Finding radio transients with anomaly detection and active learning based on volunteer classifications
Alex Andersson, Chris Lintott, Rob Fender, Michelle Lochner, Patrick Woudt, Jakob van den Eijnden, Alexander van der Horst, Assaf Horesh, Payaswini Saikia, Greg… 展开作者
Alex Andersson, Chris Lintott, Rob Fender, Michelle Lochner, Patrick Woudt, Jakob van den Eijnden, Alexander van der Horst, Assaf Horesh, Payaswini Saikia, Gregory R. Sivakoff, Lilia Tremou, Mattia Vaccari
In this work we explore the applicability of unsupervised machine learning algorithms to finding radio transients. Facilities such as the Square Kilometre Array (SKA) will provide huge volumes of data in which to detect rare transients; the challenge for astronomers is how to find them. We demonstrate the effectiveness of anomaly detection algorithms using 1.3 GHz light curves from the SKA precursor MeerKAT. We make use of three sets of descriptive parameters ('feature sets') as applied to two anomaly detection techniques in the Astronomaly package and analyse our performance by comparison with citizen science labels on the same dataset. Using transients found by volunteers as our ground truth, we demonstrate that anomaly detection techniques can recall over half of the radio transients in the 10 per cent of the data with the highest anomaly scores. We find that the choice of anomaly detection algorithm makes a minor difference, but that feature set choice is crucial, especially when considering available resources for human inspection and/or follow-up. Active learning, where human labels are given for just 2 per cent of the data, improves recall by up to 20 percentage points, depending on the combination of features and model used. The best performing results produce a factor of 5 times fewer sources requiring vetting by experts. This is the first effort to apply anomaly detection techniques to finding radio transients and shows great promise for application to other datasets, and as a real-time transient detection system for upcoming large surveys.
A Classifier-Based Approach to Multi-Class Anomaly Detection for Astronomical Transients
Irvington High School（欧文顿高中）；University of the Western Cape（西开普大学）；South African Radio Astronomy Observatory（南非射电天文观测台）；Massachusetts Institute of Technology（麻省理工学院）
Anomaly Hunter for Alerts (AHA): Anomaly Detection in the ZTF Transient Alert Stream
Breakthrough Listen, Department of Physics, University of Oxford（牛津大学物理系突破聆听项目）；Department of Physics, University of Oxford（牛津大学物理系）；SETI Institute（SETI研究所）；Berkeley SETI Research Center, University of California, Berkeley（加州大学伯克利分校伯克利SETI研究中心）；Astrophysics Research Centre, School of Mathematics and Physics, Queen’s University Belfast（贝尔法斯特女王大学数学与物理学院天体物理研究中心）
Tracing the Boundary of the South Atlantic Anomaly Region with SPHEREx Transient Flagging Rates
California Institute of Technology（加州理工学院）；Jet Propulsion Laboratory, California Institute of Technology（喷气推进实验室，加州理工学院）；Arizona State University（亚利桑那州立大学）；Rochester Institute of Technology（罗切斯特理工学院）
Data from current gravitational wave detectors contains a high rate of transient noise (glitches) that can trigger false detections and obscure true astrophysical events. Existing noise-detection algorithms largely rely on model-based methods that may miss noise transients unwitnessed by auxiliary sensors or with exotic morphologies. We propose the Unicorn Multi-window Anomaly-detection Pipeline (UniMAP): a model-free algorithm to identify and characterize transient noise leveraging the Temporal Outlier Factor (TOF) via a multi-window data-resampling scheme. We show this windowing scheme exten…
The observation of gravitational waves is hindered by the presence of transient noise (glitches). We study data from the third observing run of the Advanced LIGO detectors, and identify new glitch classes. Using training sets assembled by monitoring of the state of the detector, and by citizen-science volunteers, we update the Gravity Spy machine-learning algorithm for glitch classification. We find that a new glitch class linked to ground motion at the detector sites is especially prevalent, and identify two subclasses of this linked to different types of ground motion. Reclassification of da…
In the upcoming decade large astronomical surveys will discover millions of transients raising unprecedented data challenges in the process. Only the use of the machine learning algorithms can process such large data volumes. Most of the discovered transients will belong to the known classes of astronomical objects. However, it is expected that some transients will be rare or completely new events of unknown physical nature. The task of finding them can be framed as an anomaly detection problem. In this work, we perform for the first time an automated anomaly detection analysis in the photomet…
