Exoplanet Detection
Exoplanet detection aims to identify planets orbiting stars other than our Sun, primarily using indirect methods like radial velocity measurements and transit photometry, and increasingly through direct imaging. Current research heavily utilizes machine learning, employing convolutional neural networks (CNNs), recurrent neural networks (RNNs like LSTMs), and generative adversarial networks (GANs) to analyze diverse datasets (light curves, spectra, and images) and improve detection sensitivity, particularly for smaller, fainter planets. These advancements are crucial for characterizing exoplanet populations, refining our understanding of planetary formation, and potentially identifying potentially habitable worlds.
Papers
Machine Learning for Exoplanet Detection in High-Contrast Spectroscopy: Revealing Exoplanets by Leveraging Hidden Molecular Signatures in Cross-Correlated Spectra with Convolutional Neural Networks
Emily O. Garvin, Markus J. Bonse, Jean Hayoz, Gabriele Cugno, Jonas Spiller, Polychronis A. Patapis, Dominique Petit Dit de la Roche, Rakesh Nath-Ranga, Olivier Absil, Nicolai F. Meinshausen, Sascha P. Quanz
Machine learning for exoplanet detection in high-contrast spectroscopy Combining cross correlation maps and deep learning on medium-resolution integral-field spectra
Rakesh Nath-Ranga, Olivier Absil, Valentin Christiaens, Emily O. Garvin