Results of the Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC)
R. Hložek, K. A. Ponder, A. I. Malz, M. Dai, G. Narayan, E. E. O. Ishida, T. Allam, A. Bahmanyar, R. Biswas, L. Galbany, S. W. Jha, D. O. Jones, R. Kessler, M. … 展开作者
R. Hložek, K. A. Ponder, A. I. Malz, M. Dai, G. Narayan, E. E. O. Ishida, T. Allam, A. Bahmanyar, R. Biswas, L. Galbany, S. W. Jha, D. O. Jones, R. Kessler, M. Lochner, A. A. Mahabal, K. S. Mandel, J. R. Martínez-Galarza, J. D. McEwen, D. Muthukrishna, H. V. Peiris, C. M. Peters, C. N. Setzer
Next-generation surveys like the Legacy Survey of Space and Time (LSST) on the Vera C. Rubin Observatory will generate orders of magnitude more discoveries of transients and variable stars than previous surveys. To prepare for this data deluge, we developed the Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC), a competition which aimed to catalyze the development of robust classifiers under LSST-like conditions of a non-representative training set for a large photometric test set of imbalanced classes. Over 1,000 teams participated in PLAsTiCC, which was hosted in the Kaggle data science competition platform between Sep 28, 2018 and Dec 17, 2018, ultimately identifying three winners in February 2019. Participants produced classifiers employing a diverse set of machine learning techniques including hybrid combinations and ensemble averages of a range of approaches, among them boosted decision trees, neural networks, and multi-layer perceptrons. The strong performance of the top three classifiers on Type Ia supernovae and kilonovae represent a major improvement over the current state-of-the-art within astronomy. This paper summarizes the most promising methods and evaluates their results in detail, highlighting future directions both for classifier development and simulation needs for a next generation PLAsTiCC data set.
The Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC) is an open data challenge to classify simulated astronomical time-series data in preparation for observations from the Large Synoptic Survey Telescope (LSST), which will achieve first light in 2019 and commence its 10-year main survey in 2022. LSST will revolutionize our understanding of the changing sky, discovering and measuring millions of time-varying objects. In this challenge, we pose the question: how well can we classify objects in the sky that vary in brightness from simulated LSST time-series data, with…
Classification of transient and variable light curves is an essential step in using astronomical observations to develop an understanding of their underlying physical processes. However, upcoming deep photometric surveys, including the Large Synoptic Survey Telescope (LSST), will produce a deluge of low signal-to-noise data for which traditional labeling procedures are inappropriate. Probabilistic classification is more appropriate for the data but are incompatible with the traditional metrics used on deterministic classifications. Furthermore, large survey collaborations intend to use these c…
With an ever-increasing amount of astronomical data being collected, manual classification has become obsolete; and machine learning is the only way forward. Keeping this in mind, the Large Synoptic Survey Telescope (LSST) Team hosted the Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC) in 2018. The aim of this challenge was to develop models that accurately classify astronomical sources into different classes, scaling from a limited training set to a large test set. In this text, we report our results of experimenting with Bidirectional Gated Recurrent Unit (GRU) …
The Vera C. Rubin Observatory will increase the number of observed supernovae (SNe) by an order of magnitude; however, it is impossible to spectroscopically confirm the class for all the SNe discovered. Thus, photometric classification is crucial but its accuracy depends on the not-yet-finalized observing strategy of Rubin Observatory's Legacy Survey of Space and Time (LSST). We quantitatively analyze the impact of the LSST observing strategy on SNe classification using simulated multi-band light curves from the Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC). Fir…
Data challenges are emerging as powerful tools with which to answer fundamental astronomical questions. Time-domain astronomy lends itself to data challenges, particularly in the era of classification and anomaly detection. With improved sensitivity of wide-field surveys in optical and radio wavelengths from surveys like the Large Synoptic Survey Telescope (LSST) and the Canadian Hydrogen Intensity Mapping Experiment (CHIME), we are entering the large-volume era of transient astronomy. I highlight some recent time-domain challenges, with particular focus on the Photometric LSST Astronomical Ti…
The deluge of data from time-domain surveys is rendering traditional human-guided data collection and inference techniques impractical. We propose a novel approach for conducting data collection for science inference in the era of massive large-scale surveys that uses value-based metrics to autonomously strategize and co-ordinate follow-up in real-time. We demonstrate the underlying principles in the Recommender Engine For Intelligent Transient Tracking (REFITT) that ingests live alerts from surveys and value-added inputs from data brokers to predict the future behavior of transients and desig…
