Deep learning for exoplanet detection and characterization by direct imaging at high contrast

Théo Bodrito; Olivier Flasseur; Julien Mairal; Jean Ponce; Maud Langlois; Anne-Marie Lagrange

Deep learning for exoplanet detection and characterization by direct imaging at high contrast

Instrumentation and Methods for Astrophysics 2025-09-25 v1 Earth and Planetary Astrophysics Machine Learning

Authors: Théo Bodrito , Olivier Flasseur , Julien Mairal , Jean Ponce , Maud Langlois , Anne-Marie Lagrange

Abstract

Exoplanet imaging is a major challenge in astrophysics due to the need for high angular resolution and high contrast. We present a multi-scale statistical model for the nuisance component corrupting multivariate image series at high contrast. Integrated into a learnable architecture, it leverages the physics of the problem and enables the fusion of multiple observations of the same star in a way that is optimal in terms of detection signal-to-noise ratio. Applied to data from the VLT/SPHERE instrument, the method significantly improves the detection sensitivity and the accuracy of astrometric and photometric estimation.

Keywords

machine learning in astronomy coronagraphy astronomical image processing

Cite

@article{arxiv.2509.20310,
  title  = {Deep learning for exoplanet detection and characterization by direct imaging at high contrast},
  author = {Théo Bodrito and Olivier Flasseur and Julien Mairal and Jean Ponce and Maud Langlois and Anne-Marie Lagrange},
  journal= {arXiv preprint arXiv:2509.20310},
  year   = {2025}
}

Comments

SF2A 2025

Deep learning for exoplanet detection and characterization by direct imaging at high contrast

Abstract

Keywords

Cite

Comments

Related papers