Astronomical Images Research Articles

Multi-scale CLEAN for Fourier-based hard x-ray solar imaging

Abstract Multi-scale deconvolution is an ill-posed inverse problem in imaging, with applications ranging from microscopy, through medical imaging, to astronomical remote sensing. In the case of high-energy space telescopes, multi-scale deconvolution algorithms need to account for the peculiar property of native measurements, which are sparse samples of the Fourier transform of the incoming radiation. The present paper proposes a multi-scale version of CLEAN, which is the most popular iterative deconvolution method in Fourier-based astronomical imaging. Using synthetic data generated according to a simulated but realistic source configuration, we show that this multi-scale version of CLEAN performs better than the original one in terms of accuracy, photometry, and regularization. Further, the application to a data set measured by the NASA Reuven Ramaty High Energy Solar Spectroscopic Imager shows the ability of multi-scale CLEAN to reconstruct rather complex flaring topographies.

Point spread function deconvolution using a convolutional autoencoder

A major issue in optical astronomical image analysis is the combined effect of the instrument’s point spread function (PSF) and the atmospheric seeing that blurs images and changes their shape in a way that is band and time-of-observation dependent. In this work we present a very simple neural network based approach to nonblind image deconvolution that relies on feeding a convolutional autoencoder (CAE) input images that have been preprocessed by convolution with the corresponding PSF and its regularized inverse, a method which is both conceptually simple and computationally less intensive. We also present here, a new approach for dealing with limited input dynamic range of neural networks compared to the dynamic range present in astronomical images. Published by the American Physical Society 2024

Modeling and Estimation of Adaptive Optics-Corrected long-exposure Point Spread Function Using Gaussian Sum Approximation

Abstract Adaptive optics (AO) enhances astronomical images by correcting perturbations in the optical system, resulting in complex point spread function (PSF) shapes, which provide critical information for optical design, calibration, and diagnostics. This paper presents a parametric model for an AO-corrected long-exposure PSF that adapts to complex shapes and various seeing conditions. A complementary estimation method is also introduced, addressing the inverse problem of estimating the atmospheric PSF or power spectral density (PSD) from observed PSF data. The model, based on Gaussian sum approximation (GSA), was tested using simulated PSF data from the OOMAO toolbox for Fried parameter (r0) values ranging from 0.10 to 0.20 m and on-sky data from the Very Large Telescope’s MUSE instrument. Two approaches were analyzed: (i) direct PSF estimation using GSA, and (ii) PSF estimation derived from atmospheric PSD estimation. Both methods were evaluated using root mean square error (RMSE). While approach (i) provided the best performance, approach (ii) produced more accurate atmospheric PSF estimates compared to the Moffat approximation and the Fetick method. Additionally, approach (ii) enabled the estimation of key physical parameters, such as the Fried parameter (r0) and residual AO variance ($\sigma _{AO}^2$). The proposed methods effectively estimate atmospheric PSF and PSD, even for complex PSF shapes influenced by spiders, central obstructions, or static aberrations.

A model for suppressing stray light in astronomical images based on deep learning

Wide-Field Small Aperture Telescopes (WFSAT) are widely used for surveilling space objects. Due to their wide-field of view (FOV) characteristics, these telescopes can cover a large areas of the sky at once, improving observation efficiency. However, a wide-field optical telescope is highly sensitive to external stray light (such as moonlight and thin clouds), which can significantly reduce the quality of observation data. In severe cases, it can cause the telescope to malfunction and inaccurately position the object. In response to this problem, this paper proposes a model for suppressing stray light in astronomical images based on deep learning: the Pyramid Deformable Large Kernel Attention (PD-LKA) Model. This model expands the receptive field through a pyramid structure, captures multi-scale features, and improves the model’s robustness to various scales of stray light interference. Meanwhile, through the Deformable Large Kernel Attention (D-LKA), the model can more accurately locate and enhance the feature extraction ability in areas affected by stray light interference, thereby better suppressing stray light.Using simulated astronomical image pairs to train the model, the tests achieved a PSNR of up to 32.540 and an SSIM of up to 0.938. Finally, the model is applied to a image sequence with real stray light interference. The restored images undergo astronomical positioning and orbital association processing. The results show that the positioning accuracy of the object is better than 5 arcseconds. This indicates that the model proposed in this paper not only recovers the object and background stars but also effectively preserves their gray values, shapes, and positional information.