The Legacy Survey of Space and Time, operated by the Vera C. Rubin Observatory, is a 10-year astronomical survey due to start operations in 2022 that will image half the sky every three nights. LSST will produce ~20TB of raw data per night which will be calibrated and analyzed in almost real time. Given the volume of LSST data, the traditional subset-download-process paradigm of data reprocessing faces significant challenges. We describe here, the first steps towards a gateway for astronomical science that would enable astronomers to analyze images and catalogs at scale. In this first step we …
The Large Synoptic Survey Telescope will complete its survey in 2022 and produce terabytes of imaging data each night. To work with this massive onset of data, automated algorithms to classify astronomical light curves are crucial. Here, we present a method for automated classification of photometric light curves for a range of astronomical objects. Our approach is based on the gradient boosting of decision trees, feature extraction and selection, and augmentation. The solution was developed in the context of The Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC) and…
We perform a rigorous cosmology analysis on simulated type Ia supernovae (SN~Ia) and evaluate the improvement from including photometric host-galaxy redshifts compared to using only the "zspec" subset with spectroscopic redshifts from the host or SN. We use the Deep Drilling Fields (~50 deg^2) from the Photometric LSST Astronomical Time-Series Classification Challenge (PLaSTiCC), in combination with a low-z sample based on Data Challenge2 (DC2). The analysis includes light curve fitting to standardize the SN brightness, a high-statistics simulation to obtain a bias-corrected Hubble diagram, a …
Modern astronomical surveys such as the Large Synoptic Sky Survey (LSST) promise an unprecedented wealth of discoveries, delivered in the form of ~10 million alerts of time-variable events per night. Astronomers are faced with the daunting challenge of identifying the most scientifically important events from this flood of data in order to conduct effective and timely follow-up observations. Several ongoing observing programs have proven databases to be extremely valuable in conducting efficient follow-up, particularly when combined with tools to select targets, submit observation requests dir…
Millennium Institute of Astrophysics（千禧天体物理研究所）；Universidad de Chile（智利大学）；Harvard University（哈佛大学）；University of Florida（佛罗里达大学）；Universidad de los Andes（智利洛斯安第斯大学）
Time-domain astronomy (TDA) is facing a paradigm shift caused by the exponential growth of the sample size, data complexity and data generation rates of new astronomical sky surveys. For example, the Large Synoptic Survey Telescope (LSST), which will begin operations in northern Chile in 2022, will generate a nearly 150 Petabyte imaging dataset of the southern hemisphere sky. The LSST will stream data at rates of 2 Terabytes per hour, effectively capturing an unprecedented movie of the sky. The LSST is expected not only to improve our understanding of time-varying astrophysical objects, but al…
The remarkable scientific return and legacy of LSST, in the era that it will define, will not only be realized in the breakthrough science that will be achieved with catalog data. This Big Data survey will shape the way the entire astronomical community advances -- or fails to embrace -- new ways of approaching astronomical research and data. In this white paper, we address the NRC template questions 4,5,6,8 and 9, with a focus on the unique challenges for smaller, and often under-resourced, institutions, including institutions dedicated to underserved minority populations, in the efficient an…
Alertissimo -- a tool for orchestration of LSST broker streams
Astronomical Observatory（天文台）；University of Belgrade, Institute of Physics Belgrade（贝尔格莱德大学物理研究所）；University of Belgrade, Faculty of Organizational Sciences（贝尔格莱德大学组织科学学院）
With the advent of the Large Synoptic Survey Telescope (LSST), time-domain astronomy will be faced with an unprecedented volume and rate of data. Real-time processing of variables and transients detected by such large-scale surveys is critical to identifying the more unusual events and allocating scarce follow-up resources efficiently. We develop an algorithm to identify these novel events within a given population of variable sources. We determine the distributions of magnitude changes (dm) over time intervals (dt) for a given passband f, pf(dm|dt), and use these distributions to compute the …
