New computational technique reveals hidden giant exoplanet in James Webb Space Telescope data

Researchers at Northwestern University have developed a new method, called Physics-based Learning for Imaging Planets (FLIP), to effectively remove starlight glare from James Webb Space Telescope (JWST) images. This technique significantly improved the telescope's sensitivity for detecting faint planets by two to fifteen times and successfully revealed the exoplanet 51 Eridani b, which was previously indistinguishable from residual starlight at a specific wavelength. The method combines physics-based modeling and machine learning, offering a promising approach to discover smaller, colder, and fainter planets without requiring new hardware.