Open-Loop Wavefront Reconstruction with Pyramidal Sensors Using Convolutional Neural Networks

Neural networks have significantly advanced adaptive optics systems for telescopes in recent years. Future adaptive optics systems, especially for extremely large telescopes, are expected to predominantly employ pyramid wavefront sensors, which offer good sensitivity but suffer from a non-linear res...

Full description

Saved in:
Bibliographic Details
Main Authors: Saúl Pérez-Fernández, Alejandro Buendía-Roca, Carlos González-Gutiérrez, Francisco García-Riesgo, Javier Rodríguez-Rodríguez, Santiago Iglesias-Alvarez, Julia Fernández-Díaz, Francisco Javier Iglesias-Rodríguez
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/7/1028
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850212512032620544
author Saúl Pérez-Fernández
Alejandro Buendía-Roca
Carlos González-Gutiérrez
Francisco García-Riesgo
Javier Rodríguez-Rodríguez
Santiago Iglesias-Alvarez
Julia Fernández-Díaz
Francisco Javier Iglesias-Rodríguez
author_facet Saúl Pérez-Fernández
Alejandro Buendía-Roca
Carlos González-Gutiérrez
Francisco García-Riesgo
Javier Rodríguez-Rodríguez
Santiago Iglesias-Alvarez
Julia Fernández-Díaz
Francisco Javier Iglesias-Rodríguez
author_sort Saúl Pérez-Fernández
collection DOAJ
description Neural networks have significantly advanced adaptive optics systems for telescopes in recent years. Future adaptive optics systems, especially for extremely large telescopes, are expected to predominantly employ pyramid wavefront sensors, which offer good sensitivity but suffer from a non-linear response under certain conditions. This non-linearity limits the performance of traditional linear reconstruction methods, such as matrix–vector multiplication, leading to suboptimal performance. Convolutional Neural Networks offer a promising alternative, as they can model complex non-linear relationships and extract spatial patterns from sensor images. While CNN-based reconstruction has shown success in closed-loop systems, this study investigates their application in open-loop wavefront reconstruction. A custom network architecture and training strategy are developed, using realistic training data from end-to-end atmospheric turbulence simulations. CNNs are trained to reconstruct Zernike polynomial coefficients representing optical aberrations, enabling a tomographic estimation of turbulence. The proposed approach demonstrates significant improvements over conventional open-loop methods, underscoring the potential of CNNs to enhance wavefront reconstruction in next-generation AO systems.
format Article
id doaj-art-7dc561c93b5a4ec8b0f6b62e27b7d8a7
institution OA Journals
issn 2227-7390
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-7dc561c93b5a4ec8b0f6b62e27b7d8a72025-08-20T02:09:19ZengMDPI AGMathematics2227-73902025-03-01137102810.3390/math13071028Open-Loop Wavefront Reconstruction with Pyramidal Sensors Using Convolutional Neural NetworksSaúl Pérez-Fernández0Alejandro Buendía-Roca1Carlos González-Gutiérrez2Francisco García-Riesgo3Javier Rodríguez-Rodríguez4Santiago Iglesias-Alvarez5Julia Fernández-Díaz6Francisco Javier Iglesias-Rodríguez7Instituto de Ciencias y Tecnologías Espaciales de Asturias (ICTEA), University of Oviedo, 33004 Oviedo, SpainInstituto de Ciencias y Tecnologías Espaciales de Asturias (ICTEA), University of Oviedo, 33004 Oviedo, SpainInstituto de Ciencias y Tecnologías Espaciales de Asturias (ICTEA), University of Oviedo, 33004 Oviedo, SpainInstituto de Ciencias y Tecnologías Espaciales de Asturias (ICTEA), University of Oviedo, 33004 Oviedo, SpainInstituto de Ciencias y Tecnologías Espaciales de Asturias (ICTEA), University of Oviedo, 33004 Oviedo, SpainInstituto de Ciencias y Tecnologías Espaciales de Asturias (ICTEA), University of Oviedo, 33004 Oviedo, SpainInstituto de Ciencias y Tecnologías Espaciales de Asturias (ICTEA), University of Oviedo, 33004 Oviedo, SpainInstituto de Ciencias y Tecnologías Espaciales de Asturias (ICTEA), University of Oviedo, 33004 Oviedo, SpainNeural networks have significantly advanced adaptive optics systems for telescopes in recent years. Future adaptive optics systems, especially for extremely large telescopes, are expected to predominantly employ pyramid wavefront sensors, which offer good sensitivity but suffer from a non-linear response under certain conditions. This non-linearity limits the performance of traditional linear reconstruction methods, such as matrix–vector multiplication, leading to suboptimal performance. Convolutional Neural Networks offer a promising alternative, as they can model complex non-linear relationships and extract spatial patterns from sensor images. While CNN-based reconstruction has shown success in closed-loop systems, this study investigates their application in open-loop wavefront reconstruction. A custom network architecture and training strategy are developed, using realistic training data from end-to-end atmospheric turbulence simulations. CNNs are trained to reconstruct Zernike polynomial coefficients representing optical aberrations, enabling a tomographic estimation of turbulence. The proposed approach demonstrates significant improvements over conventional open-loop methods, underscoring the potential of CNNs to enhance wavefront reconstruction in next-generation AO systems.https://www.mdpi.com/2227-7390/13/7/1028machine learningneural networksastronomyopticsinstrumentationpyramid wavefront sensor
spellingShingle Saúl Pérez-Fernández
Alejandro Buendía-Roca
Carlos González-Gutiérrez
Francisco García-Riesgo
Javier Rodríguez-Rodríguez
Santiago Iglesias-Alvarez
Julia Fernández-Díaz
Francisco Javier Iglesias-Rodríguez
Open-Loop Wavefront Reconstruction with Pyramidal Sensors Using Convolutional Neural Networks
Mathematics
machine learning
neural networks
astronomy
optics
instrumentation
pyramid wavefront sensor
title Open-Loop Wavefront Reconstruction with Pyramidal Sensors Using Convolutional Neural Networks
title_full Open-Loop Wavefront Reconstruction with Pyramidal Sensors Using Convolutional Neural Networks
title_fullStr Open-Loop Wavefront Reconstruction with Pyramidal Sensors Using Convolutional Neural Networks
title_full_unstemmed Open-Loop Wavefront Reconstruction with Pyramidal Sensors Using Convolutional Neural Networks
title_short Open-Loop Wavefront Reconstruction with Pyramidal Sensors Using Convolutional Neural Networks
title_sort open loop wavefront reconstruction with pyramidal sensors using convolutional neural networks
topic machine learning
neural networks
astronomy
optics
instrumentation
pyramid wavefront sensor
url https://www.mdpi.com/2227-7390/13/7/1028
work_keys_str_mv AT saulperezfernandez openloopwavefrontreconstructionwithpyramidalsensorsusingconvolutionalneuralnetworks
AT alejandrobuendiaroca openloopwavefrontreconstructionwithpyramidalsensorsusingconvolutionalneuralnetworks
AT carlosgonzalezgutierrez openloopwavefrontreconstructionwithpyramidalsensorsusingconvolutionalneuralnetworks
AT franciscogarciariesgo openloopwavefrontreconstructionwithpyramidalsensorsusingconvolutionalneuralnetworks
AT javierrodriguezrodriguez openloopwavefrontreconstructionwithpyramidalsensorsusingconvolutionalneuralnetworks
AT santiagoiglesiasalvarez openloopwavefrontreconstructionwithpyramidalsensorsusingconvolutionalneuralnetworks
AT juliafernandezdiaz openloopwavefrontreconstructionwithpyramidalsensorsusingconvolutionalneuralnetworks
AT franciscojavieriglesiasrodriguez openloopwavefrontreconstructionwithpyramidalsensorsusingconvolutionalneuralnetworks