The unprecedented volume and rate of transient events that will be discovered by the Large Synoptic Survey Telescope (LSST) demands that the astronomical community update its followup paradigm. Alert-brokers -- automated software system to sift through, characterize, annotate and prioritize events for followup -- will be critical tools for managing alert streams in the LSST era. The Arizona-NOAO Temporal Analysis and Response to Events System (ANTARES) is one such broker. In this work, we develop a machine learning pipeline to characterize and classify variable and transient sources only using…
Upcoming astronomical surveys such as the Large Synoptic Survey Telescope (LSST) will rely on photometric classification to identify the majority of the transients and variables that they discover. We present a set of techniques for photometric classification that can be applied even when the training set of spectroscopically-confirmed objects is heavily biased towards bright, low-redshift objects. Using Gaussian process regression to model arbitrary light curves in all bands simultaneously, we "augment" the training set by generating new versions of the original light curves covering a range …
Time-domain astronomy is entering a new era as wide-field surveys with higher cadences allow for more discoveries than ever before. The field has seen an increased use of machine learning and deep learning for automated classification of transients into established taxonomies. Training such classifiers requires a large enough and representative training set, which is not guaranteed for new future surveys such as the Vera Rubin Observatory, especially at the beginning of operations. We present the use of Gaussian processes to create a uniform representation of supernova light curves from multip…
This paper introduces the multiband periodogram, a general extension of the well-known Lomb-Scargle approach for detecting periodic signals in time-domain data. In addition to advantages of the Lomb-Scargle method such as treatment of non-uniform sampling and heteroscedastic errors, the multiband periodogram significantly improves period finding for randomly sampled multiband light curves (e.g., Pan-STARRS, DES and LSST). The light curves in each band are modeled as arbitrary truncated Fourier series, with the period and phase shared across all bands. The key aspect is the use of Tikhonov regu…
Simulation-Based Pretraining and Domain Adaptation for Astronomical Time Series with Minimal Labeled Data
Massachusetts Institute of Technology, Cambridge, MA 02139, USA；Irvington High School, Fremont, CA 94538, USA；Center for Astrophysics, Harvard \& Smithsonian, Cambridge, MA 02138, USA
The Large Synoptic Survey Telescope (LSST) is an ambitious astronomical survey with a similarly ambitious Data Management component. Data Management for LSST includes processing on both nightly and yearly cadences to generate transient alerts, deep catalogs of the static sky, and forced photometry light-curves for billions of objects at hundreds of epochs, spanning at least a decade. The algorithms running in these pipelines are individually sophisticated and interact in subtle ways. This paper provides an overview of those pipelines, focusing more on those interactions than the details of any…
The Large Synoptic Survey Telescope (LSST), the next-generation optical imaging survey sited at Cerro Pachon in Chile, will provide an unprecedented database of astronomical measurements. The LSST design, with an 8.4m (6.7m effective) primary mirror, a 9.6 sq. deg. field of view, and a 3.2 Gigapixel camera, will allow about 10,000 sq. deg. of sky to be covered twice per night, every three to four nights on average, with typical 5-sigma depth for point sources of $r$=24.5 (AB). With over 800 observations in $ugrizy$ bands over a 10-year period, these data will enable a deep stack reaching $r$=2…
The presence of fringing in astronomical CCD images will impact photometric quality and measurements. Yet its impact on the Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) has not been fully studied. We present a detailed study on fringing for Charge-Coupled Devices (CCDs) already implemented on the Rubin Observatory LSST Camera's focal plane. After making physical measurements and knowing the compositions, we have developed a model for the e2v CCDs. We present a method to fit for the internal height variation of the epoxy layer within the sensors based on fringing measureme…
We build on previous efforts to model CCD sensors, during illumination and collection of conversions. We use a finite summation of simple, electrostatic field models. The upgraded functionality of our framework provides specific predictions for perturbations in pixel boundary enclosures (e.g., at the backside window) and the bookkeeping capability to stack those perturbations so that they may be utilized as Greens functions -- portable calculation results that may be generically applied to a range of precision astronomy related problems that naturally including astrometric, photometric and sha…
The time domain has been identified as one of the most important areas of astronomical research for the next decade. The Virtual Observatory is in the vanguard with dedicated tools and services that enable and facilitate the discovery, dissemination and analysis of time domain data. These range in scope from rapid notifications of time-critical astronomical transients to annotating long-term variables with the latest modeling results. In this paper, we will review the prior art in these areas and focus on the capabilities that the VAO is bringing to bear in support of time domain science. In p…