Lomonosov Moscow State University（莫斯科国立大学）；National Research University Higher School of Economics（俄罗斯高等经济大学）；Ural Federal University（乌拉尔联邦大学）；Carnegie Mellon University（卡内基梅隆大学）
Large modern surveys require efficient review of data in order to find transient sources such as supernovae, and to distinguish such sources from artefacts and noise. Much effort has been put into the development of automatic algorithms, but surveys still rely on human review of targets. This paper presents an integrated system for the identification of supernovae in data from Pan-STARRS1, combining classifications from volunteers participating in a citizen science project with those from a convolutional neural network. The unique aspect of this work is the deployment, in combination, of both …
We present results from applying the SNAD anomaly detection pipeline to the third public data release of the Zwicky Transient Facility (ZTF DR3). The pipeline is composed of 3 stages: feature extraction, search of outliers with machine learning algorithms and anomaly identification with followup by human experts. Our analysis concentrates in three ZTF fields, comprising more than 2.25 million objects. A set of 4 automatic learning algorithms was used to identify 277 outliers, which were subsequently scrutinised by an expert. From these, 188 (68%) were found to be bogus light curves -- includin…
The next generation of observatories will facilitate the discovery of new types of astrophysical transients. The detection of such phenomena, whose characteristics are presently poorly constrained, will hinge on the ability to perform blind searches. We present a new algorithm for this purpose, based on deep learning. We incorporate two approaches, utilising anomaly detection and classification techniques. The first is model-independent, avoiding the use of background modelling and instrument simulations. The second method enables targeted searches, relying on generic spectral and temporal pat…
AGILE is a space mission launched in 2007 to study X-ray and gamma-ray astronomy. The AGILE team developed real-time analysis pipelines to detect transient phenomena such as Gamma-Ray Bursts (GRBs) and to react to external science alerts received by other facilities. The AGILE anti-coincidence system (ACS) comprises five panels (four lateral and one on the top) that surround the AGILE detectors to reject background charged particles. It can also detect hard X-ray photons in the energy range 50 - 200 KeV. The acquisition of the ACS data produces a time series for each panel. These time series c…
A Hybrid Framework for Kilonova Anomaly Detection using Single-Epoch SEDs from the 7-Dimensional Telescope
Institute for Astronomy, University of Hawaii（夏威夷大学天文学研究所）；SNU Astronomy Research Center, Astronomy Program, Department of Physics & Astronomy, Seoul National University（首尔大学天文学研究中心天文学项目物理与天文学系）
University of Cambridge（剑桥大学）；Massachusetts Institute of Technology（麻省理工学院）；The Alan Turing Institute（艾伦·图灵研究所）；University of the Western Cape（西开普大学）；South African Radio Astronomy Observatory（南非射电天文台）；African Institute for Mathematical Sciences（非洲数学科学研究所）；Swinburne University of Technology（斯威本科技大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
New time-domain surveys, such as the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST), will observe millions of transient alerts each night, making standard approaches of visually identifying new and interesting transients infeasible. We present two novel methods of automatically detecting anomalous transient light curves in real-time. Both methods are based on the simple idea that if the light curves from a known population of transients can be accurately modelled, any deviations from model predictions are likely anomalies. The first modelling approach is a probabilistic neura…
Identification of anomalous light curves within time-domain surveys is often challenging. In addition, with the growing number of wide-field surveys and the volume of data produced exceeding astronomers ability for manual evaluation, outlier and anomaly detection is becoming vital for transient science. We present an unsupervised method for transient discovery using a clustering technique and the Astronomaly package. As proof of concept, we evaluate 85553 minute-cadenced light curves collected over two 1.5 hour periods as part of the Deeper, Wider, Faster program, using two different telescope…
In this work, we propose several enhancements to a geometric transformation based model for anomaly detection in images (GeoTranform). The model assumes that the anomaly class is unknown and that only inlier samples are available for training. We introduce new filter based transformations useful for detecting anomalies in astronomical images, that highlight artifact properties to make them more easily distinguishable from real objects. In addition, we propose a transformation selection strategy that allows us to find indistinguishable pairs of transformations. This results in an improvement of…