CoaddNet: Enhancing signal-to-noise ratio in single-shot images using convolutional neural networks with coadded image effect

Noise in astronomical images significantly impacts observations and analyses. Traditional denoising methods, such as increasing exposure time and image stacking, are limited when dealing with single-shot images or studying rapidly changing astronomical objects. To address this, we developed a novel deep-learning denoising model, CoaddNet, designed to improve the image quality of single-shot images and enhance the detection of faint sources. To train and validate the model, we constructed a dataset containing high and low signal-to-noise ratio (SNR) images, comprising coadded and single-shot types. CoaddNet combines the efficiency of convolutional operations with the advantages of the Transformer architecture, enhancing spatial feature extraction through a multi-branch structure and reparameterization techniques. Performance evaluation shows that CoaddNet surpasses the baseline model, NAFNet, by increasing the Peak Signal-to-Noise Ratio (PSNR) by 0.03 dB and the Structural Similarity Index (SSIM) by 0.005 while also improving throughput by 35.18%. The model significantly improves the SNR of single-shot images, with an average increase of 22.8, surpassing the noise reduction achieved by stacking 70-90 images. By boosting the SNR, CoaddNet significantly enhances the detection of faint sources, enabling SExtractor to detect an additional 22.88% of faint sources. Meanwhile, CoaddNet reduced the Mean Absolute Percentage Error (MAPE) of flux measurements for detected sources by at least 27.74%.

Lossy Compression of Integer Astronomical Images Preserving Photometric Properties* *This work was supported in part by the Spanish Ministry of Science and Innovation (MICINN) and by the European Regional Development Fund (FEDER), funded by MCIN/AEI/10.13039/501100011033/FEDER, UE, under grant PID2021-125258OB-I00; also by the Catalan Government under grant SGR2021-00643; and also by the “PhotSat” project under the Institute for Space Studies of

Observatories are producing astronomical image data at quickly increasing rates. As a result, the efficiency of the compression methods employed is critical to meet the storage and distribution requirements of both observatories and scientists. This paper presents a novel lossy compression technique that is able to preserve the results of photometry analysis with high fidelity while improving upon the state of the art in terms of compression performance. The proposed compression pipeline combines a flexible bi-region quantization scheme with the lossless, dictionary-based, LPAQ9M encoder. The quantization process allows compression performance and photometric fidelity to be precisely tailored to different scientific requirements. A representative data set of 16-bit integer astronomical images produced by telescopes from all around the world has been employed to empirically assess its compression-fidelity trade-offs, and compare them to those of the de facto standard Fpack compressor. In these experiments, the widespread SExtractor software is employed as the ground truth for photometric analysis. Results indicate that after lossy compression with our proposed method, the decompressed data allows consistent detection of over 99% of all astronomical objects for all tested telescopes, maintaining the highest photometric fidelity (as compared to state of the art lossy techniques). When compared to the best configuration of Fpack (Hcompress lossy using 1 quantization parameter) at similar compression rates, our proposed method provides better photometry precision: 7.15% more objects are detected with magnitude errors below 0.01, and 9.13% more objects with magnitudes below SExtractor’s estimated measurement error. Compared to the best lossless compression results, the proposed pipeline allows us to reduce the compressed data set volume by up to 38.75% and 27.94% while maintaining 90% and 95%, respectively, of the detected objects with magnitude differences lower than 0.01 mag; and up to 18.93% while maintaining 90% of the detected objects with magnitude differences lower than the photometric measure error.

At First Sight! Zero-shot Classification of Astronomical Images with Large Multimodal Models

Abstract Vision-Language multimodal Models (VLMs) offer the possibility for zero-shot classification in astronomy: i.e., classification via natural language prompts, with no training. We investigate two models, GPT-4o and LLaVA-NeXT, for zero-shot classification of low-surface brightness galaxies and artifacts, as well as morphological classification of galaxies. We show that with natural language prompts these models achieved significant accuracy (above 80% typically) without additional training/fine tuning. We discuss areas that require improvement, especially for LLaVA-NeXT, which is an open source model. Our findings aim to motivate the astronomical community to consider VLMs as a powerful tool for both research and pedagogy, with the prospect that future custom-built or fine-tuned models could perform better.

