Exoplanetology: Exoplanets & Exomoons

A New Statistical Model of Star Speckles for Learning to Detect and Characterize Exoplanets in Direct Imaging Observations

By Keith Cowing

Status Report

astro-ph.IM

March 25, 2025

Filed under astro-ph.IM, astronomy, data, exoplanet, imaging, SPEHRE, VLT

A New Statistical Model of Star Speckles for Learning to Detect and Characterize Exoplanets in Direct Imaging Observations — Workflow of the proposed method: it exploits both the spectral behavior of speckles and the apparent motion of exoplanets to disentangle the exoplanet signal from the nuisance component in the observations y. To achieve this, local patches of the nuisance are modeled as Gaussian distributions, leveraging problem symmetries and incorporating multiple scales. These patches are fed to our convolutional statistical model, and combined to form a detection map. Additionally, a learned object prior, represented by a UNet fν, is introduced to denoise this detection map produced by the statistical model. This approach results in an end-to-end learnable architecture. — astro-ph.IM

The search for exoplanets is an active field in astronomy, with direct imaging as one of the most challenging methods due to faint exoplanet signals buried within stronger residual starlight.

Successful detection requires advanced image processing to separate the exoplanet signal from this nuisance component. This paper presents a novel statistical model that captures nuisance fluctuations using a multi-scale approach, leveraging problem symmetries and a joint spectral channel representation grounded in physical principles.

Our model integrates into an interpretable, end-to-end learnable framework for simultaneous exoplanet detection and flux estimation. The proposed algorithm is evaluated against the state of the art using datasets from the SPHERE instrument operating at the Very Large Telescope (VLT).

It significantly improves the precision-recall trade-off, notably on challenging datasets that are otherwise unusable by astronomers. The proposed approach is computationally efficient, robust to varying data quality, and well suited for large-scale observational surveys.

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

Comments: Accepted to CVPR 2025
Subjects: Instrumentation and Methods for Astrophysics (astro-ph.IM); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Applications (stat.AP)
Cite as: arXiv:2503.17117 [astro-ph.IM] (or arXiv:2503.17117v1 [astro-ph.IM] for this version)
https://doi.org/10.48550/arXiv.2503.17117
Focus to learn more
Submission history
From: Théo Bodrito
[v1] Fri, 21 Mar 2025 13:07:55 UTC (6,967 KB)
https://arxiv.org/abs/2503.17117
Astrobiology,

Keith Cowing

Explorers Club Fellow, ex-NASA Space Station Payload manager/space biologist, Away Teams, Journalist, Lapsed climber, Synaesthete, Na’Vi-Jedi-Freman-Buddhist-mix, ASL, Devon Island and Everest Base Camp veteran, (he/him) 🖖🏻

Follow on Twitter