Anomaly detection in Fink. I. Discovery, follow-up, and classification of unusual sources
Université Clermont Auvergne（克莱蒙奥弗涅大学）；CNRS（法国国家科学研究中心）；LPCA（粒子与宇宙学实验室）；Lomonosov Moscow State University（莫斯科罗蒙诺索夫国立大学）；Sternberg Astronomical Institute（斯滕伯格天文研究所）；National Research University Higher School of Economics（高等经济大学）；Center for Astrophysics and Cosmology, University of Nova Gorica（新戈里察大学天体物理学与宇宙学中心）；Institute of Astronomy (Russian Academy of Sciences)（俄罗斯科学院天文研究所）；Université Paris-Saclay（巴黎萨克雷大学）；CNRS/IN2P3（法国国家科学研究中心/粒子物理研究所）；IJCLab（伊西莱穆利诺原子能委员会和粒子物理联合实验室）；Institute of Mechanics of Lomonosov Moscow State University（莫斯科罗蒙诺索夫国立大学力学研究所）
Columbia University（哥伦比亚大学）；Princeton University（普林斯顿大学）；Flatiron Institute（弗莱迪龙研究所）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Supernovae mark the explosive deaths of stars and enrich the cosmos with heavy elements. Future telescopes will discover thousands of new supernovae nightly, creating a need to flag astrophysically interesting events rapidly for followup study. Ideally, such an anomaly detection pipeline would be independent of our current knowledge and be sensitive to unexpected phenomena. Here we present an unsupervised method to search for anomalous time series in real time for transient, multivariate, and aperiodic signals. We use a RNN-based variational autoencoder to encode supernova time series and an i…
Self-supervised reconstruction of transients in data from space-borne gravitational-wave detectors
Center for Gravitational Wave Experiment, National Microgravity Laboratory, Institute of Mechanics, Chinese Academy of Sciences（中国科学院力学研究所微重力实验室引力波实验中心）；Taiji Laboratory for Gravitational Wave Universe (Beijing/Hangzhou), University of Chinese Academy of Sciences (UCAS)（中国科学院大学太极引力波宇宙实验室（北京/杭州））
The University of Manchester（曼彻斯特大学）；Radboud University（拉德堡德大学）；University of Cape Town（开普敦大学）；South African Astronomical Observatory（南非天文台）；Edge Hill University（边山大学）；Dataspex B.V.（Dataspex公司）；Leiden University（莱顿大学）；Northwestern University（西北大学）
Astronomers require efficient automated detection and classification pipelines when conducting large-scale surveys of the (optical) sky for variable and transient sources. Such pipelines are fundamentally important, as they permit rapid follow-up and analysis of those detections most likely to be of scientific value. We therefore present a deep learning pipeline based on the convolutional neural network architecture called $\texttt{MeerCRAB}$. It is designed to filter out the so called 'bogus' detections from true astrophysical sources in the transient detection pipeline of the MeerLICHT teles…
A Classifier-Based Approach to Multi-Class Anomaly Detection Applied to Astronomical Time-Series
Kavli Institute for Astrophysics and Space Research, Massachusetts Institute of Technology（麻省理工学院卡弗里天体物理与空间研究所）；Irvington High School（欧文顿高中）；Department of Physics and Astronomy, University of the Western Cape（西开普大学物理与天文学系）；South African Radio Astronomy Observatory（南非射电天文观测台）
An automated, rapid classification of transient events detected in the modern synoptic sky surveys is essential for their scientific utility and effective follow-up using scarce resources. This presents some unusual challenges: the data are sparse, heterogeneous and incomplete; evolving in time; and most of the relevant information comes not from the data stream itself, but from a variety of archival data and contextual information (spatial, temporal, and multi-wavelength). We are exploring a variety of novel techniques, mostly Bayesian, to respond to these challenges, using the ongoing CRTS s…
The periodic pulsations of stars teach us about their underlying physical process. We present a convolutional autoencoder-based pipeline as an automatic approach to search for out-of-distribution anomalous periodic variables within The Zwicky Transient Facility Catalog of Periodic Variable Stars (ZTF CPVS). We use an isolation forest to rank each periodic variable by its anomaly score. Our overall most anomalous events have a unique physical origin: they are mostly highly variable and irregular evolved stars. Multiwavelength data suggest that they are most likely Red Giant or Asymptotic Giant …
