- Award ID(s):
- 1821294
- NSF-PAR ID:
- 10406089
- Date Published:
- Journal Name:
- The Astrophysical Journal Supplement Series
- Volume:
- 263
- Issue:
- 2
- ISSN:
- 0067-0049
- Page Range / eLocation ID:
- 25
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
Abstract In recent years, the new physics of the Sun has been revealed using advanced data with high spatial and temporal resolutions. The Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamic Observatory has accumulated abundant observation data for the study of solar activity with sufficient cadence, but their spatial resolution (about 1″) is not enough to analyze the subarcsecond structure of the Sun. On the other hand, high-resolution observation from large-aperture ground-based telescopes, such as the 1.6 m Goode Solar Telescope (GST) at the Big Bear Solar Observatory, can achieve a much higher resolution on the order of 0.″1 (about 70 km). However, these high-resolution data only became available in the past 10 yr, with a limited time period during the day and with a very limited field of view. The Generative Adversarial Network (GAN) has greatly improved the perceptual quality of images in image translation tasks, and the self-attention mechanism can retrieve rich information from images. This paper uses HMI and GST images to construct a precisely aligned data set based on the scale-invariant feature transform algorithm and t0 reconstruct the HMI continuum images with four times better resolution. Neural networks based on the conditional GAN and self-attention mechanism are trained to restore the details of solar active regions and to predict the reconstruction error. The experimental results show that the reconstructed images are in good agreement with GST images, demonstrating the success of resolution improvement using machine learning.more » « less
-
Improving spatial resolution of sunspot HMI images using conditional generative adversarial networksSolar Dynamics Observatory (SDO) spacecraft as a space-based project is able to conduct continuous monitoring of the Sun. The Helioseismic and Magnetic Imager (HMI) instrument on SDO, in particular, provides continuum images and magnetograms with a cadence of under 1 minute. SDO/HMI's spatial resolution is only about 1'', which makes it impossible to perform a good analysis on the subarcsecond scale. On the other hand, larger aperture ground-based telescopes such as the Goode Solar Telescope (GST) at the Big Bear Solar Observatory are able to achieve a better resolution (16 times better than SDO/HMI). However, ground-based telescopes like GST have limitations in terms of observation time, which can only make observations during the day in clearsky condition. The purpose of this study is to make attempts in improving the spatial resolution of images captured by HMI beyond the diffraction limit of the telescope by employing the Conditional Generative Adversarial Networks algorithm (cGAN). The cGAN model was trained using 1800 pairs of HMI and GST sunspot images. This method successfully reconstruct HMI images with a spatial resolution close to GST images, this is supported by \raisebox{-0.5ex}\textasciitilde62\% increase in the peak signal-to-noise ratio (PSNR) value and \raisebox{-0.5ex}\textasciitilde90\% decrease in the mean squared error (MSE) value. The higher resolution sunspot images produced by this model can be useful for further Solar Physics studies.more » « less
-
Super-resolution (SR) is a well-studied technique for reconstructing high-resolution (HR) images from low-resolution (LR) ones. SR holds great promise for video streaming since an LR video segment can be transmitted from the video server to the client that then reconstructs the HR version using SR, resulting in a significant reduction in network bandwidth. However, SR is seldom used in practice for real-time video streaming, because the computational overhead of frame reconstruction results in large latency and low frame rate. To reduce the computational overhead and make SR practical, we propose a deep-learning-based SR method called Fo veated Cas caded Video Super Resolution (focas). focas relies on the fact that human eyes only have high acuity in a tiny central foveal region of the retina. focas uses more neural network blocks in the foveal region to provide higher video quality, while using fewer blocks in the periphery as lower quality is sufficient. To optimize the computational resources and reduce reconstruction latency, focas formulates and solves a convex optimization problem to decide the number of neural network blocks to use in each region of the frame. Using extensive experiments, we show that focas reduces the latency by 50%-70% while maintaining comparable visual quality as traditional (non-foveated) SR. Further, focas provides a 12-16x reduction in the client-to-server network bandwidth in comparison with sending the full HR video segments.more » « less
-
Abstract—Numerical simulation of weather is resolution-constrained due to the high computational cost of integrating the coupled PDEs that govern atmospheric motion. For example, the most highly-resolved numerical weather prediction models are limited to approximately 3 km. However many weather and climate impacts occur over much finer scales, especially in urban areas and regions with high topographic complexity like mountains or coastal regions. Thus several statistical methods have been developed in the climate community to downscale numerical model output to finer resolutions. This is conceptually similar to image super-resolution (SR) [1] and in this work we report the results of applying SR methods to the downscaling problem. In particular we test the extent to which a SR method based on a Generative Adversarial Network (GAN) can recover a grid of wind speed from an artificially downsampled version, compared against a standard bicubic upsampling approach and another machine learning based approach, SR-CNN [1]. We use ESRGAN ([2]) to learn to downscale wind speeds by a factor of 4 from a coarse grid. We find that we can recover spatial details with higher fidelity than bicubic upsampling or SR-CNN. The bicubic and SR-CNN methods perform better than ESRGAN on coarse metrics such as MSE. However, the high frequency power spectrum is captured remarkably well by the ESRGAN, virtually identical to the real data, while bicubic and SR-CNN fidelity drops significantly at high frequency. This indicates that SR is considerably better at matching the higher-order statistics of the dataset, consistent with the observation that the generated images are of superior visual quality compared with SR-CNN.more » « less
-
Abstract The first significant sunquake event of Solar Cycle 25 was observed during the X1.5 flare of 2022 May 10, by the Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamics Observatory. We perform a detailed spectro-polarimetric analysis of the sunquake photospheric sources, using the Stokes profiles of the Fe
i 6173 Å line, reconstructed from the HMI linear and circular polarized filtergrams. The results show fast variations of the continuum emission with rapid growth and slower decay lasting 3–4 minutes, coinciding in time with the hard X-ray impulses observed by the Konus instrument on board the Wind spacecraft. The variations in the line core appeared slightly ahead of the variations in the line wings, showing that the heating started in the higher atmospheric layers and propagated downward. The most significant feature of the line profile variations is the transient emission in the line core in three of the four sources, indicating intense, impulsive heating in the lower chromosphere and photosphere. In addition, the observed variations of the Stokes profiles reflect transient and permanent changes in the magnetic field strength and geometry in the sunquake sources. Comparison with the radiative hydrodynamics models shows that the physical processes in the impulsive flare phase are substantially more complex than those predicted by proton and electron beam flare models currently presented in the literature.