Denoising astronomical images using an enhanced Pix2Pix model

Astronomical images are frequently affected by sensor noise, which can negatively impact the accuracy of subsequent data analysis. To address this issue, this study proposes an enhanced Pix2Pix generative adversarial network model that incorporates Residual Blocks and Self-Attention mechanisms to improve denoising performance. The effectiveness of the proposed model is evaluated by comparing it with traditional denoising methods, standard Pix2Pix, Pix2Pix with Residual Blocks, and Pix2Pix with Self-Attention using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) metrics. The findings demonstrate that the Pix2Pix model, when combined with both Residual Blocks and Self-Attention, significantly outperforms other models in noise reduction and detail preservation. This improved approach offers a robust solution for high-quality processing of astronomical images, providing clearer and more reliable data for scientific analysis. The results highlight the potential of advanced deep learning techniques in overcoming the challenges posed by sensor noise in astronomical imaging.

Intensity-sensitive Quality Assessment of Extended Sources in Astronomical Images

Radio astronomy studies the Universe by observing the radio emissions of celestial bodies. Different methods can be used to recover the sky brightness distribution (SBD), which describes the distribution of celestial sources from recorded data, with the output dependent on the method used. Image quality assessment (IQA) indexes can be used to compare the differences between restored SBDs produced by different image reconstruction techniques to evaluate their effectiveness. However, reconstructed images (for the same SBD) can appear to be very similar, especially when observed by the human visual system (HVS). Hence, current structural similarity methods, inspired by the HVS, are not effective. In the past, we have proposed two methods to assess point-source images, where low amounts of concentrated information are present in larger regions of noise-like data. But for images that include extended source(s), the increase in complexity of the structure makes the IQA methods for point sources oversensitive because the important objects cannot be described by isolated point sources. Therefore, in this article we propose the augmented low-information similarity index (augLISI), an improved version of LISI, to assess images including extended source(s). Experiments have been carried out to illustrate how this new IQA method can help with the development and study of astronomical imaging techniques. Note that although we focus on radio astronomical images herein, these IQA methods are also applicable to other astronomical images and imaging techniques.

Self-supervised learning on MeerKAT wide-field continuum images

Context. Self-supervised learning (SSL) applied to natural images has demonstrated a remarkable ability to learn meaningful, low-dimension representations without labels, resulting in models that are adaptable to many different tasks. Until now, applications of SSL to astronomical images have been limited to Galaxy Zoo datasets, which require a significant amount of preprocessing to prepare sparse images centered on a single galaxy. With wide-field survey instruments at the forefront of the Square Kilometer Array (SKA) era, this approach to gathering training data is impractical. Aims. We demonstrate that continuum images from surveys such as the MeerKAT Galactic Cluster Legacy Survey (MGCLS) can be successfully used with SSL, without extracting single-galaxy cutouts. Methods. Using the SSL framework DINO, we experimented with various preprocessing steps, augmentations, and architectures to determine the optimal approach for this data. We trained both ResNet50 and Vision Transformer (ViT) backbones. Results. Our models match state-of-the-art results (trained on Radio Galaxy Zoo) for FRI/FRII morphology classification. Furthermore, they predict the number of compact sources via linear regression with much higher accuracy. Open-source foundation models trained on natural images such as DINOv2 also excel at simple FRI/FRII classification; the advantage of domain-specific backbones is much smaller models trained on far less data. Smaller models are more efficient to fine-tune, and doing so results in a similar performance between our models, the state-of-the-art, and open-source models on multi-class morphology classification. Conclusions. Using source-rich crops from wide-field images to train multi-purpose models is an easily scalable approach that significantly reduces data preparation time. For the tasks evaluated in this work, twenty thousand crops is sufficient training data for models that produce results similar to state-of-the-art. In the future, complex tasks like source detection and characterization, together with domain-specific tasks, ought to demonstrate the true advantages of training models with radio astronomy data over natural-image foundation models.

YOLO-CIANNA: Galaxy detection with deep learning in radio data

Context. The upcoming Square Kilometer Array (SKA) will set a new standard regarding data volume generated by an astronomical instrument, which is likely to challenge widely adopted data-analysis tools that scale inadequately with the data size. Aims. The aim of this study is to develop a new source detection and characterization method for massive radio astronomical datasets based on modern deep-learning object detection techniques. For this, we seek to identify the specific strengths and weaknesses of this type of approach when applied to astronomical data. Methods. We introduce YOLO-CIANNA, a highly customized deep-learning object detector designed specifically for astronomical datasets. In this paper, we present the method and describe all the elements introduced to address the specific challenges of radio astronomical images. We then demonstrate the capabilities of this method by applying it to simulated 2D continuum images from the SKA observatory Science Data Challenge 1 (SDC1) dataset. Results. Using the SDC1 metric, we improve the challenge-winning score by +139% and the score of the only other post-challenge participation by +61%. Our catalog has a detection purity of 94% while detecting 40–60% more sources than previous top-score results, and exhibits strong characterization accuracy. The trained model can also be forced to reach 99% purity in post-process and still detect 10–30% more sources than the other top-score methods. It is also computationally efficient, with a peak prediction speed of 500 images of 512×512 pixels per second on a single GPU. Conclusions. YOLO-CIANNA achieves state-of-the-art detection and characterization results on the simulated SDC1 dataset and is expected to transfer well to observational data from SKA precursors.