Transfer Learning for Transient Classification: From Simulations to Real Data and ZTF to LSST
Kavli Institute for Astrophysics and Space Research, Massachusetts Institute of Technology（凯斯勒天体物理与空间研究研究所，麻省理工学院）；Irvington High School（伊里弗顿高中）；Department of Physics and Astronomy, Northwestern University（物理与天文学系，西北大学）；Center for Interdisciplinary Exploration and Research in Astrophysics (CIERA)（天体物理学跨学科探索与研究中心（CIERA））；NSF-Simons AI Institute for the Sky (SkAI)（NSF-模拟ons人工智能研究所（SkAI））
The previous decade saw the discovery of the first four known interstellar objects due to advances in astronomical viewing equipment. Future sky surveys with greater sensitivity will allow for more frequent detections of such objects, including increasingly small objects. We consider the capabilities of the Legacy Survey of Space and Time (LSST) of the Vera C. Rubin Observatory to detect interstellar objects of small sizes during its period of operation over the next decade. We use LSST's detection capabilities and simulate populations of interstellar objects in the range of 1-50m in diameter …
We present the Active Galactic Nuclei (AGN) classifier as currently implemented within the Fink broker. Features were built upon summary statistics of available photometric points, as well as color estimation enabled by symbolic regression. The learning stage includes an active learning loop, used to build an optimized training sample from labels reported in astronomical catalogs. Using this method to classify real alerts from the Zwicky Transient Facility (ZTF), we achieved 98.0% accuracy, 93.8% precision and 88.5% recall. We also describe the modifications necessary to enable processing data…
In the next decade, the LSST will become a major facility for the astronomical community. However accurately determining the redshifts of the observed galaxies without using spectroscopy is a major challenge. Reconstruction of the redshifts with high resolution and well-understood uncertainties is mandatory for many science goals, including the study of baryonic acoustic oscillations. We investigate different approaches to establish the accuracy that can be reached by the LSST six-band photometry. We construct a realistic mock galaxy catalog, based on the GOODS survey luminosity function, by s…
Simulation-Based Inference for Probabilistic Galaxy Detection and Deblending
University of Maryland, College Park（马里兰大学帕克分校）；University of Michigan（密歇根大学）；Leinweber Institute for Theoretical Physics, University of Michigan（密歇根大学莱因韦伯理论物理研究所）；The Voleon Group（Voleon集团）；Carnegie Mellon University（卡内基梅隆大学）
Department of Computer Science University of California Irvine（加利福尼亚大学尔湾分校计算机科学系）；Université Clermont Auvergne CNRS/IN2P3, LPC Clermont Ferrand（克莱蒙费朗大学（Université Clermont Auvergne）、法国国家科学研究中心/法国国家核物理与粒子物理研究所（CNRS/IN2P3）、克莱蒙费朗物理实验室（LPC Clermont Ferrand））；CENTRA-Centro de Astrofísica e Gravitação Universidade de Lisboa（里斯本大学（Universidade de Lisboa）中心天体物理与引力中心（CENTRA-Centro de Astrofísica e Gravitação））；Shanghai Astronomical Observatory Chinese Academy of Sciences（中国科学院上海天文台）；Berkeley Center for Cosmological Physics University of California Berkeley（加利福尼亚大学伯克利分校宇宙物理伯克利中心）；Department of Computer Science University of Houston（休斯顿大学计算机科学系）；Department of Physics and Astronomy The Johns Hopkins University（约翰斯·霍普金斯大学物理与天文系）；Department of Informatics University of California Irvine（加利福尼亚大学尔湾分校信息学系）；NSF’s NOIRLab（美国国家科学基金会国家光学红外天文学研究实验室（NOIRLab））；Gemini Observatory（双子座天文台）
The recent increase in volume and complexity of available astronomical data has led to a wide use of supervised machine learning techniques. Active learning strategies have been proposed as an alternative to optimize the distribution of scarce labeling resources. However, due to the specific conditions in which labels can be acquired, fundamental assumptions, such as sample representativeness and labeling cost stability cannot be fulfilled. The Recommendation System for Spectroscopic follow-up (RESSPECT) project aims to enable the construction of optimized training samples for the Rubin Observ…
University College London（伦敦大学学院）；Université Paris-Saclay（巴黎萨克雷大学）；The Alan Turing Institute（艾伦·图灵研究所）
A new golden age in astronomy is upon us, dominated by data. Large astronomical surveys are broadcasting unprecedented rates of information, demanding machine learning as a critical component in modern scientific pipelines to handle the deluge of data. The upcoming Legacy Survey of Space and Time (LSST) of the Vera C. Rubin Observatory will raise the big-data bar for time-domain astronomy, with an expected 10 million alerts per-night, and generating many petabytes of data over the lifetime of the survey. Fast and efficient classification algorithms that can operate in real-time, yet robustly a…
