TY - JOUR
T1 - Detection of exomoons in simulated light curves with a regularized convolutional neural network
AU - Alshehhi, Rasha
AU - Rodenbeck, Kai
AU - Gizon, Laurent
AU - Sreenivasan, Katepalli R.
N1 - Funding Information:
Acknowledgements. We thank Chris Hanson for constructive comments. This work was supported in part by NYUAD Institute grant G1502 “Center for Space Science”. RA acknowledges support from the NYUAD Kawader Research Program. Computational resources were provided by the NYUAD Institute through Muataz Al Barwani and the HPC Center. The simulated light curves were produced at the DLR-supported PLATO Data Center at the MPI for Solar System Research. Author Contributions: LG proposed the research idea. RA proposed the Machine Learning algorithm and analyzed the data and the results. KR prepared the simulated data and performed the BIC analysis. KR is a member of the International Max Planck Research School for Solar System Science at the University of Göttingen. All authors contributed to the final manuscript.
Publisher Copyright:
© ESO 2020.
PY - 2020/8/1
Y1 - 2020/8/1
N2 - Context. Many moons have been detected around planets in our Solar System, but none has been detected unambiguously around any of the confirmed extrasolar planets. Aims. We test the feasibility of a supervised convolutional neural network to classify photometric transit light curves of planet-host stars and identify exomoon transits, while avoiding false positives caused by stellar variability or instrumental noise. Methods. Convolutional neural networks are known to have contributed to improving the accuracy of classification tasks. The network optimization is typically performed without studying the effect of noise on the training process. Here we design and optimize a 1D convolutional neural network to classify photometric transit light curves. We regularize the network by the total variation loss in order to remove unwanted variations in the data features. Results. Using numerical experiments, we demonstrate the benefits of our network, which produces results comparable to or better than the standard network solutions. Most importantly, our network clearly outperforms a classical method used in exoplanet science to identify moon-like signals. Thus the proposed network is a promising approach for analyzing real transit light curves in the future.
AB - Context. Many moons have been detected around planets in our Solar System, but none has been detected unambiguously around any of the confirmed extrasolar planets. Aims. We test the feasibility of a supervised convolutional neural network to classify photometric transit light curves of planet-host stars and identify exomoon transits, while avoiding false positives caused by stellar variability or instrumental noise. Methods. Convolutional neural networks are known to have contributed to improving the accuracy of classification tasks. The network optimization is typically performed without studying the effect of noise on the training process. Here we design and optimize a 1D convolutional neural network to classify photometric transit light curves. We regularize the network by the total variation loss in order to remove unwanted variations in the data features. Results. Using numerical experiments, we demonstrate the benefits of our network, which produces results comparable to or better than the standard network solutions. Most importantly, our network clearly outperforms a classical method used in exoplanet science to identify moon-like signals. Thus the proposed network is a promising approach for analyzing real transit light curves in the future.
KW - Methods: data analysis
KW - Methods: numerical
KW - Moon
UR - http://www.scopus.com/inward/record.url?scp=85089602220&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089602220&partnerID=8YFLogxK
U2 - 10.1051/0004-6361/201937059
DO - 10.1051/0004-6361/201937059
M3 - Article
AN - SCOPUS:85089602220
SN - 0004-6361
VL - 640
JO - Astronomy and Astrophysics
JF - Astronomy and Astrophysics
M1 - A41
ER -