Artificial intelligence for real-time processing of high-contrast images for exoplanet detection during active wavefront sensing and control

Directly imaging and detecting exoplanets with a high-contrast imaging instrument must overcome residual starlight and quasi-static wavefront errors which pose significant challenges for real-time detection. In this work, we combine an Extended Kalman Filter (EKF) and a Convolutional Neural Network (CNN) to enhance exoplanet detection in high-contrast images. The EKF estimates the real and imaginary components of the open-loop electric field as well as the incoherent intensity for each pixel. The EKF is assembled using blocks or cells of pixels in the dark zone where each cell is the size of a potential planet point spread function (PSF). This aids the estimator as the properties of the planet PSF pixels should be related. The cell mapping for the EKF is initialized randomly assuming no prior knowledge of the potential planet location. The CNN is trained and tested on images from the High-contrast imager for Complex Aperture Telescopes (HiCAT) testbed at the Space Telescope Science Institute. HiCAT does not have an off-axis light source to emulate a planet on the testbed, so planets are injected via software into the raw testbed images. The CNN is trained to distinguish planetary signals from noise, such as starlight leakage, and to identify potential planets within specific grid cells in an image. Once the CNN identifies a possible planetary signal, the cell mapping and all appropriate EKF components are adjusted to center the detected planet within a single cell. This enables the EKF to refine the estimation of coherent and incoherent light at the updated grid coordinates, allowing for a more dynamic adaptation to changing wavefront errors and helping to ensure optimal suppression of residual starlight. This CNN-EKF approach provides a pathway for integrating machine learning and statistical modeling for real-time, autonomous exoplanet detection. It highlights the potential for advancing the performance of future space-based high-contrast imaging missions. The scope of this paper demonstrated that all major components of the autonomous detection pipeline are functional without causing delays or contrast degradation.