Convolutional Neural Networks for Searching Superflares from Pixel-level Data of the Transiting Exoplanet Survey Satellite
arXiv:2204.04019 · doi:10.3847/1538-4357/ac7f2c
Abstract
In this work, six convolutional neural networks (CNNs) have been trained based on %different feature images and arrays from the database including 15,638 superflare candidates on solar-type stars, which are collected from the three-years observations of Transiting Exoplanet Survey Satellite ({\em TESS}). These networks are used to replace the artificially visual inspection, which was a direct way to search for superflares, and exclude false positive events in recent years. Unlike other methods, which only used stellar light curves to search superflare signals, we try to identify superflares through {\em TESS} pixel-level data with lower risks of mixing false positive events, and give more reliable identification results for statistical analysis. The evaluated accuracy of each network is around 95.57\%. After applying ensemble learning to these networks, stacking method promotes accuracy to 97.62\% with 100\% classification rate, and voting method promotes accuracy to 99.42\% with relatively lower classification rate at 92.19\%. We find that superflare candidates with short duration and low peak amplitude have lower identification precision, as their superflare-features are hard to be identified. The database including 71,732 solar-type stars and 15,638 superflare candidates from {\em TESS} with corresponding feature images and arrays, and trained CNNs in this work are public available.
Published in ApJ, 27 pages, 11 figures, 3 tables
References in corpus (26)
- The NumPy array: a structure for efficient numerical computation
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- The Transiting Exoplanet Survey Satellite
- astroquery: An Astronomical Web-Querying Package in Python
- The Kepler Catalog of Stellar Flares
- Chromospheric Activity, Rotation, and Rotational Braking in M and L Dwarfs
- Statistical properties of superflares on solar-type stars based on 1-min cadence data
- Do Kepler superflare stars really include slowly-rotating Sun-like stars ? - Results using APO 3.5m telescope spectroscopic observations and Gaia-DR2 data -
- Probable detection of an eruptive filament from a superflare on a solar-type star
- The flare catalog and the flare activity in the Kepler mission
- Statistical Properties of Superflares on Solar-type Stars: Results Using All of the Kepler Primary Mission Data
- Risks for life on habitable planets from superflares of their host stars
- Superflares on solar-type stars from the first year observation of TESS
- Superflares, chromospheric activities and photometric variabilities of solar-type stars from the second-year observation of TESS and spectra of LAMOST
- Uncloaking hidden repeating fast radio bursts with unsupervised machine learning
- Deep Learning for Strong Lensing Search: Tests of the Convolutional Neural Networks and New Candidates from KiDS DR3
- A rapid cosmic-ray increase in BC 3372-3371 from ancient buried tree rings in China
- Detection of Flare-associated CME Candidates on Two M-dwarfs by GWAC and Fast, Time-resolved Spectroscopic Follow-ups
- Testing Self-Organized Criticality Across the Main Sequence using Stellar Flares from TESS
- Finding flares in Kepler and TESS data with recurrent deep neural networks
- Automated identification of transiting exoplanet candidates in NASA Transiting Exoplanets Survey Satellite (TESS) data with machine learning methods
- Classification of 4XMM-DR9 Sources by Machine Learning
- Stellar flares from blended and neighbouring stars in Kepler short cadence observations
- Identify Light-Curve Signals with Deep Learning Based Object Detection Algorithm. I. Transit Detection
- 81 New Candidate Fast Radio Bursts in Parkes Archive
- Nigraha: Machine-learning based pipeline to identify and evaluate planet candidates from TESS