Fink: early supernovae Ia classification using active learning

Abstract

We describe how the Fink broker early supernova Ia classifier optimizes its ML classifications by employing an active learning (AL) strategy. We demonstrate the feasibility of implementation of such strategies in the current Zwicky Transient Facility (ZTF) public alert data stream. We compare the performance of two AL strategies: uncertainty sampling and random sampling. Our pipeline consists of 3 stages: feature extraction, classification and learning strategy. Starting from an initial sample of 10 alerts (5 SN Ia and 5 non-Ia), we let the algorithm identify which alert should be added to the training sample. The system is allowed to evolve through 300 iterations. Our data set consists of 23 840 alerts from the ZTF with confirmed classification via cross-match with SIMBAD database and the Transient name server (TNS), 1 600 of which were SNe Ia (1 021 unique objects). The data configuration, after the learning cycle was completed, consists of 310 alerts for training and 23 530 for testing. Averaging over 100 realizations, the classifier achieved 89% purity and 54% efficiency. From 01/November/2020 to 31/October/2021 Fink has applied its early supernova Ia module to the ZTF stream and communicated promising SN Ia candidates to the TNS. From the 535 spectroscopically classified Fink candidates, 459 (86%) were proven to be SNe Ia. Our results confirm the effectiveness of active learning strategies for guiding the construction of optimal training samples for astronomical classifiers. It demonstrates in real data that the performance of learning algorithms can be highly improved without the need of extra computational resources or overwhelmingly large training samples. This is, to our knowledge, the first application of AL to real alerts data.

arXiv commentaccepted for publication in Astronomy and Astrophysics

References in corpus (22)

• The SIMBAD astronomical database
• SNANA: A Public Software Package for Supernova Analysis
• Photometric Supernova Classification With Machine Learning
• The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Real-bogus classification for the Zwicky Transient Facility using deep learning
• Results from the Supernova Photometric Classification Challenge
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• Machine Learning for the Zwicky Transient Facility
• Fink, a new generation of broker for the LSST community
• SPICY: The Spitzer/IRAC Candidate YSO Catalog for the Inner Galactic Midplane
• Transient processing and analysis using $\text{AMPEL}$: Alert Management, Photometry and Evaluation of Lightcurves
• Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream
• Optimizing spectroscopic follow-up strategies for supernova photometric classification with active learning
• Kernel PCA for type Ia supernovae photometric classification
• Photometric classification of type Ia supernovae in the SuperNova Legacy Survey with supervised learning
• Semi-supervised Learning for Photometric Supernova Classification
• Prediction of galaxy halo masses in SDSS DR7 via a machine learning approach
• Active Anomaly Detection for time-domain discoveries
• On the discovery of stars, quasars, and galaxies in the Southern Hemisphere with S-PLUS DR2
• Assessment of Supervised Machine Learning for Atmospheric Retrieval of Exoplanets
• An Active Instance-based Machine Learning method for Stellar Population Studies

Cited by in corpus (14)

• Combined spin orientation and phase function of asteroids
• Persistent and occasional: searching for the variable population of the ZTF/4MOST sky using ZTF data release 11
• Enabling the discovery of fast transients: A kilonova science module for the Fink broker
• Transient Classifiers for Fink: Benchmarks for LSST
• SNGuess: A method for the selection of young extragalactic transients
• ORACLE: A Real-Time, Hierarchical, Deep-Learning Photometric Classifier for the LSST
• Early Identification of Optical Tidal Disruption Events: A science module for the Fink broker
• ELEPHANT: ExtragaLactic alErt Pipeline for Hostless AstroNomical Transients
• Real-Time Active Learning for optimised spectroscopic follow-up: Enhancing early SN Ia classification with the Fink broker
• Uncertainty estimation for time series classification: Exploring predictive uncertainty in transformer-based models for variable stars
• The Tiny Time-series Transformer: Low-latency High-throughput Classification of Astronomical Transients using Deep Model Compression
• Explainable classification of astronomical uncertain time series
• Can AI Dream of Unseen Galaxies? Conditional Diffusion Model for Galaxy Morphology Augmentation
• PIE-ADA: Physics-Informed Ensemble with Adaptive Data Augmentation for Photometric Transient Classification