Compensating atmospheric turbulence with CNNs for defocused pupil image wavefront sensors

2020 ◽  
Author(s):  
Sergio Luis Suárez Gómez ◽  
Carlos González-Gutiérrez ◽  
Juan Díaz Suárez ◽  
Juan José Fernández Valdivia ◽  
José Manuel Rodríguez Ramos ◽  
...  
Keyword(s):  
Neural Networks ◽  
Adaptive Optics ◽  
Structural Similarity ◽  
Detailed Comparison ◽  
Optical Measurements ◽  
Wavefront Sensors ◽  
Machine Learning Model ◽  
Reconstruction Software ◽  
Astronomical Images ◽  
Zernike Modes

Abstract Adaptive optics are techniques used for processing the spatial resolution of astronomical images taken from large ground-based telescopes. In this work, computational results are presented for a modified curvature sensor, the tomographic pupil image wavefront sensor (TPI-WFS), which measures the turbulence of the atmosphere, expressed in terms of an expansion over Zernike polynomials. Convolutional neural networks (CNN) are presented as an alternative to the TPI-WFS reconstruction. This technique is a machine learning model of the family of artificial neural networks, which are widely known for its performance as modeling and prediction technique in complex systems. Results obtained from the reconstruction of the networks are compared with the TPI-WFS reconstruction by estimating errors and optical measurements (root mean square error, mean structural similarity and Strehl ratio). The reconstructed wavefronts from both techniques are compared for wavefronts of 153 Zernike modes. For this case, a detailed comparison and grid search to find the most suitable neural network is performed, searching between multi-layer perceptron, CNN and recurrent networks topologies. In general, the best network was a CNN trained for TPI-WFS reconstruction, achieving better performance than the reconstruction software from TPI-WFS in most of the turbulent profiles, but the most significant improvements were found for higher turbulent profiles that have the lowest r0 values.

scholarly journals Defocused Image Deep Learning Designed for Wavefront Reconstruction in Tomographic Pupil Image Sensors

Mathematics ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 15
Author(s):  
Sergio Luis Suárez Gómez ◽  
Francisco García Riesgo ◽  
Carlos González Gutiérrez ◽  
Luis Fernando Rodríguez Ramos ◽  
Jesús Daniel Santos
Keyword(s):  
Neural Networks ◽  
Adaptive Optics ◽  
Convolutional Neural Networks ◽  
Image Sensors ◽  
Wavefront Reconstruction ◽  
Least Squares Fit ◽  
Astronomical Images ◽  
Defocused Image ◽  
Zernike Modes ◽  
Modelling Methods

Mathematical modelling methods have several limitations when addressing complex physics whose calculations require considerable amount of time. This is the case of adaptive optics, a series of techniques used to process and improve the resolution of astronomical images acquired from ground-based telescopes due to the aberrations introduced by the atmosphere. Usually, with adaptive optics the wavefront is measured with sensors and then reconstructed and corrected by means of a deformable mirror. An improvement in the reconstruction of the wavefront is presented in this work, using convolutional neural networks (CNN) for data obtained from the Tomographic Pupil Image Wavefront Sensor (TPI-WFS). The TPI-WFS is a modified curvature sensor, designed for measuring atmospheric turbulences with defocused wavefront images. CNNs are well-known techniques for its capacity to model and predict complex systems. The results obtained from the presented reconstructor, named Convolutional Neural Networks in Defocused Pupil Images (CRONOS), are compared with the results of Wave-Front Reconstruction (WFR) software, initially developed for the TPI-WFS measurements, based on the least-squares fit. The performance of both reconstruction techniques is tested for 153 Zernike modes and with simulated noise. In general, CRONOS showed better performance than the reconstruction from WFR in most of the turbulent profiles, with significant improvements found for the most turbulent profiles; overall, obtaining around 7% of improvements in wavefront restoration, and 18% of improvements in Strehl.

scholarly journals Fully Convolutional Approaches for Numerical Approximation of Turbulent Phases in Solar Adaptive Optics

Mathematics ◽  
2021 ◽  
Vol 9 (14) ◽  
pp. 1630
Author(s):  
Francisco García Riesgo ◽  
Sergio Luis Suárez Gómez ◽  
Enrique Díez Alonso ◽  
Carlos González-Gutiérrez ◽  
Jesús Daniel Santos
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
High Altitude ◽  
Adaptive Optics ◽  
Numerical Approximation ◽  
Reconstruction Algorithms ◽  
Wavefront Sensors ◽  
Night Time ◽  
Phase Recovery ◽  
Fully Convolutional Neural Networks

