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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bodrito, Théo, Flasseur, Olivier, Mairal, Julien, Ponce, Jean, Langlois, Maud, Lagrange, Anne-Marie
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915511618502656
author Bodrito, Théo
Flasseur, Olivier
Mairal, Julien
Ponce, Jean
Langlois, Maud
Lagrange, Anne-Marie
author_facet Bodrito, Théo
Flasseur, Olivier
Mairal, Julien
Ponce, Jean
Langlois, Maud
Lagrange, Anne-Marie
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20310
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep learning for exoplanet detection and characterization by direct imaging at high contrast
Bodrito, Théo
Flasseur, Olivier
Mairal, Julien
Ponce, Jean
Langlois, Maud
Lagrange, Anne-Marie
Instrumentation and Methods for Astrophysics
Earth and Planetary Astrophysics
Machine Learning
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.
title Deep learning for exoplanet detection and characterization by direct imaging at high contrast
topic Instrumentation and Methods for Astrophysics
Earth and Planetary Astrophysics
Machine Learning
url https://arxiv.org/abs/2509.20310