Searching for Exoplanets Using Artificial Intelligence

Abstract

In the last decade, over a million stars were monitored to detect transiting planets. Manual interpretation of potential exoplanet candidates is labor intensive and subject to human error, the results of which are difficult to quantify. Here we present a new method of detecting exoplanet candidates in large planetary search projects which, unlike current methods uses a neural network. Neural networks, also called "deep learning" or "deep nets" are designed to give a computer perception into a specific problem by training it to recognize patterns. Unlike past transit detection algorithms deep nets learn to recognize planet features instead of relying on hand-coded metrics that humans perceive as the most representative. Our convolutional neural network is capable of detecting Earth-like exoplanets in noisy time-series data with a greater accuracy than a least-squares method. Deep nets are highly generalizable allowing data to be evaluated from different time series after interpolation without compromising performance. As validated by our deep net analysis of Kepler light curves, we detect periodic transits consistent with the true period without any model fitting. Our study indicates that machine learning will facilitate the characterization of exoplanets in future analysis of large astronomy data sets.

Accepted, 16 Pages, 14 Figures, https://github.com/pearsonkyle/Exoplanet-Artificial-Intelligence

References in corpus (13)

• The Transiting Exoplanet Survey Satellite
• The K2 Mission: Characterization and Early results
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Planetary Candidates Observed by Kepler V: Planet Sample from Q1-Q12 (36 Months)
• Testing the recovery of stellar rotation signals from Kepler light curves using a blind hare-and-hounds exercise
• A nearby M star with three transiting super-Earths discovered by K2
• Automatic Classification of Kepler Planetary Transit Candidates
• Revisiting Spitzer transit observations with Independent Component Analysis: new results for the GJ436 system
• Transit Shapes and Self Organising Maps as a Tool for Ranking Planetary Candidates: Application to Kepler and K2
• The ground-based H, K, and L-band absolute emission spectra of HD 209458b
• Robust, open-source removal of systematics in Kepler data
• Transit Clairvoyance: Enhancing TESS follow-up using artificial neural networks
• K2 Variable Catalogue I: A Catalogue of Variable Stars from K2 Field 0

Cited by in corpus (5)

• Identifying Exoplanets with Deep Learning III: Automated Triage and Vetting of TESS Candidates
• AutoRegressive Planet Search: Application to the Kepler Mission
• Transit least-squares survey -- II. Discovery and validation of 17 new sub- to super-Earth-sized planets in multi-planet systems from K2
• Detecting Exoplanet Transits through Machine Learning Techniques with Convolutional Neural Networks
• Identifying MgII Narrow Absorption Lines with Deep Learning