Detecting Exoplanet Transits through Machine Learning Techniques with Convolutional Neural Networks

Abstract

A machine learning technique with two-dimension convolutional neural network is proposed for detecting exoplanet transits. To test this new method, five different types of deep learning models with or without folding are constructed and studied. The light curves of the Kepler Data Release 25 are employed as the input of these models. The accuracy, reliability, and completeness are determined and their performances are compared. These results indicate that a combination of two-dimension convolutional neural network with folding would be an excellent choice for the future transit analysis.

32 pages, 14 figures, to be published in PASP soon (Figure 1 is replaced)

References in corpus (22)

• Analytic Lightcurves for Planetary Transit Searches
• Planetary Candidates Observed by Kepler, III: Analysis of the First 16 Months of Data
• Kepler Presearch Data Conditioning II - A Bayesian Approach to Systematic Error Correction
• A box-fitting algorithm in the search for periodic transits
• Overview of the Kepler Science Processing Pipeline
• Planetary Candidates Observed by Kepler. VIII. A Fully Automated Catalog With Measured Completeness and Reliability Based on Data Release 25
• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• Planetary Candidates Observed by Kepler VI: Planet Sample from Q1-Q16 (47 Months)
• Planetary Candidates Observed by Kepler. VII. The First Fully Uniform Catalog Based on The Entire 48 Month Dataset (Q1-Q17 DR24)
• Searching for Exoplanets Using Artificial Intelligence
• Automatic Classification of Kepler Planetary Transit Candidates
• Measuring Transit Signal Recovery in the Kepler Pipeline II: Detection Efficiency as Calculated in One Year of Data
• Discovery of the Transiting Planet Kepler-5b
• QSO Selection Algorithm Using Time Variability and Machine Learning: Selection of 1,620 QSO Candidates from MACHO LMC Database
• Measuring Transit Signal Recovery in the Kepler Pipeline I: Individual Events
• A Machine Learning Technique to Identify Transit Shaped Signals
• Measuring Transit Signal Recovery in the Kepler Pipeline. III. Completeness of the Q1-Q17 DR24 Planet Candidate Catalogue, with Important Caveats for Occurrence Rate Calculations
• Machine Learning Techniques for Stellar Light Curve Classification
• Shallow Transits - Deep Learning I: Feasibility Study of Deep Learning to Detect Periodic Transits of Exoplanets
• Transit Shapes and Self Organising Maps as a Tool for Ranking Planetary Candidates: Application to Kepler and K2
• Identifying False Alarms in the Kepler Planet Candidate Catalog
• How accurate are the time delay estimates in gravitational lensing?

Cited by in corpus (5)

• Multilayer Perceptron and Geometric Albedo Spectra for Quick Parameter Estimations of Exoplanets
• Searching for Possible Exoplanet Transits from BRITE Data through a Machine Learning Technique
• The GPU Phase Folding and Deep Learning Method for Detecting Exoplanet Transits
• A Possible Converter to Denoise the Images of Exoplanet Candidates through Machine Learning Techniques
• Search for exocomets transits in Kepler light curves: Ten new transits identified