Exoplanets & Exomoons

ExoMiner: A Highly Accurate And Explainable Deep Learning Classifier To Mine Exoplanets

By Keith Cowing
November 23, 2021
Filed under
ExoMiner: A Highly Accurate And Explainable Deep Learning Classifier To Mine Exoplanets
Example DV 1-page summary report. It includes multiple diagnostic plots and variables: (0) Stellar parameters, (1) Full time series flux, (2) Full-orbit phase-folded flux, (3) Transit-view phase-folded secondary eclipsing flux, (4) Transit-view phase-folded flux, (5) Transit-view phase-folded whitened flux, (6) Transit-view phase-folded odd & even flux, (7) Difference image (out-of-transit) centroid offsets, and (8) DV analysis table of variables.

The Kepler and TESS missions have generated over 100,000 potential transit signals that must be processed in order to create a catalog of planet candidates.

During the last few years, there has been a growing interest in using machine learning to analyze these data in search of new exoplanets. Different from the existing machine learning works, ExoMiner, the proposed deep learning classifier in this work, mimics how domain experts examine diagnostic tests to vet a transit signal. ExoMiner is a highly accurate, explainable, and robust classifier that 1) allows us to validate 301 new exoplanets from the MAST Kepler Archive and 2) is general enough to be applied across missions such as the on-going TESS mission.

We perform an extensive experimental study to verify that ExoMiner is more reliable and accurate than the existing transit signal classifiers in terms of different classification and ranking metrics. For example, for a fixed precision value of 99%, ExoMiner retrieves 93.6% of all exoplanets in the test set (i.e., recall=0.936) while this rate is 76.3% for the best existing classifier. Furthermore, the modular design of ExoMiner favors its explainability. We introduce a simple explainability framework that provides experts with feedback on why ExoMiner classifies a transit signal into a specific class label (e.g., planet candidate or not planet candidate).

Hamed Valizadegan, Miguel Martinho, Laurent S. Wilkens, Jon M. Jenkins, Jeffrey Smith, Douglas A. Caldwell, Joseph D. Twicken, Pedro C. Gerum, Nikash Walia, Kaylie Hausknecht, Noa Y. Lubin, Stephen T. Bryson, Nikunj C. Oza

Comments: Accepted for Publication in Astrophysical Journals, November 20201
Subjects: Earth and Planetary Astrophysics (astro-ph.EP); Instrumentation and Methods for Astrophysics (astro-ph.IM); Machine Learning (cs.LG)
MSC classes: J.2, I.2.6
Cite as: arXiv:2111.10009 [astro-ph.EP] (or arXiv:2111.10009v1 [astro-ph.EP] for this version)
Submission history
From: Hamed Valizadegan
[v1] Fri, 19 Nov 2021 02:22:34 UTC (24,243 KB)

Explorers Club Fellow, ex-NASA Space Station Payload manager/space biologist, Away Teams, Journalist, Lapsed climber, Synaesthete, Na’Vi-Jedi-Freman-Buddhist-mix, ASL, Devon Island and Everest Base Camp veteran, (he/him) 🖖🏻