Using AI for Wave-front Estimation with the Rubin Observatory Active Optics System

The Rubin Observatory will use a sophisticated auto-focus system (i.e., active optics) to enable the fast cadence and high image quality required for its groundbreaking ten year survey of the southern sky.

This system must operate with higher speed and deliver higher precision than what has been necessary for previous wide-field surveys which limits the applicability of existing state-of-the-art active optics algorithms. In this work we design a new algorithm which uses artificial intelligence (AI) to accelerate and increase the predictive power of the active optics system in a wide variety of observing conditions which the Rubin Observatory will face

John Franklin Crenshaw is a 5th year PhD student in the Physics Department.

He works with Professor Andy Connolly and UW scientists Bryce Kalmbach and Chris Suberlak on building the active optics pipeline for the Vera Rubin Observatory.

Published paper in February 2024, it can be found here.


The Vera C. Rubin Observatory will, over a period of 10 yr, repeatedly survey the southern sky. To ensure that images generated by Rubin meet the quality requirements for precision science, the observatory will use an active-optics system (AOS) to correct for alignment and mirror surface perturbations introduced by gravity and temperature gradients in the optical system.

To accomplish this, Rubin will use out-of-focus images from sensors located at the edge of the focal plane to learn and correct for perturbations to the wave front. We have designed and integrated a deep-learning (DL) model for wave-front estimation into the AOS pipeline. In this paper, we compare the performance of this DL approach to Rubin’s baseline algorithm when applied to images from two different simulations of the Rubin optical system. We show the DL approach is faster and more accurate, achieving the atmospheric error floor both for high-quality images and low-quality images with heavy blending and vignetting. Compared to the baseline algorithm, the DL model is 40× faster, the median error 2× better under ideal conditions, 5× better in the presence of vignetting by the Rubin camera, and 14× better in the presence of blending in crowded fields. In addition, the DL model surpasses the required optical quality in simulations of the AOS closed loop.

This system promises to increase the survey area useful for precision science by up to 8%. We discuss how this system might be deployed when commissioning and operating Rubin.