@article{111c96d2e61c40969d03bb65b3d2e9b6,
title = "Fast and accurate emulation of the sdo/hmi stokes inversion with uncertainty quantification",
abstract = "The Helioseismic and Magnetic Imager (HMI) on board NASA's Solar Dynamics Observatory produces estimates of the photospheric magnetic field, which are a critical input to many space weather modeling and forecasting systems. The magnetogram products produced by HMI and its analysis pipeline are the result of a per-pixel optimization that estimates solar atmospheric parameters and minimizes disagreement between a synthesized and observed Stokes vector. In this paper, we introduce a deep-learning-based approach that can emulate the existing HMI pipeline results two orders of magnitude faster than the current pipeline algorithms. Our system is a U-Net trained on input Stokes vectors and their accompanying optimization-based Very Fast Inversion of the Stokes Vector (VFISV) inversions. We demonstrate that our system, once trained, can produce high-fidelity estimates of the magnetic field and kinematic and thermodynamic parameters while also producing meaningful confidence intervals. We additionally show that despite penalizing only per-pixel loss terms, our system is able to faithfully reproduce known systematic oscillations in full-disk statistics produced by the pipeline. This emulation system could serve as an initialization for the full Stokes inversion or as an ultrafast proxy inversion. This work is part of the NASA Heliophysics DRIVE Science Center (SOLSTICE) at the University of Michigan, under grant NASA 80NSSC20K0600E, and will be open sourced.",
author = "Higgins, {Richard E.L.} and Fouhey, {David F.} and Dichang Zhang and Antiochos, {Spiro K.} and Graham Barnes and {Todd Hoeksema}, J. and Leka, {K. D.} and Yang Liu and Schuck, {Peter W.} and Gombosi, {Tamas I.}",
note = "Funding Information: The Helioseismic and Magnetic Imager (HMI) on board NASA{\textquoteright}s Solar Dynamics Observatory produces estimates of the photospheric magnetic field, which are a critical input to many space weather modeling and forecasting systems. The magnetogram products produced by HMI and its analysis pipeline are the result of a per-pixel optimization that estimates solar atmospheric parameters and minimizes disagreement between a synthesized and observed Stokes vector. In this paper, we introduce a deep-learning-based approach that can emulate the existing HMI pipeline results two orders of magnitude faster than the current pipeline algorithms. Our system is a U-Net trained on input Stokes vectors and their accompanying optimization-based Very Fast Inversion of the Stokes Vector (VFISV) inversions. We demonstrate that our system, once trained, can produce high-fidelity estimates of the magnetic field and kinematic and thermodynamic parameters while also producing meaningful confidence intervals. We additionally show that despite penalizing only per-pixel loss terms, our system is able to faithfully reproduce known systematic oscillations in full-disk statistics produced by the pipeline. This emulation system could serve as an initialization for the full Stokes inversion or as an ultrafast proxy inversion. This work is part of the NASA Heliophysics DRIVE Science Center (SOLSTICE) at the University of Michigan, under grant NASA 80NSSC20K0600E, and will be open sourced. Publisher Copyright: {\textcopyright} 2021 Institute of Physics Publishing. All rights reserved.",
year = "2021",
month = apr,
day = "20",
doi = "10.3847/1538-4357/abd7fe",
language = "English (US)",
volume = "911",
journal = "Astrophysical Journal",
issn = "0004-637X",
publisher = "IOP Publishing Ltd.",
number = "2",
}