Joint Deconvolution of Astronomical Images in the Presence of Poisson Noise

We present a new framework for joint likelihood deconvolution (Jolideco) of a set of astronomical observations of the same sky region in the presence of Poisson noise. The observations may be obtained from different instruments with different resolution, and different point-spread functions (PSFs). Jolideco reconstructs a single flux image by optimizing the posterior distribution based on the joint Poisson likelihood of all observations under one of several prior distributions. Most notably, we employ a patch-based image prior that is parameterized via a Gaussian mixture model, which we train on high-signal-to-noise astronomical images, including data from the JWST and the GLEAM radio survey. This prior favors correlation structures among the reconstructed pixel intensities that are characteristic of those observed in the training images. It is, however, not informative for the mean or scale of the reconstruction. By applying the method to simulated data, we show that the combination of multiple observations and the patch-based prior leads to much improved reconstruction quality in many different source scenarios and signal-to-noise regimes. We demonstrate that with the patch prior Jolideco yields superior reconstruction quality relative to alternative standard methods such as the Richardson–Lucy method. We illustrate the results of Jolideco applied to example data from the Chandra X-ray Observatory and the Fermi Gamma-ray Space Telescope. By comparing the measured width of a counts-based and the corresponding Jolideco flux profile of an X-ray filament in SNR 1E 0102.2–7219, we find the deconvolved width of 0.″58 ± 0.″02 to be consistent with the theoretical expectation derived from the known width of the PSF.

Pathfinding Pulsar Observations with the CVN Incorporating the FAST

Abstract The importance of Very Long Baseline Interferometry (VLBI) for pulsar research is becoming increasingly prominent and receiving more and more attention. We present the pathfinding pulsar observation results with the Chinese VLBI Network (CVN) incorporating the Five-hundred-meter Aperture Spherical radio Telescope (FAST). On MJD 60045 (11th April 2023), PSRs B0919+06 and B1133+16 were observed with the phase-referencing mode in the L-band using four radio telescopes (FAST, TianMa, Haoping, and Nanshan) and correlated with the pulsar binning mode of the distributed FX-style software correlator in Shanghai. After further data processing with the NRAO Astronomical Image Processing System (AIPS), we detected these two pulsars and fitted their current positions with accuracy at the milliarcsecond level. By comparison, our results show significantly better agreement with predicted values based on historical VLBI observations than those with previous timing observations, as pulsar astrometry with the VLBI provides a more direct and model-independent method for accurately obtaining related parameters.

Blind deblurring of astronomical images using a SCGTV-based single-frame method

Atmospheric turbulence often distorts space target imaging, leading to degraded image quality. To address the issue of image quality degradation, various hardware and software approaches have been proposed, including adaptive optics, lucky imaging, and blind deconvolution. Traditional astronomical image deblurring algorithms rely on information from multiple frames, requiring extensive processing time and computational resources. This study introduces the saturation-corrected graph total variation (SCGTV) method to address low signal-to-noise ratio and pixel saturation in single-frame astronomical image deblurring. This method effectively minimizes the influence of atmospheric turbulence and noise by leveraging a reweighted graph total variation prior. Saturation correction and dark channel information are integrated in SCGTV to enhance resolution and reduce artifacts. The SCGTV method is well-designed for astronomical scenarios, successfully deblurring real-world astronomical images and demonstrating superior performance on thirty simulated dataset compared to other algorithms. Quantitative evaluations on artificially blurred datasets demonstrate that SCGTV outperforms existing methods. These enhancements provide significant benefits for astronomical observation and analysis.

