Identify Light-Curve Signals with Deep Learning Based Object Detection Algorithm. I. Transit Detection

Abstract

Deep learning techniques have been well explored in the transiting exoplanet field; however, previous work mainly focuses on classification and inspection. In this work, we develop a novel detection algorithm based on a well proven object detection framework in the computer vision field. Through training the network on the light curves of the confirmed Kepler exoplanets, our model yields about 90% precision and recall for identifying transits with signal-to-noise ratio higher than 6 (set the confidence threshold to 0.6). Giving a slightly lower confidence threshold, recall can reach higher than 95%. We also transfer the trained model to the TESS data and obtain similar performance. The results of our algorithm match the intuition of the human visual perception and make it useful to find single-transiting candidates. Moreover, the parameters of the output bounding boxes can also help to find multiplanet systems. Our network and detection functions are implemented in the Deep-Transit toolkit, which is an open-source Python package hosted on GitHub and PyPI.

arXiv comment22 pages, 14 figures, 1 table, matches the version to be published in AJ

References in corpus (44)

• Array Programming with NumPy
• Astropy: A Community Python Package for Astronomy
• The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
• YOLOv3: An Incremental Improvement
• Analytic Lightcurves for Planetary Transit Searches
• A Survey of Autonomous Driving: Common Practices and Emerging Technologies
• batman: BAsic Transit Model cAlculatioN in Python
• Planetary Candidates Observed by Kepler, III: Analysis of the First 16 Months of Data
• A box-fitting algorithm in the search for periodic transits
• Architecture and Dynamics of Kepler's Candidate Multiple Transiting Planet Systems
• Validation of Kepler's Multiple Planet Candidates. III: Light Curve Analysis & Announcement of Hundreds of New Multi-planet Systems
• The TESS Objects of Interest Catalog from the TESS Prime Mission
• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• Parameter Estimation from Time-Series Data with Correlated Errors: A Wavelet-Based Method and its Application to Transit Light Curves
• Transit Least Squares: Optimized transit detection algorithm to search for periodic transits of small planets
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• Deep learning of multi-element abundances from high-resolution spectroscopic data
• Predicting Solar Flares Using a Long Short-Term Memory Network
• RAPID: Early Classification of Explosive Transients using Deep Learning
• Flare Statistics for Young Stars from a Convolutional Neural Network Analysis of $\text{TESS}$ Data
• Planet Hunters: The First Two Planet Candidates Identified by the Public using the Kepler Public Archive Data
• Searching for Exoplanets Using Artificial Intelligence
• Deep Recurrent Neural Networks for Supernovae Classification
• The population of long-period transiting exoplanets
• Autoregressive Times Series Methods for Time Domain Astronomy
• Detection of Potential Transit Signals in 17 Quarters of Kepler Data: Results of the Final Kepler Mission Transiting Planet Search (DR25)
• Scientific Domain Knowledge Improves Exoplanet Transit Classification with Deep Learning
• 150 New transiting planet candidates from Kepler Q1-Q6 data
• Identifying Exoplanets with Deep Learning III: Automated Triage and Vetting of TESS Candidates
• Identifying Exoplanets with Deep Learning II: Two New Super-Earths Uncovered by a Neural Network in K2 Data
• Machine-learning Approaches to Exoplanet Transit Detection and Candidate Validation in Wide-field Ground-based Surveys
• Single Transit Candidates from K2: Detection and Period Estimation
• Rapid Classification of TESS Planet Candidates with Convolutional Neural Networks
• Shallow Transits - Deep Learning I: Feasibility Study of Deep Learning to Detect Periodic Transits of Exoplanets
• Machine Learning Techniques for Stellar Light Curve Classification
• Planet Hunters TESS II: Findings from the first two years of TESS
• Transiting Planet Candidates Beyond the Snow Line Detected by Visual Inspection of 7557 Kepler Objects of Interest
• An Estimate of the Yield of Single-Transit Planetary Events from the Transiting Exoplanet Survey Satellite
• Classifying Exoplanet Candidates with Convolutional Neural Networks: Application to the Next Generation Transit Survey
• AutoRegressive Planet Search: Application to the Kepler Mission
• Single site observations of \textit{TESS} single transit detections
• Transiting Planets near the Snow Line from Kepler. I. Catalog
• Identifying Planetary Transit Candidates in TESS Full-Frame Image Light Curves via Convolutional Neural Networks
• Following up TESS Single Transits With Archival Photometry and Radial Velocities

Cited by in corpus (7)

• Identifying Exoplanets with Deep Learning. V. Improved Light Curve Classification for TESS Full Frame Image Observations
• Identifying Light-curve Signals with a Deep Learning Based Object Detection Algorithm. II. A General Light Curve Classification Framework
• The GPU Phase Folding and Deep Learning Method for Detecting Exoplanet Transits
• Convolutional Neural Networks for Searching Superflares from Pixel-level Data of the Transiting Exoplanet Survey Satellite
• Exoplanet Transit Candidate Identification in TESS Full-Frame Images via a Transformer-Based Algorithm
• FALCO: a Foundation model of Astronomical Light Curves for time dOmain astronomy
• The Visual Survey Group: A Decade of Hunting Exoplanets and Unusual Stellar Events with Space-Based Telescopes