Information on the correlations from solar Shack–Hartmann wavefront sensors is usually used for reconstruction algorithms. However, modern applications of artificial neural networks as adaptive optics reconstruction algorithms allow the use of the full image as an input to the system intended for estimating a correction, avoiding approximations and a loss of information, and obtaining numerical values of those correlations. Although studied for night-time adaptive optics, the solar scenario implies more complexity due to the resolution of the solar images potentially taken. Fully convolutional neural networks were the technique chosen in this research to address this problem. In this work, wavefront phase recovery for adaptive optics correction is addressed, comparing networks that use images from the sensor or images from the correlations as inputs. As a result, this research shows improvements in performance for phase recovery with the image-to-phase approach. For recovering the turbulence of high-altitude layers, up to 93% similarity is reached.

scholarly journals Synthetic neural-like computing in microbial consortia for pattern recognition

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Ximing Li ◽  
Luna Rizik ◽  
Valeriia Kravchik ◽  
Maria Khoury ◽  
Netanel Korin ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Gradient Descent ◽  
Biological Systems ◽  
Logic Gates ◽  
Structural Similarity ◽  
Microbial Consortia ◽  
Promoter Strength ◽  
Chemical Inducers ◽  
Artificial Neural

AbstractComplex biological systems in nature comprise cells that act collectively to solve sophisticated tasks. Synthetic biological systems, in contrast, are designed for specific tasks, following computational principles including logic gates and analog design. Yet such approaches cannot be easily adapted for multiple tasks in biological contexts. Alternatively, artificial neural networks, comprised of flexible interactions for computation, support adaptive designs and are adopted for diverse applications. Here, motivated by the structural similarity between artificial neural networks and cellular networks, we implement neural-like computing in bacteria consortia for recognizing patterns. Specifically, receiver bacteria collectively interact with sender bacteria for decision-making through quorum sensing. Input patterns formed by chemical inducers activate senders to produce signaling molecules at varying levels. These levels, which act as weights, are programmed by tuning the sender promoter strength Furthermore, a gradient descent based algorithm that enables weights optimization was developed. Weights were experimentally examined for recognizing 3 × 3-bit pattern.

scholarly journals Generation of geometric interpolations of building types with deep variational autoencoders

2020 ◽  
Vol 6 ◽  
Author(s):  
Jaime de Miguel Rodríguez ◽  
Maria Eugenia Villafañe ◽  
Luka Piškorec ◽  
Fernando Sancho Caparrini
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Large Data ◽  
Learning Model ◽  
Large Data Sets ◽  
Data Sets ◽  
Connectivity Map ◽  
Data Set ◽  
3D Objects ◽  
Machine Learning Model

Abstract This work presents a methodology for the generation of novel 3D objects resembling wireframes of building types. These result from the reconstruction of interpolated locations within the learnt distribution of variational autoencoders (VAEs), a deep generative machine learning model based on neural networks. The data set used features a scheme for geometry representation based on a ‘connectivity map’ that is especially suited to express the wireframe objects that compose it. Additionally, the input samples are generated through ‘parametric augmentation’, a strategy proposed in this study that creates coherent variations among data by enabling a set of parameters to alter representative features on a given building type. In the experiments that are described in this paper, more than 150 k input samples belonging to two building types have been processed during the training of a VAE model. The main contribution of this paper has been to explore parametric augmentation for the generation of large data sets of 3D geometries, showcasing its problems and limitations in the context of neural networks and VAEs. Results show that the generation of interpolated hybrid geometries is a challenging task. Despite the difficulty of the endeavour, promising advances are presented.

scholarly journals Successful application of PSF-R techniques to the case of the globular cluster NGC 6121 (M 4)

2020 ◽  
Vol 634 ◽  
pp. L5 ◽  
Author(s):  
D. Massari ◽  
A. Marasco ◽  
O. Beltramo-Martin ◽  
J. Milli ◽  
G. Fiorentino ◽  
...  
Keyword(s):  
Adaptive Optics ◽  
Globular Cluster ◽  
Hybrid Technique ◽  
Large Telescope ◽  
Point Spread ◽  
Accurate Knowledge ◽  
Viable Solution ◽  
Spread Function ◽  
Astronomical Images ◽  
Proper Analysis

