TY - JOUR
T1 - Nonlinear Wave Front Reconstruction from a Pyramid Sensor using Neural Networks
AU - Wong, Alison P.
AU - Norris, Barnaby R.M.
AU - Deo, Vincent
AU - Tuthill, Peter G.
AU - Scalzo, Richard
AU - Sweeney, David
AU - Ahn, Kyohoon
AU - Lozi, Julien
AU - Vievard, Sébastien
AU - Guyon, Olivier
N1 - Publisher Copyright:
© 2023. The Author(s). Published by IOP Publishing Ltd on behalf of the Astronomical Society of the Pacific (ASP). All rights reserved.
PY - 2023/11/1
Y1 - 2023/11/1
N2 - The pyramid wave front sensor (PyWFS) has become increasingly popular to use in adaptive optics (AO) systems due to its high sensitivity. The main drawback of the PyWFS is that it is inherently nonlinear, which means that classic linear wave front reconstruction techniques face a significant reduction in performance at high wave front errors, particularly when the pyramid is unmodulated. In this paper, we consider the potential use of neural networks (NNs) to replace the widely used matrix vector multiplication (MVM) control. We aim to test the hypothesis that the NN's ability to model nonlinearities will give it a distinct advantage over MVM control. We compare the performance of a MVM linear reconstructor against a dense NN, using daytime data acquired on the Subaru Coronagraphic Extreme Adaptive Optics system (SCExAO) instrument. In a first set of experiments, we produce wavefronts generated from 14 Zernike modes and the PyWFS responses at different modulation radii (25, 50, 75, and 100 mas). We find that the NN allows for a far more precise wave front reconstruction at all modulations, with differences in performance increasing in the regime where the PyWFS nonlinearity becomes significant. In a second set of experiments, we generate a data set of atmosphere-like wavefronts, and confirm that the NN outperforms the linear reconstructor. The SCExAO real-time computer software is used as baseline for the latter. These results suggest that NNs are well positioned to improve upon linear reconstructors and stand to bring about a leap forward in AO performance in the near future.
AB - The pyramid wave front sensor (PyWFS) has become increasingly popular to use in adaptive optics (AO) systems due to its high sensitivity. The main drawback of the PyWFS is that it is inherently nonlinear, which means that classic linear wave front reconstruction techniques face a significant reduction in performance at high wave front errors, particularly when the pyramid is unmodulated. In this paper, we consider the potential use of neural networks (NNs) to replace the widely used matrix vector multiplication (MVM) control. We aim to test the hypothesis that the NN's ability to model nonlinearities will give it a distinct advantage over MVM control. We compare the performance of a MVM linear reconstructor against a dense NN, using daytime data acquired on the Subaru Coronagraphic Extreme Adaptive Optics system (SCExAO) instrument. In a first set of experiments, we produce wavefronts generated from 14 Zernike modes and the PyWFS responses at different modulation radii (25, 50, 75, and 100 mas). We find that the NN allows for a far more precise wave front reconstruction at all modulations, with differences in performance increasing in the regime where the PyWFS nonlinearity becomes significant. In a second set of experiments, we generate a data set of atmosphere-like wavefronts, and confirm that the NN outperforms the linear reconstructor. The SCExAO real-time computer software is used as baseline for the latter. These results suggest that NNs are well positioned to improve upon linear reconstructors and stand to bring about a leap forward in AO performance in the near future.
UR - http://www.scopus.com/inward/record.url?scp=85176919849&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85176919849&partnerID=8YFLogxK
U2 - 10.1088/1538-3873/acfdcb
DO - 10.1088/1538-3873/acfdcb
M3 - Article
AN - SCOPUS:85176919849
SN - 0004-6280
VL - 135
JO - Publications of the Astronomical Society of the Pacific
JF - Publications of the Astronomical Society of the Pacific
IS - 1053
M1 - 114501
ER -