Improving Adaptive Optics Reconstructions with a Deep Learning Approach

Gómez, Sergio Luis Suárez; González-Gutiérrez, Carlos; Alonso, Enrique Díez; Rodríguez, Jesús Daniel Santos; Rodríguez, María Luisa Sánchez; Landeira, Jorge Carballido; Basden, Alastair; Osborn, James

doi:10.1007/978-3-319-92639-1_7

Cited by 14 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a convolutional neural network, the model is intended to allow the use of images, or high-dimensional data samples, that represent a computational problem when the dimension is lowered to vector shape. If, for example, an image is reshaped to a vector to be used as the inputs of a MLP network, some relevant information, as spatial position, may be lost [44]. The convolutional networks were developed to avoid this issue, using the whole sample.…”

Section: Methodsmentioning

confidence: 99%

Convolutional Neural Networks Approach for Solar Reconstruction in SCAO Configurations

Gómez

González-Gutiérrez

Riesgo

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

Correcting atmospheric turbulence effects in light with Adaptive Optics is necessary, since it produces aberrations in the wavefront of astronomical objects observed with telescopes from Earth. These corrections are performed classically with reconstruction algorithms; between them, neural networks showed good results. In the context of solar observation, the usage of Adaptive Optics on solar differs from nocturnal operations, bringing up a challenge to correct the image aberrations. In this work, a convolutional approach is given to address this issue, considering SCAO configurations. A reconstruction algorithm is presented, “Shack-Hartmann reconstruction with deep learning on solar–prototype” (proto-HELIOS), to correct on fixed solar images, achieving an average 85.39% of precision in the reconstruction. Additionally, results encourage to continue working with these techniques to achieve a reconstruction technique for all the regions of the sun.

show abstract

Section: Methodsmentioning

confidence: 99%

Convolutional Neural Networks Approach for Solar Reconstruction in SCAO Configurations

Gómez

González-Gutiérrez

Riesgo

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, in actual on-sky experiments, the performance of CARMEN only approached that of L&A [36] . Following this, SLS.Gómez et al improved the CARMEN MLP by introducing Convolutional CARMEN, where a convolutional neural network replaced the multilayer perceptron [37] . The structure of Convolutional CARMEN is illustrated in Figure 3(b).…”

Section: Application In Shwfsmentioning

confidence: 99%

“…(a) (b) Figure 3: (a) The architecture of the CARMEN MLP [34] . (b) The architecture of the Convolutional CARMEN [37] .…”

Section: Application In Shwfsmentioning

confidence: 99%

Review on intelligent wavefront reconstruction approaches for pyramid wavefront sensors

Cao,

Wang

2024

Sixth Conference on Frontiers in Optical Imaging and Technology: Novel Technologies in Optical Systems

View full text Add to dashboard Cite

In the adaptive optics system of large-aperture ground-based telescopes, the wavefront sensor plays a crucial role. Pyramid wavefront sensors are increasingly favored by an expanding number of world-class telescopes. However, traditional wavefront reconstruction algorithms with pyramid wavefront sensors have limited ability to fit nonlinearity, resulting in restricted improvement in reconstruction accuracy. The kernel of deep learning lies in the ability of artificial neural networks to approximate nonlinear functions with arbitrary precision, which is well-suited for solving the nonlinear wavefront reconstruction problem of pyramid wavefront sensors and achieving more accurate wavefront sensing. This paper introduces the application of deep learning in pyramid wavefront sensors and Shack-Hartmann wavefront sensors, conducts a comparative analysis between them, and discusses potential future research directions.

show abstract

“…To further improve the speed and accuracy of the above SHWS, DL technology can be used to solve the relationship between the SHWS focus spot, the Zernike polynomial and wavefront graph. In this study, we integrate CNN [3,4] with SHWS to solve the disadvantage above. The network is based on U-Net and constituted by several residual blocks, used to capture a variety of different features.…”

Section: Introductionmentioning

confidence: 99%

Model predictive control-based adaptive optics system with deep-learning Shack-Hartmann wavefront sensor

Huang,

Hsu,

Hsu

et al. 2023

Digital Optical Technologies 2023

View full text Add to dashboard Cite

Model predictive control (MPC) can use the state of the current measurement processing to predict future events and be able to take control processing accordingly. To implement MPC in our adaptive optics system (AOS), a multichannel state-space model is first identified between the driving voltage for a 61-channel deformable mirror (DM) as the input and the 8-order Zernike polynomial coefficients via a lab-made Shack-Hartmann wavefront sensor (SHWS) as the output. Conventionally, the center of weight algorithm is utilized to reconstruct the wavefront from SHWS, but it takes a lot of computation time. Therefore, a deep learning (DL) approach based on U-Net is adopted to rapid reconstruct the wavefront. The U-Net significantly reduces the time to compute the wavefront and also gets the higher accuracy. After that, the MPC controller based on the identified system model is implemented in AOS. Currently, the simulation results demonstrate that the MPC with the DL-SHWS can fast correct the wavefront aberration. Eventually, the MPC-based AOS will be implemented under Robot Operating System (ROS) to achieve real-time control.

show abstract

Improving Adaptive Optics Reconstructions with a Deep Learning Approach

Cited by 14 publications

References 16 publications

Convolutional Neural Networks Approach for Solar Reconstruction in SCAO Configurations

Convolutional Neural Networks Approach for Solar Reconstruction in SCAO Configurations

Review on intelligent wavefront reconstruction approaches for pyramid wavefront sensors

Model predictive control-based adaptive optics system with deep-learning Shack-Hartmann wavefront sensor

Contact Info

Product

Resources

About