Systematic Serendipity: A Test of Unsupervised Machine Learning as a Method for Anomaly Detection

Abstract

Advances in astronomy are often driven by serendipitous discoveries. As survey astronomy continues to grow, the size and complexity of astronomical databases will increase, and the ability of astronomers to manually scour data and make such discoveries decreases. In this work, we introduce a machine learning-based method to identify anomalies in large datasets to facilitate such discoveries, and apply this method to long cadence lightcurves from NASA's Kepler Mission. Our method clusters data based on density, identifying anomalies as data that lie outside of dense regions. This work serves as a proof-of-concept case study and we test our method on four quarters of the Kepler long cadence lightcurves. We use Kepler's most notorious anomaly, Boyajian's Star (KIC 8462852), as a rare `ground truth' for testing outlier identification to verify that objects of genuine scientific interest are included among the identified anomalies. We evaluate the method's ability to identify known anomalies by identifying unusual behavior in Boyajian's Star, we report the full list of identified anomalies for these quarters, and present a sample subset of identified outliers that includes unusual phenomena, objects that are rare in the Kepler field, and data artifacts. By identifying <4% of each quarter as outlying data, we demonstrate that this anomaly detection method can create a more targeted approach in searching for rare and novel phenomena.

21 pages, 10 figures, Submitted to MNRAS

References in corpus (30)

• Scikit-learn: Machine Learning in Python
• Astropy: A Community Python Package for Astronomy
• Gaia Data Release 2. Summary of the contents and survey properties
• Gaia Data Release 1. Summary of the astrometric, photometric, and survey properties
• LSST Science Book, Version 2.0
• Rotation Periods of 34,030 Kepler Main-Sequence Stars: The Full Autocorrelation Sample
• The Pan-STARRS1 Surveys
• Kepler Eclipsing Binary Stars. I. Catalog and Principal Characterization of 1879 Eclipsing Binaries in the First Data Release
• Revised Stellar Properties of Kepler Targets for the Quarter 1-16 Transit Detection Run
• False positive probabilties for all Kepler Objects of Interest: 1284 newly validated planets and 428 likely false positives
• Kepler Eclipsing Binary Stars. VII. The Catalog of Eclipsing Binaries Found in the Entire Kepler Data-Set
• Kepler Eclipsing Binary Stars. II. 2165 Eclipsing Binaries in the Second Data Release
• On Machine-Learned Classification of Variable Stars with Sparse and Noisy Time-Series Data
• Selection, Prioritization, and Characteristics of Kepler Target Stars
• Planet Hunters X. KIC 8462852 - Where's the Flux?
• Kepler Mission Stellar and Instrument Noise Properties
• A Class of Eccentric Binaries with Dynamic Tidal Distortions Discovered with Kepler
• Rotation Periods, Variability Properties and Ages for Kepler Exoplanet Candidate Host Stars
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• Contamination in the Kepler Field. Identification of 685 KOIs as False Positives Via Ephemeris Matching Based On Q1-Q12 Data
• Global stellar variability study in the field-of-view of the Kepler satellite
• The Ĝ Infrared Search for Extraterrestrial Civilizations with Large Energy Supplies. II. Framework, Strategy, and First Result
• The Kepler light curves of V1504 Cygni and V344 Lyrae: A study of the Outburst Properties
• Detection of Potential Transit Signals in the First Three Quarters of Kepler Mission Data
• Kepler Mission Stellar and Instrument Noise Properties Revisited
• Exploring a Stream of Highly-Eccentric Binaries with Kepler
• The Classificiation of Kepler B star Variables
• The First Post-Kepler Brightness Dips of KIC 8462852
• KIC 8462852 Faded Throughout the Kepler Mission
• Extinction and the Dimming of KIC 8462852

Cited by in corpus (28)

• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• Astronomaly: Personalised Active Anomaly Detection in Astronomical Data
• Anomaly detection in the Zwicky Transient Facility DR3
• Active Anomaly Detection for time-domain discoveries
• A review of unsupervised learning in astronomy
• Anomaly detection in Hyper Suprime-Cam galaxy images with generative adversarial networks
• Unsupervised machine learning for transient discovery in Deeper, Wider, Faster light curves
• Anomaly Detection in Gravitational Waves data using Convolutional AutoEncoders
• SILVERRUSH X: Machine Learning-Aided Selection of $9318$ LAEs at $z=2.2$, $3.3$, $4.9$, $5.7$, $6.6$, and $7.0$ from the HSC SSP and CHORUS Survey Data
• Real-Time Detection of Anomalies in Large-Scale Transient Surveys
• A method for finding anomalous astronomical light curves and their analogs
• A semi-supervised Machine Learning search for never-seen Gravitational-Wave sources
• Astronomaly at scale: searching for anomalies amongst 4 million galaxies
• Density Based Outlier Scoring on Kepler Data
• Identifying outliers in astronomical images with unsupervised machine learning
• On Detecting Interstellar Scintillation in Narrowband Radio SETI
• A Classifier-Based Approach to Multi-Class Anomaly Detection for Astronomical Transients
• Hundreds of new periodic signals detected in the first year of $TESS$ with the $\mathtt{weirddetector}$
• Black Swans in Astronomical Data
• AT 2020iko: a WZ Sge-type DN candidate with an anomalous precursor event
• Finding radio transients with anomaly detection and active learning based on volunteer classifications
• Automated Discovery of Anomalous Features in Ultra-Large Planetary Remote Sensing Datasets using Variational Autoencoders
• A statistical study of lopsided galaxies using random forest
• Comparison of outlier detection methods on astronomical image data
• One of Everything: The Breakthrough Listen Exotica Catalog
• Launching the VASCO citizen science project
• Searching for technosignatures in exoplanetary systems with current and future missions
• Automatically detecting anomalous exoplanet transits