Focal Plane Wavefront Sensing using Machine Learning: Performance of Convolutional Neural Networks compared to Fundamental Limits

Abstract

Focal plane wavefront sensing (FPWFS) is appealing for several reasons. Notably, it offers high sensitivity and does not suffer from non-common path aberrations (NCPA). The price to pay is a high computational burden and the need for diversity to lift any phase ambiguity. If those limitations can be overcome, FPWFS is a great solution for NCPA measurement, a key limitation for high-contrast imaging, and could be used as adaptive optics wavefront sensor. Here, we propose to use deep convolutional neural networks (CNNs) to measure NCPA based on focal plane images. Two CNN architectures are considered: ResNet-50 and U-Net which are used respectively to estimate Zernike coefficients or directly the phase. The models are trained on labelled datasets and evaluated at various flux levels and for two spatial frequency contents (20 and 100 Zernike modes). In these idealized simulations we demonstrate that the CNN-based models reach the photon noise limit in a large range of conditions. We show, for example, that the root mean squared (rms) wavefront error (WFE) can be reduced to < $\lambda$/1500 for $2\times 10^6$ photons in one iteration when estimating 20 Zernike modes. We also show that CNN-based models are sufficiently robust to varying signal-to-noise ratio, under the presence of higher-order aberrations, and under different amplitudes of aberrations. Additionally, they display similar to superior performance compared to iterative phase retrieval algorithms. CNNs therefore represent a compelling way to implement FPWFS, which can leverage the high sensitivity of FPWFS over a broad range of conditions.

arXiv commentAccepted for publication in MNRAS; 13 pages, 14 figures

References in corpus (17)

• Array Programming with NumPy
• Astropy: A Community Python Package for Astronomy
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Limits of Adaptive Optics for high contrast imaging
• Calibration of quasi-static aberrations in exoplanet direct-imaging instruments with a Zernike phase-mask sensor
• High Sensitivity Wavefront Sensing with a non-linear Curvature Wavefront Sensor
• High-order myopic coronagraphic phase diversity (COFFEE) for wave-front control in high-contrast imaging systems
• Open-loop tomography with artificial neural networks on CANARY: on-sky results
• AOtools -- a Python package for adaptive optics modelling and analysis
• Closed Loop Predictive Control of Adaptive Optics Systems with Convolutional Neural Networks
• Wavefront prediction using artificial neural networks for open-loop Adaptive Optics
• Nonlinear wavefront reconstruction with convolutional neural networks for Fourier-based wavefront sensors
• Variation on a Zernike wavefront sensor theme: optimal use of photons
• Focal-plane wavefront sensing with the vector Apodizing Phase Plate
• Extremely fast focal-plane wavefront sensing for extreme adaptive optics
• Review of high-contrast imaging systems for current and future ground-based and space-based telescopes II. Common path wavefront sensing/control and Coherent Differential Imaging
• Optical measurements of phase steps in segmented mirrors - fundamental precision limits

Cited by in corpus (9)

• A deep learning approach for focal-plane wavefront sensing using vortex phase diversity
• Transformer neural networks for closed-loop adaptive optics using non-modulated pyramid wavefront sensors
• Phasing segmented telescopes via deep learning methods: application to a deployable CubeSat
• High-Contrast Coronagraphy
• Impact of water vapor seeing on mid-infrared high-contrast imaging at ELT scale
• A simulator-based autoencoder for focal plane wavefront sensing
• Focal-plane wavefront sensing with moderately broadband light using a short multi-mode fiber
• Focal plane wavefront control with model-based reinforcement learning
• Estimating differential pistons for the Extremely Large Telescope using focal plane imaging and a residual network