Discovery of the Smallest Ultra-short-period Exoplanet Using Novel GPU-Parallelized Phase Folding Detection System
CSEF · 2023 Physics & Astronomy First Award
Overview
The longstanding question of how ultra-short-period (USP) planets form and survive so close to their host stars signifies a gap in our understanding of planetary formation in the Universe. With only 127 USPs confirmed from the NASA Archive, the scarcity of samples hinders our investigation. Searching for USP exoplanets which have avoided detection so far requires significantly higher sensitivity and faster computation than existing transit detection methods. I design ExoScout, an independent detection system for large-scale surveys, to discern weak signals using an innovative phase folding algorithm parallelized on a Graphics Processing Unit (GPU) to efficiently handle the intensive computational workload and a Convolutional Neural Network to accurately identify transit signals in light curves. The system achieves 97% accuracy at 120 times the speed of the traditional Box-fitting Least Squares method and recovers all known USPs from a blind search. With ExoScout, I report the discovery of the smallest USP planet ever detected and a rare USP found in adversely hot conditions around a high temperature F-dwarf, only the eleventh of its kind from the NASA Archive. The discovery of these small exoplanets offers new samples to characterize USP planet formation and highlights ExoScout’s increased sensitivity to uncover previously missed exoplanets, unlocking large-scale exoplanet search in further transit missions such as TESS, JWST, and Earth 2.0. The innovation of this GPU-parallelized folding algorithm, which runs on relatively cheap hardware, replaces expensive supercomputers to make research more accessible and can be applied for high-precision periodic signal detection in many fields.
Source coverage
This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.
Awards (1)
Competition history
- CSEF 2023
Resources
Related projects
ISEF · 2023
Discovery of the Smallest Ever Ultra-Short-Period Planet Using Novel Phase Folding Detection System Parallelized on a Cheap GPU
ISEF · 2024
Discovery of Two Potentially Habitable Super-Earths! StealthPlanetFinder: Innovative & Computationally Efficient Algorithms to Detect Exoplanets Overcoming Low Signal-to-Noise Ratio
AJAS · 2022
New Exoplanet Discovered! Deep Learning Enables the Fastest, Most Sensitive Detections to Date
ISEF · 2024
Discovery of New Extragalactic Planet Candidates: A Novel End-to-End Machine Learning Pipeline for Efficient Transit Detection in the X-ray Spectrum
ISEF · 2022
A Specialized Searching Algorithm Towards the Improvement in Detection of Single-Transit and Long-Period Exoplanets in Brightness Time-Series Data
ISEF · 2021
A Mathematically Driven Physical Analysis into Exoplanet Detection Confirmation Surveys Using Bayesian Inferential Statistics, Machine Learning/Linear Algebra Sklearn and TensorFlow Techniques, the BATMAN Python Programming Library, 3D Printing Techniques, and a Custom-made Python Processing Pipeline for Image Analysis and Lightcurve Detection
ISEF · 2018
Far Out! Analyzing NASA's Kepler Space Telescope Data Using the Transit-Timing Variation Method to Discover Additional Exoplanets in Planetary Systems
ISEF · 2018
Challenging Limitations: Using Deep Learning, Time Series Analysis, and Statistical Methods for Noise Reduction to Develop an Innovative Approach to Exoplanet Candidate Detection Using Earth-Based Telescopes
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects