Physically constrained causal noise models for high-contrast imaging of exoplanets
This work addresses the challenge of exoplanet detection for astronomers, offering a potentially significant advancement if confirmed, though it appears incremental as it builds on existing methods.
The paper tackled the problem of detecting exoplanets in high-contrast imaging data by proposing a new post-processing approach that combines machine learning with domain knowledge, demonstrating improved performance over a leading algorithm on three real datasets with better visual and SNR results.
The detection of exoplanets in high-contrast imaging (HCI) data hinges on post-processing methods to remove spurious light from the host star. So far, existing methods for this task hardly utilize any of the available domain knowledge about the problem explicitly. We propose a new approach to HCI post-processing based on a modified half-sibling regression scheme, and show how we use this framework to combine machine learning with existing scientific domain knowledge. On three real data sets, we demonstrate that the resulting system performs clearly better (both visually and in terms of the SNR) than one of the currently leading algorithms. If further studies can confirm these results, our method could have the potential to allow significant discoveries of exoplanets both in new and archival data.