Letter to the Editor

Making the unmodulated pyramid wavefront sensor smart

II. First on-sky demonstration of extreme adaptive optics with deep learning

¹ Leiden Observatory, Leiden University, PO Box 9513 2300 RA Leiden, The Netherlands
² Steward Observatory, The Unversity of Arizona, 933 North Cherry Avenue, Tucson, Arizona, USA
³ Center for Computational Astrophysics, Flatiron Institute, 162 5th Avenue, New York, New York, USA
⁴ Wyant College of Optical Sciences, The University of Arizona, 1630 E University Blvd, Tucson, Arizona, USA
⁵ Subaru Telescope, National Observatory of Japan, National Institutes of Natural Sciences, 650 N. A’ohoku Place, Hilo, Hawai’i, USA
⁶ Astrobiology Center, National Institutes of Natural Sciences, 2-21-1 Osawa, Mitaka, Tokyo, Japan
⁷ Northrop Grumman Corporation, 600 South Hicks Road, Rolling Meadows, Illinois, USA
⁸ Draper Laboratory, 555 Technology Square, Cambridge, Massachusetts, USA
⁹ Starfire Optical Range, Kirtland Air Force Base, Albuquerque, New Mexico, USA

^⋆ Corresponding author; rlandman@strw.leidenuniv.nl

Received: 14 January 2025
Accepted: 10 March 2025

Abstract

Pyramid wavefront sensors (PWFSs) are the preferred choice for current and future extreme adaptive optics (XAO) systems. Almost all instruments use the PWFS in its modulated form to mitigate its limited linearity range. However, this modulation comes at the cost of a reduction in sensitivity, a blindness to petal-piston modes, and a limit to the sensor’s ability to operate at high speeds. Therefore, there is strong interest to use the PWFS without modulation, which can be enabled with nonlinear reconstructors. Here, we present the first on-sky demonstration of XAO with an unmodulated PWFS using a nonlinear reconstructor based on convolutional neural networks. We discuss the real-time implementation on the Magellan Adaptive Optics eXtreme (MagAO-X) instrument using the optimized TensorRT framework and show that inference is fast enough to run the control loop at > 2 kHz frequencies. Our on-sky results demonstrate a successful closed-loop operation using a model calibrated with internal source data that delivers stable and robust correction under varying conditions. Performance analysis reveals that our smart PWFS achieves nearly the same Strehl ratio as the highly optimized modulated PWFS under favorable conditions on bright stars. Notably, we observe an improvement in performance on a fainter star under the influence of strong winds. These findings confirm the feasibility of using the PWFS in its unmodulated form and highlight its potential for next-generation instruments. Future efforts will focus on achieving even higher control loop frequencies (> 3 kHz), optimizing the calibration procedures, and testing its performance on fainter stars, where more gain is expected for the unmodulated PWFS compared to its modulated counterpart.