Multi-scale deep learning for estimating horizontal velocity fields on the solar surface

Abstract

Context. The dynamics in the photosphere is governed by the multi-scale turbulent convection termed as granulation and supergranulation. It is important to derive three-dimensional velocity vectors to understand the nature of the turbulent convection and to evaluate the vertical Poynting flux toward the upper atmosphere. The line-of-sight component of the velocity can be obtained by observing the Doppler shifts. However, it is difficult to obtain the velocity component perpendicular to the line of sight, which corresponds to the horizontal velocity in disk center observations. Aims. We present a new method based on a deep neural network that can estimate the horizontal velocity from the spatial and temporal variations of the intensity and vertical velocity. We suggest a new measure for examining the performance of the method. Methods. We developed a convolutional neural network model with a multi-scale deep learning architecture. The method consists of multiple convolutional kernels with various sizes of receptive fields, and performs convolution for spatial and temporal axes. The network is trained with data from three different numerical simulations of turbulent convection. Furthermore, we introduced a novel coherence spectrum to assess the horizontal velocity fields that were derived for each spatial scale. Results. The multi-scale deep learning method successfully predicts the horizontal velocities for each convection simulation in terms of the global correlation coefficient, which is often used to evaluate the prediction accuracy of the methods. The coherence spectrum reveals the strong dependence of the correlation coefficients on the spatial scales. Although the coherence spectra are higher than 0.9 for large-scale structures, they drastically decrease to less than 0.3 for small-scale structures, wherein the global correlation coefficient indicates a high value of approximately 0.95. By comparing the results of the three convection simulations, we determined that this decrease in the coherence spectrum occurs around the energy injection scales, which are characterized by the peak of the power spectra of the vertical velocities. Conclusions. The accuracy for the small-scale structures is not guaranteed solely by the global correlation coefficient. To improve the accuracy on small scales, it is important to improve the loss function for enhancing the small-scale structures and to utilize other physical quantities related to the nonlinear cascade of convective eddies as input data.

A Comparison of Velocimetry Algorithms: Orthogonal Dynamic Programming Based Particle Image Velocimetry Versus Local Correlation Tracking

“…A trial use of LCT-Flowmaker with fusion plasma data will be performed in future. In addition, a deep learning based velocity field estimation technique has recently been developed [24]. An application of this approach to magnetic plasma fusion data is also underway.…”

Quantifying Poynting Flux in the Quiet Sun Photosphere

“…This, then, presents a clear avenue for improvement, particularly when DKIST observations with higher spatial resolution (down to 0 03; Rimmele et al 2020) become available, since features in IGLs are especially vulnerable to resolution effects. Another way to improve the neural network approach is to train it to match coherence spectra, i.e., to match velocities at different frequencies in the Fourier space, as was done in Ishikawa et al (2022).…”

Formulating Mass-loss Rates for Sun-like Stars: A Hybrid Model Approach

“…We utilize a larger λ ⊥,* value than that commonly applied in past studies (∼150 km, Cranmer & Saar 2011;Shoda et al 2020;Shoda & Takasao 2021). This is attributed to the energy-containing scale in the horizontal velocity field of the photosphere resembling the granular scale (∼1000 km; Matsumoto & Shibata 2010;Ishikawa et al 2022). Given that the larger convective structures persist to higher altitudes (Kostik et al 2009), the granular scale is expected to be greater in the upper atmosphere.…”