Improving supernova detection by using YOLOv8 for astronomical image analysis

Improving supernova detection by using YOLOv8 for astronomical image analysis

Application of Neural Networks to Searching for Optical Transients in Astronomical Images Using the Subtraction Method

Application of Neural Networks to Searching for Optical Transients in Astronomical Images Using the Subtraction Method

Novel Conjugate Gradient Methods for Image Restoration

The image restoration problem can be solved with the right techniques and tools. Although the quality of images may be lowered throughout the data collecting procedure, there are ways to do so. Clarity may be enhanced as a result of the procedure. It is the goal of image restoration to restore the original image from the damaged data. Here are some examples of applications in forensic research, picture restoration, medical imaging, astronomical imaging, and more. It can be advantageous to enhance image quality as much as possible, which justifies the expense and difficulty of the restoration methods. The conjugate gradient method is a numerical optimization technique that places emphasis on the conjugate of the coefficient in order to determine the optimal solution. The current study introduces a novel quadratic function-based coefficient conjugate gradient methodology for the removal of impulse noise from pictures. Global convergence has been shown to occur with the suggested method. The numerical results indicate that the proposed methods have high efficiency and global convergence in image restoration problems compared to the Fletcher-Reevess (FR) method.

Deeper, Sharper, Faster: Application of Efficient Transformer to Galaxy Image Restoration

The Transformer architecture has revolutionized the field of deep learning over the past several years in diverse areas, including natural language processing, code generation, image recognition, and time-series forecasting. We propose to apply Zamir et al.'s efficient transformer to perform deconvolution and denoising to enhance astronomical images. We conducted experiments using pairs of high-quality images and their degraded versions, and our deep learning model demonstrates exceptional restoration of photometric, structural, and morphological information. When compared with the ground-truth James Webb Space Telescope images, the enhanced versions of our Hubble Space Telescope–quality images reduce the scatter of isophotal photometry, Sérsic index, and half-light radius by factors of 4.4, 3.6, and 4.7, respectively, with Pearson correlation coefficients approaching unity. The performance is observed to degrade when input images exhibit correlated noise, point-like sources, and artifacts. We anticipate that this deep learning model will prove valuable for a number of scientific applications, including precision photometry, morphological analysis, and shear calibration.

AstroSR: A Data Set of Galaxy Images for Astronomical Superresolution Research

In the past decade, various sky surveys with a wide range of wavelengths have been conducted, resulting in an explosive growth of survey data. There may be overlapping regions between different surveys, but the data quality and brightness are different. The translation of data quality between different surveys provides benefits for studying the properties of galaxies in specific regions that high-quality surveys have not yet covered. In this paper, we create a data set for analyzing the quality transformation of different surveys, AstroSR, using the galaxy images from overlapping regions from the Subaru/Hyper Suprime-Cam (HSC) and the Sloan Digital Sky Survey (SDSS). In addition, we use superresolution (SR) techniques to improve the quality of low-resolution images in the AstroSR and explore whether the proposed data set is suitable for SR. We try four representative models: EDSR, RCAN, ENLCN, and SRGAN. Finally, we compare the evaluation metrics and visual quality of the above methods. SR models trained with AstroSR successfully generate HSC-like images from SDSS images, which enhance the fine structure present in the SDSS images while retaining important morphological information and increasing the brightness and signal-to-noise. Improving the resolution of astronomical images by SR can improve the size and quality of the sky surveys. The data set proposed in this paper provides strong data support for the study of galaxy SR and opens up new research possibilities in astronomy. The data set is available online at https://github.com/jiaweimmiao/AstroSR.

Meta Shack–Hartmann wavefront sensor with large sampling density and large angular field of view: phase imaging of complex objects

Shack–Hartmann wavefront sensors measure the local slopes of an incoming wavefront based on the displacement of focal spots created by a lenslet array, serving as key components for adaptive optics for astronomical and biomedical imaging. Traditionally, the challenges in increasing the density and the curvature of the lenslet have limited the use of such wavefront sensors in characterizing slowly varying wavefront structures. Here, we develop a metasurface-enhanced Shack–Hartmann wavefront sensor (meta SHWFS) to break this limit, considering the interplay between the lenslet parameters and the performance of SHWFS. We experimentally validate the meta SHWFS with a sampling density of 5963 per mm2 and a maximum acceptance angle of 8° which outperforms the traditional SFWFS by an order of magnitude. Furthermore, to the best of our knowledge, we demonstrate the first use of a wavefront sensing scheme in single-shot phase imaging of highly complex patterns, including biological tissue patterns. The proposed approach opens up new opportunities in incorporating exceptional light manipulation capabilities of the metasurface platform in complex wavefront characterization.