Image-based wavefront sensing for astronomy using neural networks

Abstract

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.

Differentiable model-based adaptive optics for two-photon microscopy

“…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.…”

Review of PSF reconstruction methods and application to post-processing

“…The calibration of instrumental aberrations, through phase diversity approaches, [30][31][32] focal plane sharpening 33 techniques, or even Deep-learning strategies, 34,35 is particularly challenging. First of all, sampling the instrumental aberrations across the fov is feasible by the use of internal fibers within the system, 36,37 but can be potentially time consuming and requires direct control of the system.…”

Differentiable model-based adaptive optics with transmitted and reflected light

“…Machine learning offers novel approaches to correct for aberrations encountered when imaging though scattering materials, [1][2][3][4] from astronomy [5][6][7][8][9] to microscopy with transmitted (for example [10][11][12]) and reflected light [13]. To find aberration corrections in these situations, machine learning typically relies on large synthetic datasets.…”

“…In practice, training datasets are often based on combinations of Zernike polynomials [5][6][7][8][9][10][11][12][13] which might however not accurately capture all aspects of experimentally encountered aberrations. Additionally, for more strongly scattering samples, which require increasingly higher orders of Zernike modes, covering all potential scattering situations by sampling a sufficient number of different mode combinations eventually results in very large datasets.…”