Massachusetts Institute of Technology（麻省理工学院）；University of Cambridge（剑桥大学）；University of the Western Cape（西开普大学）；South African Radio Astronomy Observatory（南非射电天文台）；Swinburne University of Technology（斯威本科技大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Astronomical transients are stellar objects that become temporarily brighter on various timescales and have led to some of the most significant discoveries in cosmology and astronomy. Some of these transients are the explosive deaths of stars known as supernovae while others are rare, exotic, or entirely new kinds of exciting stellar explosions. New astronomical sky surveys are observing unprecedented numbers of multi-wavelength transients, making standard approaches of visually identifying new and interesting transients infeasible. To meet this demand, we present two novel methods that aim to…
Multi-Class Deep SVDD: Anomaly Detection Approach in Astronomy with Distinct Inlier Categories
Universidad de Concepción（康塞普西翁大学）；Millennium Institute of Astrophysics (MAS)（千年天体物理研究所（MAS））；Universidad of Valparaíso（瓦尔帕莱索大学）；Universidad de Chile（智利大学）；European Southern Observatory（欧洲南方天文台）
As of this moment, fifty gravitational waves (GW) detections have been announced, thanks to the observational efforts of the LIGO-Virgo Collaboration, working with the Advanced LIGO and the Advanced Virgo interferometers. The detection of signals is complicated by the noise-dominated nature of the data. Conventional approaches in GW detection procedures require either precise knowledge of the GW waveform in the context of matched filtering searches or coincident analysis of data from multiple detectors. Furthermore, the analysis is prone to contamination by instrumental or environmental artifa…
Mega-pixel charge-integrating detectors are common in near-IR imaging applications. Optimal signal-to-noise ratio estimates of the photocurrents, which are particularly important in the low-signal regime, are produced by fitting linear models to sequential reads of the charge on the detector. Algorithms that solve this problem have a long history, but can be computationally intensive. Furthermore, the cosmic ray background is appreciable for these detectors in Earth orbit, particularly above the Earth's magnetic poles and the South Atlantic Anomaly, and on-board reduction routines must be capa…
The classic classification scheme for Active Galactic Nuclei (AGNs) was recently challenged by the discovery of the so-called changing-state (changing-look) AGNs (CSAGNs). The physical mechanism behind this phenomenon is still a matter of open debate and the samples are too small and of serendipitous nature to provide robust answers. In order to tackle this problem, we need to design methods that are able to detect AGN right in the act of changing-state. Here we present an anomaly detection (AD) technique designed to identify AGN light curves with anomalous behaviors in massive datasets. The m…
Representation Learning for Time-Domain High-Energy Astrophysics: Discovery of Extragalactic Fast X-ray Transient XRT 200515
Institute for Computational and Mathematical Engineering, Stanford University（斯坦福大学计算与数学工程研究所）；University of Cambridge（剑桥大学）；Center for Astrophysics | Harvard & Smithsonian（哈佛-史密森天体物理中心）；INAF – Osservatorio Astrofisico di Torino（意大利国家天体物理研究所都灵天文台）；The University of Sydney（悉尼大学）
MADGRAV: a multilevel anomaly-detection pipeline for gravitational-wave searches applied to LIGO data
Marietta Blau Institute for Particle Physics, Austrian Academy of Sciences（奥地利科学院玛丽埃塔·布劳粒子物理研究所）；Università degli Studi di Urbino ‘Carlo Bo’（乌尔比诺“卡洛·博”大学）；INFN（意大利国家核物理研究所）
To maximize the discovery potential of future synoptic surveys, especially in the field of transient science, it will be necessary to use automatic classification to identify some of the astronomical sources. The data mining technique of supervised classification is suitable for this problem. Here, we present a supervised learning method to automatically classify variable X-ray sources in the second \textit{XMM-Newton} serendipitous source catalog (2XMMi-DR2). Random Forest is our classifier of choice since it is one of the most accurate learning algorithms available. Our training set consists…
Identifying Light-curve Signals with a Deep Learning Based Object Detection Algorithm. II. A General Light Curve Classification Framework
Tsung-Dao Lee Institute, Shanghai Jiao Tong University（上海交通大学李政道研究所）；University of Warwick（华威大学）；School of Physics and Astronomy, Shanghai Jiao Tong University（上海交通大学物理与天文学院）
Astronomical surveys of celestial sources produce streams of noisy time series measuring flux versus time ("light curves"). Unlike in many other physical domains, however, large (and source-specific) temporal gaps in data arise naturally due to intranight cadence choices as well as diurnal and seasonal constraints. With nightly observations of millions of variable stars and transients from upcoming surveys, efficient and accurate discovery and classification techniques on noisy, irregularly sampled data must be employed with minimal human-in-the-loop involvement. Machine learning for inference…
