Effective Image Differencing with ConvNets for Real-time Transient Hunting

Abstract

Large sky surveys are increasingly relying on image subtraction pipelines for real-time (and archival) transient detection. In this process one has to contend with varying PSF, small brightness variations in many sources, as well as artifacts resulting from saturated stars, and, in general, matching errors. Very often the differencing is done with a reference image that is deeper than individual images and the attendant difference in noise characteristics can also lead to artifacts. We present here a deep-learning approach to transient detection that encapsulates all the steps of a traditional image subtraction pipeline -- image registration, background subtraction, noise removal, psf matching, and subtraction -- into a single real-time convolutional network. Once trained the method works lighteningly fast, and given that it does multiple steps at one go, the advantages for multi-CCD, fast surveys like ZTF and LSST are obvious.

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• The Gaia mission
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science
• A New Algorithm For Difference Image Analysis
• Glitch Classification and Clustering for LIGO with Deep Transfer Learning
• Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection
• Evryscope science: exploring the potential of all-sky gigapixel-scale telescopes
• The IPAC Image Subtraction and Discovery Pipeline for the intermediate Palomar Transient Factory
• Deep-Learnt Classification of Light Curves
• The Palomar-Quest Digital Synoptic Sky Survey
• The Zwicky Transient Facility
• Machine-learning Selection of Optical Transients in Subaru/Hyper Suprime-Cam Survey

Cited by in corpus (24)

• Machine Learning for the Zwicky Transient Facility
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• Radio Galaxy Zoo: ClaRAN - A Deep Learning Classifier for Radio Morphologies
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• Image Subtraction in Fourier Space
• Deep Learning for Image Sequence Classification of Astronomical Events
• deepCR: Cosmic Ray Rejection with Deep Learning
• A variational encoder-decoder approach to precise spectroscopic age estimation for large Galactic surveys
• Deep Neural Network Classifier for Variable Stars with Novelty Detection Capability
• Machine Learning on Difference Image Analysis: A comparison of methods for transient detection
• Deriving star cluster parameters with convolutional neural networks. I. Age, mass, and size
• Machines Learn to Infer Stellar Parameters Just by Looking at a Large Number of Spectra
• DECORAS: detection and characterization of radio-astronomical sources using deep learning
• Stellar Spectral Interpolation using Machine Learning
• What's the Difference? The potential for Convolutional Neural Networks for transient detection without template subtraction
• Detecting optical transients using artificial neural networks and reference images from different surveys
• PyTorchDIA: A flexible, GPU-accelerated numerical approach to Difference Image Analysis
• Stellar Karaoke: deep blind separation of terrestrial atmospheric effects out of stellar spectra by velocity whitening
• Searching for Sub-Second Stellar Variability with Wide-Field Star Trails and Deep Learning
• A Possible Converter to Denoise the Images of Exoplanet Candidates through Machine Learning Techniques
• Time delay estimation in unresolved lensed quasars
• Real-time regression analysis with deep convolutional neural networks
• Textual interpretation of transient image classifications from large language models
• Physical Parameters of Stars in NGC 6397 Using ANN-Based Interpolation and Full Spectrum Fitting