Transient-optimized real-bogus classification with Bayesian convolutional neural networks – sifting the GOTO candidate stream

@article{Killestein2021TransientoptimizedRC,
  title={Transient-optimized real-bogus classification with Bayesian convolutional neural networks – sifting the GOTO candidate stream},
  author={Thomas L. Killestein and Joseph D. Lyman and D. Steeghs and Kendall Ackley and Martin J Dyer and Krzysztof Ulaczyk and Ry Cutter and Y.-L. Mong and Duncan K. Galloway and Vik S. Dhillon and P. T. O’Brien and Gavin Ramsay and Saran Poshyachinda and Rubina Kotak and Rene P. Breton and Laura K Nuttall and Enric Pall'e and Don Pollacco and Eric Thrane and Suparerk Aukkaravittayapun and Supachai Awiphan and U. Burhanudin and Paul Robin Brian Chote and A. A. Chrimes and E J Daw and C Duffy and R A J Eyles-Ferris and Benjamin P. Gompertz and Teppo Heikkila and P. Irawati and Mark R. Kennedy and Andrew J. Levan and Stuart P. Littlefair and L. Makrygianni and Daniel Mata S'anchez and Seppo Mattila and Justyn R. Maund and J. McCormac and David Mkrtichian and James R. Mullaney and Evert Rol and Utane Sawangwit and Elizabeth R. Stanway and Rhaana L. C. Starling and Paul A. Str{\o}m and S M Tooke and Klaas Wiersema and S. C. Williams},
  journal={Monthly Notices of the Royal Astronomical Society},
  year={2021}
}
Large-scale sky surveys have played a transformative role in our understanding of astrophysical transients, only made possible by increasingly powerful machine learning-based filtering to accurately sift through the vast quantities of incoming data generated. In this paper, we present a new real-bogus classifier based on a Bayesian convolutional neural network that provides nuanced, uncertainty-aware classification of transient candidates in difference imaging, and demonstrate its application… 

The Gravitational-wave Optical Transient Observer (GOTO)

The Gravitational-wave Optical Transient Observer (GOTO) is a wide-field telescope project focused on detecting optical counterparts to gravitational-wave sources. GOTO uses arrays of 40 cm unit

The Gravitational-wave Optical Transient Observer (GOTO)

The Gravitational-wave Optical Transient Observer (GOTO) is a wide-field telescope project focused on detecting optical counterparts to gravitational-wave sources. Each GOTO robotic mount holds eight

Deep-learning real/bogus classification for the Tomo-e Gozen transient survey

A deep neural network real/bogus classifier is presented that improves classification performance in the Tomo-e Gozen Transient survey by handling label errors in the training data by saving relabeling effort by humans and works better on training data with a high fraction of label errors.

Identifying Transient Candidates in the Dark Energy Survey Using Convolutional Neural Networks

This work presents the results of an automated transient candidate identification on images with CNNs for an extant data set from the Dark Energy Survey Supernova program, whose main focus was on using Type Ia supernovae for cosmology.

Seeking new physics in cosmology with Bayesian neural networks: Dark energy and modified gravity

We study the potential of Bayesian Neural Networks (BNNs) to detect new physics in the dark matter power spectrum, concentrating here on evolving dark energy and modifications to General Relativity.

Searching for Fermi GRB optical counterparts with the prototype Gravitational-wave Optical Transient Observer (GOTO)

The typical detection rate of ∼1 gamma-ray burst (GRB) per day by the Fermi Gamma-ray Burst Monitor (GBM) provides a valuable opportunity to further our understanding of GRB physics. However, the

AI-driven spatio-temporal engine for finding gravitationally lensed supernovae

We present a spatio-temporal AI framework that concurrently exploits both the spatial and time-variable features of gravitationally lensed supernovae in optical images to ultimately aid in the

Light-curve classification with recurrent neural networks for GOTO: dealing with imbalanced data

A recurrent neural network (RNN) classifier that takes in photometric time-series data and additional contextual information to produce real-time classification of objects observed by the Gravitational-wave Optical Transient Observer is presented, and an algorithm-level approach for handling imbalance with a focal loss function is used.

References

SHOWING 1-10 OF 90 REFERENCES

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

The TensorFlow interface and an implementation of that interface that is built at Google are described, which has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields.

The handbook of brain theory and neural networks

A circular cribbage board having a circular base plate on which a circular counter disc, bearing a circular scale having 122 divisions numbered consecutively from 0, is mounted for rotation. A

Real-bogus classification for the Zwicky Transient Facility using deep learning

Braai, a convolutional-neural-network, deep-learning real/bogus classifier designed to separate genuine astrophysical events and objects from false positive, or bogus, detections in the data of the Zwicky Transient Facility, a new robotic time-domain survey currently in operation at the Palomar Observatory in California, USA.

LSST: From Science Drivers to Reference Design and Anticipated Data Products

The LSST design is driven by four main science themes: probing dark energy and dark matter, taking an inventory of the solar system, exploring the transient optical sky, and mapping the Milky Way.

Efficient object localization using Convolutional Networks

A novel architecture which includes an efficient `position refinement' model that is trained to estimate the joint offset location within a small region of the image to achieve improved accuracy in human joint location estimation is introduced.

The Handbook of Brain Theory and Neural Networks

The next sections will review the neural and mechanical mechanisms underlying vertebrates’ fascinating locomotor abilities, as well as energy efficiency (for swimming) and agility.

Using machine learning for discovery in synoptic survey imaging data

This work presents a machine learning (ML) framework for discovery of variability in time-domain imaging surveys and shows that the classification methodology is insensitive to mis-labelled training data up to a contamination of nearly 10%, making it easier to compile sufficient training sets for accurate performance in future surveys.

Bayesian Active Learning for Classification and Preference Learning

This work proposes an approach that expresses information gain in terms of predictive entropies, and applies this method to the Gaussian Process Classier (GPC), and makes minimal approximations to the full information theoretic objective.

The Pan-STARRS1 Surveys

Pan-STARRS1 has carried out a set of distinct synoptic imaging sky surveys including the $3\pi$ Steradian Survey and the Medium Deep Survey in 5 bands ($grizy_{P1}$). The mean 5$\sigma$ point source

The Gravitational-wave Optical Transient Observer (GOTO): Prototype performance and prospects for transient science

The Gravitational-wave Optical Transient Observer (GOTO) is an array of wide-field optical telescopes, designed to exploit new discoveries from the next generation of gravitational wave detectors
...