The next decade will feature a growing number of massive ground-based photometric, spectroscopic, and time-domain surveys, including those produced by DECam, DESI, and LSST. The NOAO Data Lab was launched in 2017 to enable efficient exploration and analysis of large surveys, with particular focus on the petabyte-scale holdings of the NOAO Archive and their associated catalogs. The Data Lab mission and future development align well with two of the NSF's Big Ideas, namely Harnessing Data for 21st Century Science and Engineering and as part of a network to contribute to Windows on the Universe: T…
We present a new framework to detect various types of variable objects within massive astronomical time-series data. Assuming that the dominant population of objects is non-variable, we find outliers from this population by using a non-parametric Bayesian clustering algorithm based on an infinite GaussianMixtureModel (GMM) and the Dirichlet Process. The algorithm extracts information from a given dataset, which is described by six variability indices. The GMM uses those variability indices to recover clusters that are described by six-dimensional multivariate Gaussian distributions, allowing o…
One of the scientific goals of the Large Synoptic Survey Telescope (LSST) is to measure the evolution of dark energy by measuring subtle distortions of galaxy shapes due to weak gravitational lensing caused by the evolving dark matter distribution. Understanding the point spread function (PSF) for LSST is a crucial step to accurate measurements of weak gravitational lensing. Atmospheric contributions dominate the LSST PSF. Simulations of Kolmogorov turbulence models are commonly used to characterize and correct for these atmospheric effects. In order to validate these simulations, we compare t…
Mechanical Studies of an Additional Light Baffle for the LSST Camera
SLAC National Accelerator Laboratory（SLAC国家加速器实验室）；INAF - Osservatorio di Astrofisica e Scienza dello Spazio（意大利天体物理学与空间科学国家研究所）；Vera C. Rubin Observatory（薇拉·C·鲁宾天文台）；Fermi National Accelerator Laboratory（费米国家加速器实验室）；Department of Physics and Astronomy (DIFA), University of Bologna（博洛尼亚大学物理与天文学系）；Department of Physics, University of Chicago（芝加哥大学物理系）；Kavli Institute for Particle Astrophysics and Cosmology, SLAC National Accelerator Laboratory（SLAC国家加速器实验室卡弗里粒子天体物理与宇宙学研究所）；Institut National de Physique Nucléaire et de Physique des Particules (IN2P3) du CNRS（法国国家核物理与粒子物理研究所）；Université Paris Cité, CNRS, Astroparticule et Cosmologie（巴黎西岱大学）
Point spread function modelling for astronomical telescopes: a review focused on weak gravitational lensing studies
CEA（法国原子能和替代能源委员会）；CNRS（法国国家科学研究中心）；AIM（天体物理与宇宙学研究所）；University College London (UCL)（伦敦大学学院）；Mullard Space Science Laboratory（穆拉德空间科学实验室）；Institute of Astrophysics（天体物理研究所）
In this decade astronomy is undergoing a paradigm shift to handle data from next generation observatories such as the Square Kilometre Array (SKA) or the Vera C. Rubin Observatory (LSST). Producing real time data streams of up to 10 TB/s and data products of the order of 600 Pbytes/year, the SKA will be the biggest civil data producing machine of the world that demands novel solutions on how these data volumes can be stored and analysed. Through the use of complex, automated pipelines the provenance of this real time data processing is key to establish confidence within the system, its final d…
Commodity cloud computing, as provided by commercial vendors such as Amazon, Google, and Microsoft, has revolutionized computing in many sectors. With the advent of a new class of big data, public access astronomical facility such as LSST, DKIST, and WFIRST, there exists a real opportunity to combine these missions with cloud computing platforms and fundamentally change the way astronomical data is collected, processed, archived, and curated. Making these changes in a cross-mission, coordinated way can provide unprecedented economies of scale in personnel, data collection and management, archi…
A new generation of observational science instruments is dramatically increasing collected data volumes in a range of fields. These instruments include the Square Kilometre Array (SKA), Large Synoptic Survey Telescope (LSST), terrestrial sensor networks, and NASA satellites participating in "decadal survey" missions. Their unprecedented coverage and sensitivity will likely reveal wholly new categories of unexpected and transient events. Commensal methods passively analyze these data streams, recognizing anomalous events of scientific interest and reacting in real time. We report on a case exam…
We introduce AXS (Astronomy eXtensions for Spark), a scalable open-source astronomical data analysis framework built on Apache Spark, a widely used industry-standard engine for big data processing. Building on capabilities present in Spark, AXS aims to enable querying and analyzing almost arbitrarily large astronomical catalogs using familiar Python/AstroPy concepts, DataFrame APIs, and SQL statements. We achieve this by i) adding support to Spark for efficient on-line positional cross-matching and ii) supplying a Python library supporting commonly-used operations for astronomical data analysi…
