Neural networks for image-based wavefront sensing for astronomy

Andersen, Torben; Owner-Petersen, Mette; Enmark, Anita

doi:10.1364/ol.44.004618

Cited by 31 publications

(15 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with other optimization approaches that rely on iterative methods, including prior information about the experimental setup additionally constrains the optimization process [12]. Compared to neural network approaches [33,34,35,36,37,38,39,40,24,41], differentiable model-based approaches have the advantage that they don't rely on a predetermined model of sample aberrations.…”

Section: Discussionmentioning

confidence: 99%

Differentiable model-based adaptive optics for two-photon microscopy

Vishniakou,

Seelig

2021

Preprint

View full text Add to dashboard Cite

Aberrations limit scanning fluorescence microscopy when imaging in scattering materials such as biological tissue. Model-based approaches for adaptive optics take advantage of a computational model of the optical setup. Such models can be combined with the optimization techniques of machine learning frameworks to find aberration corrections, as was demonstrated for focusing a laser beam through aberrations onto a camera [1]. Here, we extend this approach to two-photon scanning microscopy. The developed sensorless technique finds corrections for aberrations in scattering samples and will be useful for a range of imaging application, for example in brain tissue.

show abstract

Section: Discussionmentioning

confidence: 99%

Differentiable model-based adaptive optics for two-photon microscopy

Vishniakou,

Seelig

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Wavefront prediction and reconstruction have been demonstrated with simulated data for the Gemini telescope with an NN that combines both LSTMs and CNNs 14 and there has been some success in applying Google's Inception v. 3 CNN to predict Zernike coefficients from in-focus and out-of-focus artificially generated point spread functions (PSFs). 15 CNNs have also been used to reconstruct phase maps of simulated data from the corresponding PSF, 16 and an LSTM has been used to extract wavefront aberrations from in-focus and out-of-focus images with simulated data. 17 In an indirectly related area, feedforward NNs have been used to control a deformable mirror using Shack-Hartmann WFSMs.…”

Section: Introductionmentioning

confidence: 99%

Predictive control for adaptive optics using neural networks

Wong

Norris

Tuthill

et al. 2021

J. Astron. Telesc. Instrum. Syst.

View full text Add to dashboard Cite

Adaptive optics (AO) has become an indispensable tool for ground-based telescopes to mitigate atmospheric seeing and obtain high angular resolution observations. Predictive control aims to overcome latency in AO systems: the inevitable time delay between wavefront measurement and correction. A current method of predictive control uses the empirical orthogonal functions (EOFs) framework borrowed from weather prediction, but the advent of modern machine learning and the rise of neural networks (NNs) offer scope for further improvement.Here, we evaluate the potential application of NNs to predictive control and highlight the advantages that they offer. We first show their superior regularization over the standard truncation regularization used by the linear EOF method with on-sky data before demonstrating the NNs' capacity to model nonlinearities on simulated data. This is highly relevant to the operation of pyramid wavefront sensors (PyWFSs), as the handling of nonlinearities would enable a PyWFS to be used with low modulation and deliver extremely sensitive wavefront measurements.

show abstract

“…A first, brief report was given in a previous article. 17 Here, we go into more detail to demonstrate the possibilities and limitations of the use of neural networks for image-based wavefront Fig. 1 Number of Zernike terms (dash-dot green and solid blue) and RMS wavefront error (dashed red) at the entrance pupil needed for a given Strehl ratio for two different primary mirror diameters and Fried's parameter r 0 ¼ 0.17 m.…”

Section: Introductionmentioning

confidence: 99%

Image-based wavefront sensing for astronomy using neural networks

Andersen

Owner-Petersen

Enmark

2020

J. Astron. Telesc. Instrum. Syst.

Self Cite

View full text Add to dashboard Cite

Motivated by the potential of nondiffraction limited, real-time computational image sharpening with neural networks in astronomical telescopes, we studied wavefront sensing with convolutional neural networks based on a pair of in-focus and out-of-focus point spread functions. By simulation, we generated a large dataset for training and validation of neural networks and trained several networks to estimate Zernike polynomial approximations for the incoming wavefront. We included the effect of noise, guide star magnitude, blurring by wide-band imaging, and bit depth. We conclude that the "ResNet" works well for our purpose, with a wavefront RMS error of 130 nm for r 0 ¼ 0.3 m, guide star magnitudes 4 to 8, and inference time of 8 ms. It can also be applied for closed-loop operation in an adaptive optics system. We also studied the possible use of a Kalman filter or a recurrent neural network and found that they were not beneficial to the performance of our wavefront sensor. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

Neural networks for image-based wavefront sensing for astronomy

Cited by 31 publications

References 6 publications

Differentiable model-based adaptive optics for two-photon microscopy

Differentiable model-based adaptive optics for two-photon microscopy

Predictive control for adaptive optics using neural networks

Image-based wavefront sensing for astronomy using neural networks

Contact Info

Product

Resources

About