Deep learning for exoplanet detection and characterization by direct imaging at high contrast
This work addresses the problem of exoplanet imaging for astronomers, representing an incremental improvement in detection methods.
The authors tackled the challenge of exoplanet detection in high-contrast imaging by developing a multi-scale statistical model integrated into a learnable architecture, which significantly improved detection sensitivity and accuracy in astrometric and photometric estimation when applied to VLT/SPHERE data.
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.