The GPU phase folding and deep learning method for detecting exoplanet transits

ABSTRACT This paper presents GPFC, a novel Graphics Processing Unit (GPU) Phase Folding and Convolutional Neural Network (CNN) system to detect exoplanets using the transit method. We devise a fast-folding algorithm parallelized on a GPU to amplify low signal-to-noise ratio transit signals, allowing...

Full description

Saved in:
Bibliographic Details
Published inMonthly notices of the Royal Astronomical Society Vol. 528; no. 3; pp. 4053 - 4067
Main Authors Wang, Kaitlyn, Ge, Jian, Willis, Kevin, Wang, Kevin, Zhao, Yinan
Format Journal Article
LanguageEnglish
Published London Oxford University Press 01.03.2024
Subjects
Algorithms
Artificial neural networks
Extrasolar planets
Folding
Graphics processing units
Light curve
Machine learning
Orbits
Planet detection
Signal to noise ratio
Transit
surveys
methods: data analysis
catalogues
planets and satellites: detection
techniques: photometric
Online AccessGet full text

Cover

More Information
Summary:ABSTRACT This paper presents GPFC, a novel Graphics Processing Unit (GPU) Phase Folding and Convolutional Neural Network (CNN) system to detect exoplanets using the transit method. We devise a fast-folding algorithm parallelized on a GPU to amplify low signal-to-noise ratio transit signals, allowing a search at high precision and speed. A CNN trained on two million synthetic light curves reports a score indicating the likelihood of a planetary signal at each period. While the GPFC method has broad applicability across period ranges, this research specifically focuses on detecting ultrashort-period planets with orbital periods less than one day. GPFC improves on speed by three orders of magnitude over the predominant Box-fitting Least Squares (BLS) method. Our simulation results show GPFC achieves 97 per cent training accuracy, higher true positive rate at the same false positive rate of detection, and higher precision at the same recall rate when compared to BLS. GPFC recovers 100 per cent of known ultrashort-period planets in Kepler light curves from a blind search. These results highlight the promise of GPFC as an alternative approach to the traditional BLS algorithm for finding new transiting exoplanets in data taken with Kepler and other space transit missions such as K2, TESS, and future PLATO and Earth 2.0.
ISSN:0035-8711
1365-2966
DOI:10.1093/mnras/stae245