic Approach to Classifying Supernovae Using Photometric Information
- Fuzzy Supernova Templates I: Classification
- Gravitational lensing in the Supernova Legacy Survey (SNLS)
- Photometric Identification of Type Ia Supernovae at Moderate Redshift
- Statistical Classification Techniques for Photometric Supernova Typing
- Cosmology with Photometric Surveys of Type Ia Supernovae
- Model-Independent Reconstruction of the Expansion History of the Universe from Type Ia Supernovae
- Tentative detection of the gravitational magnification of type Ia supernovae
- The Effect of Type Ibc Contamination in Cosmological Supernova Samples
- Utilizing Type Ia Supernovae in a Large, Fast, Imaging Survey to Constrain Dark Energy
- Weighing dark matter haloes with gravitationally lensed supernovae
- Characterizing the contaminating distance distribution for Bayesian supernova cosmology
Cited by in corpus (43)
- Importance Nested Sampling and the MultiNest Algorithm
- Photometric Supernova Classification With Machine Learning
- The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
- Automated Transient Identification in the Dark Energy Survey
- RAPID: Early Classification of Explosive Transients using Deep Learning
- Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation
- Deep Recurrent Neural Networks for Supernovae Classification
- SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
- Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream
- Theoretical Models of Optical Transients. I. A Broad Exploration of the Duration-Luminosity Phase Space
- Optimizing spectroscopic follow-up strategies for supernova photometric classification with active learning
- Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
- Kernel PCA for type Ia supernovae photometric classification
- Spectrophotometric templates for core collapse supernovae and their application in simulations of time-domain surveys
- Supernova Photometric Classification Pipelines Trained on Spectroscopically Classified Supernovae from the Pan-STARRS1 Medium-Deep Survey
- Photometric classification of type Ia supernovae in the SuperNova Legacy Survey with supervised learning
- Machine Learning Techniques for Stellar Light Curve Classification
- Dreaming of atmospheres
- PELICAN: deeP architecturE for the LIght Curve ANalysis
- The Young Supernova Experiment Data Release 1 (YSE DR1): Light Curves and Photometric Classification of 1975 Supernovae
- GHOST: Using Only Host Galaxy Information to Accurately Associate and Distinguish Supernovae
- Probing the stellar initial mass function with high- supernovae
- A probabilistic approach to emission-line galaxy classification
- Unsupervised machine learning for transient discovery in Deeper, Wider, Faster light curves
- Defining Photometric Peculiar Type Ia Supernovae
- Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves
- Photometric Classification of Early-Time Supernova Lightcurves with SCONE
- Classification of Multiwavelength Transients with Machine Learning
- Single-epoch supernova classification with deep convolutional neural networks
- Star formation and morphological properties of galaxies in the Pan-STARRS survey- I. A machine learning approach to galaxy and supernova classification
- Identifying complex sources in large astronomical data using a coarse-grained complexity measure
- HAFFET: Hybrid Analytic Flux FittEr for Transients
- Identifying anomalous radio sources in the EMU Pilot Survey using a complexity-based approach
- On the cosmological performance of photometrically classified supernovae with machine learning
- Understanding of the properties of neural network approaches for transient light curve approximations
- GausSN: Bayesian Time-Delay Estimation for Strongly Lensed Supernovae
- Photometric light curves classification with machine learning
- Leveraging pre-trained vision Transformers for multi-band photometric light curve classification
- Uncertainty estimation for time series classification: Exploring predictive uncertainty in transformer-based models for variable stars
- Using Random Forest Machine Learning Algorithms in Binary Supernovae Classification
- Artificial Neural Network for search for metal poor galaxies
- State Space Modelling for detecting and characterising Gravitational Waves afterglows
- A Template-Based Approach to the Photometric Classification of SN 1991bg-like Supernovae in the SDSS-II Supernova Survey