Context. Precise photometric and astrometric measurements on astronomical images require an accurate knowledge of the point spread function (PSF). When the PSF cannot be modelled directly from the image, PSF-reconstruction techniques become the only viable solution. So far, however, their performance on real observations has rarely been quantified. Aims. In this Letter, we test the performance of a novel hybrid technique, called PRIME, on Adaptive Optics-assisted SPHERE/ZIMPOL observations of the Galactic globular cluster NGC 6121. Methods. PRIME couples PSF-reconstruction techniques, based on control-loop data and direct image fitting performed on the only bright point-like source available in the field of view of the ZIMPOL exposures, with the aim of building the PSF model. Results. By exploiting this model, the magnitudes and positions of the stars in the field can be measured with an unprecedented precision, which surpasses that obtained by more standard methods by at least a factor of four for on-axis stars and by up to a factor of two on fainter, off-axis stars. Conclusions. Our results demonstrate the power of PRIME in recovering precise magnitudes and positions when the information directly coming from astronomical images is limited to only a few point-like sources and, thus, paving the way for a proper analysis of future Extremely Large Telescope observations of sparse stellar fields or individual extragalactic objects.

scholarly journals Multiconjugate Adaptive Optics for Astronomy

2018 ◽  
Vol 56 (1) ◽  
pp. 277-314 ◽  
Author(s):  
François Rigaut ◽  
Benoit Neichel
Keyword(s):  
Adaptive Optics ◽  
Near Infrared ◽  
Phase Reconstruction ◽  
Large Telescope ◽  
Wavefront Sensors ◽  
Error Sources ◽  
New Concepts ◽  
Year 2000 ◽  
Current Systems ◽  
Solar Astronomy

Since the year 2000, adaptive optics (AO) has seen the emergence of a variety of new concepts addressing particular science needs; multiconjugate adaptive optics (MCAO) is one of them. By correcting the atmospheric turbulence in 3D using several wavefront sensors and a tomographic phase reconstruction approach, MCAO aims to provide uniform diffraction limited images in the near-infrared over fields of view larger than 1 arcmin2, i.e., 10 to 20 times larger in area than classical single conjugated AO. In this review, we give a brief reminder of the AO principles and limitations, and then focus on aspects particular to MCAO, such as tomography and specific MCAO error sources. We present examples and results from past or current systems: MAD (Multiconjugate Adaptive Optics Demonstrator) and GeMS (Gemini MCAO System) for nighttime astronomy and the AO system, at Big Bear for solar astronomy. We examine MCAO performance (Strehl ratio up to 40% in H band and full width at half maximum down to 52 mas in the case of MCAO), with a particular focus on photometric and astrometric accuracy, and conclude with considerations on the future of MCAO in the Extremely Large Telescope and post–HST era.

scholarly journals On-sky correction of non-common path aberration with the pyramid wavefront sensor

2020 ◽  
Vol 636 ◽  
pp. A88 ◽  
Author(s):  
S. Esposito ◽  
A. Puglisi ◽  
E. Pinna ◽  
G. Agapito ◽  
F. Quirós-Pacheco ◽  
...  
Keyword(s):  
Adaptive Optics ◽  
Critical Issue ◽  
Wavefront Sensor ◽  
Interaction Matrix ◽  
Scientific Instrument ◽  
Wavefront Sensors ◽  
Successful Operation ◽  
Optical Elements ◽  
Common Path ◽  
External Conditions

The paper deals with with the on-sky performance of the pyramid wavefront sensor-based Adaptive Optics (AO) systems. These wavefront sensors are of great importance, being used in all first light AO systems of the ELTs (E-ELT, GMT, and TMT), currently in design phase. In particular, non-common path aberrations (NCPAs) are a critical issue encountered when using an AO system to produce corrected images in an associated astronomical instrument. The AO wavefront sensor (WFS) and the supported scientific instrument typically use a series of different optical elements, thus experiencing different aberrations. The usual way to correct for such NCPAs is to introduce a static offset in the WFS signals. In this way, when the AO loop is closed the sensor offsets are zeroed and the deformable mirror converges to the shape required to null the NCPA. The method assumes that the WFS operation is linear and completely described by some pre-calibrated interaction matrix. This is not the case for some frequently used wavefront sensors like the Pyramid sensor or a quad-cell Shack-Hartmann sensor. Here we present a method to work in closed-loop with a pyramid wavefront sensor, or more generally a non-linear WFS, introducing a wavefront offset that remains stable when AO correction quality changes due to variations in external conditions like star brightness, seeing, and wind speed. The paper details the methods with analytical and numerical considerations. Then we present results of tests executed at the LBT telescope, in daytime and on sky, using the FLAO system and LUCI2 facility instrument. The on-sky results clearly show the successful operation of the method that completely nulls NCPA, recovering diffraction-limited images with about 70% Strehl ratio in H band in variable seeing conditions. The proposed method is suitable for application to the above-mentioned ELT AO systems.

Sign in / Sign up

Export Citation Format

Share Document