AI-powered exoplanet detection web application using Kepler light curves, Box Least Squares transit detection, and machine learning.
-
Updated
Jul 2, 2026 - JavaScript
AI-powered exoplanet detection web application using Kepler light curves, Box Least Squares transit detection, and machine learning.
An end-to-end AI-driven pipeline for automated exoplanet detection, using a hybrid framework of 1D CNNs and Box Least Squares (BLS) to filter, classify, and physically model transit signals from noisy, crowded-field TESS light curves.
A MATLAB system implementing signal conditioning and periodic correlation to detect exoplanetary transits in curve light signals.
Full codebase for my Astronomy research project with David Hogg (NYU, Flatiron), including transit search algorithms and statistics tests!
AI pipeline that detects and classifies exoplanet transits in noisy TESS light curves - BLS/TLS search, 15 astrophysical vetting tests, a calibrated transit / eclipsing-binary / blend / other ML ensemble, and Bayesian fitting of period, depth & duration with uncertainties, plus one-page vetting sheets and a 3-page report. (BAH 2026 PS7)
Add a description, image, and links to the box-least-squares topic page so that developers can more easily learn about it.
To associate your repository with the box-least-squares topic, visit your repo's landing page and select "manage topics."