Spectropolarimetric Inversion in Four Dimensions with Deep Learning (SPIn4D): I. Overview, Magnetohydrodynamic Modeling, and Stokes Profile Synthesis

Abstract

The National Science Foundation's Daniel K. Inouye Solar Telescope (DKIST) will provide high-resolution, multi-line spectropolarimetric observations that are poised to revolutionize our understanding of the Sun. Given the massive data volume, novel inference techniques are required to unlock its full potential. Here, we provide an overview of our "SPIn4D" project, which aims to develop deep convolutional neural networks (CNNs) for estimating the physical properties of the solar photosphere from DKIST spectropolarimetric observations. We describe the magnetohydrodynamic (MHD) modeling and the Stokes profile synthesis pipeline that produce the simulated output and input data, respectively. These data will be used to train a set of CNNs that can rapidly infer the four-dimensional MHD state vectors by exploiting the spatiotemporally coherent patterns in the Stokes profile time series. Specifically, our radiative MHD model simulates the small-scale dynamo actions that are prevalent in quiet-Sun and plage regions. Six cases with different mean magnetic fields have been conducted; each case covers six solar-hours, totaling 109 TB in data volume. The simulation domain covers at least $25\times 25\times 8$ Mm with $16\times 16\times 12$ km spatial resolution, extending from the upper convection zone up to the temperature minimum region. The outputs are stored at a 40 s cadence. We forward model the Stokes profile of two sets of Fe I lines at 630 and 1565 nm, which will be simultaneously observed by DKIST and can better constrain the parameter variations along the line of sight. The MHD model output and the synthetic Stokes profiles are publicly available, with 13.7 TB in the initial release.

22 pages, 13 figures, published on ApJ

References in corpus (57)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• The chemical composition of the Sun
• Solar Flare Prediction Using SDO/HMI Vector Magnetic Field Data with a Machine-Learning Algorithm
• Radiative MHD simulation of sunspot structure
• Numerical simulations of quiet Sun magnetism: On the contribution from a small-scale dynamo
• A solar surface dynamo
• Simulation of the Formation of a Solar Active Region
• Extension of the MURaM radiative MHD code for coronal simulations
• An Open Source, Massively Parallel Code for Non-LTE Synthesis and Inversion of Spectral Lines and Zeeman-induced Stokes Profiles
• Hot Spine Loops and the Nature of a Late-Phase Solar Flare
• Advanced Forward Modeling and Inversion of Stokes Profiles Resulting from the Joint Action of the Hanle and Zeeman Effects
• Forecasting Solar Flares Using Magnetogram-based Predictors and Machine Learning
• Generation of Solar Spicules and Subsequent Atmospheric Heating
• Deep Flare Net (DeFN) model for solar flare prediction
• Numerical sunspot models: Robustness of photospheric velocity and magnetic field structure
• Mining gold from implicit models to improve likelihood-free inference
• STiC -- A multi-atom non-LTE PRD inversion code for full-Stokes solar observations
• Inversion of the radiative transfer equation for polarized light
• Predicting Coronal Mass Ejections Using Machine Learning Methods
• High-resolution observations of flare precursors in the low solar atmosphere
• DeepVel: deep learning for the estimation of horizontal velocities at the solar surface
• Emergence of magnetic flux generated in a solar convective dynamo. I: Formation of Sunspots and Active regions, and Origin of Their Asymmetries
• Spectropolarimetric NLTE inversion code SNAPI
• Recovering Thermodynamics from Spectral Profiles observed by IRIS: A Machine and Deep Learning Approach
• A Comprehensive Method of Estimating Electric Fields from Vector Magnetic Field and Doppler Measurements
• Enhancing SDO/HMI images using deep learning
• Stokes Inversion based on Convolutional Neural Networks
• The Visible Spectro-Polarimeter of the Daniel K. Inouye Solar Telescope
• The Role of Subsurface Flows in Solar Surface Convection: Modeling the Spectrum of Supergranular and Larger Scale Flows
• Compact solar UV burst triggered in a magnetic field with a fan-spine topology
• Flare differentially rotates sunspot on Sun's surface
• Basal magnetic flux and the local solar dynamo
• DeSIRe: Departure coefficient aided Stokes Inversion based on Response functions
• Real-time multiframe blind deconvolution of solar images
• Solar image denoising with convolutional neural networks
• FIRTEZ-dz: A Forward and Inverse solver of the polarized Radiative Transfer Equation under Zeeman regime in geometrical scale
• Combining magneto-hydrostatic constraints with Stokes profiles inversions
• The Photospheric Poynting Flux and Coronal Heating
• The influence of NLTE effects in Fe I lines on an inverted atmosphere I. 6301 A and 6302 A lines formed in 1D NLTE
• Machine learning initialization to accelerate Stokes profile inversions
• Mimicking spectropolarimetric inversions using convolutional neural networks
• Diagnostic capabilities of spectropolarimetric observations for understanding solar phenomena I. Zeeman-sensitive photospheric lines
• Magnetic helicity estimations in models and observations of the solar magnetic field. Part IV: Application to solar observations
• Data-Driven Radiative Magnetohydrodynamics Simulations with the MURaM code
• Eruption of a Magnetic Flux Rope in a Comprehensive Radiative Magnetohydrodynamic Simulation of flare-productive active regions
• Combining magneto-hydrostatic constraints with Stokes profile inversions. II. Application to Hinode/SP observations
• Determining the Transport of Magnetic Helicity and Free Energy in the Sun's Atmosphere
• SynthIA: A Synthetic Inversion Approximation for the Stokes Vector Fusing SDO and Hinode into a Virtual Observatory
• Influence of NLTE effects in Fe I lines on inverted atmosphere II. 6301 A and 6302 A lines formed in 3DNLTE
• Probing the effect of cadence on the estimates of photospheric energy and helicity injections in eruptive active region NOAA AR 11158
• End-to-end simulations of the Visible Tunable Filter for the Daniel K. Inouye Solar Telescope
• SuNeRF: 3D reconstruction of the solar EUV corona using Neural Radiance Fields
• SunnyNet: A neural network approach to 3D non-LTE radiative transfer
• Combining magneto-hydrostatic constraints with Stokes profiles inversions. III. Uncertainty in the inference of electric currents
• Convolutional Neural Networks and Stokes Response Functions
• A study of the capabilities for inferring atmospheric information from high-spatial-resolution simulations
• Deep solar ALMA neural network estimator for image refinement and estimates of small-scale dynamics

Cited by in corpus (1)

• Neural translation for Stokes inversion and synthesis