Machine learning initialization to accelerate Stokes profile inversions. (arXiv:2103.09651v1 [astro-ph.IM])
<a href="http://arxiv.org/find/astro-ph/1/au:+Gafeira_R/0/1/0/all/0/1">R. Gafeira</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Suarez_D/0/1/0/all/0/1">D. Orozco Suárez</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Milic_I/0/1/0/all/0/1">I. Milic</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Noda_C/0/1/0/all/0/1">C. Quintero Noda</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Cobo_B/0/1/0/all/0/1">B. Ruiz Cobo</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Uitenbroek_H/0/1/0/all/0/1">H. Uitenbroek</a>
In this work, we discuss the application of convolutional neural networks
(CNNs) as a tool to advantageously initialize Stokes profile inversions. To
demonstrate the usefulness of CNNs, we concentrate in this paper on the
inversion of LTE Stokes profiles. We use observations taken with the
spectropolarimeter onboard the Hinode spacecraft as a test benchmark. First, we
carefully analyze the data with the SIR inversion code using a given initial
atmospheric model. The code provides a set of atmospheric models that reproduce
the observations. These models are then used to train a CNN. Afterwards, the
same data are again inverted with SIR but using the trained CNN to provide the
initial guess atmospheric models for SIR. The CNNs allow us to significantly
reduce the number of inversion cycles when used to compute initial guess model
atmospheres, decreasing the computational time for LTE inversions by a factor
of two to four. CNN’s alone are much faster than assisted inversions, but the
latter are more robust and accurate. The advantages and limitations of machine
learning techniques for estimating optimum initial atmospheric models for
spectral line inversions are discussed. Finally, we describe a python wrapper
for the SIR and DeSIRe codes that allows for the easy setup of parallel
inversions. The assisted inversions can speed up the inversion process, but the
efficiency and accuracy of the inversion results depend strongly on the solar
scene and the data used for the CNN training. This method (assisted inversions)
will not obviate the need for analyzing individual events with the utmost care
but will provide solar scientists with a much better opportunity to sample
large amounts of inverted data, which will undoubtedly broaden the physical
discovery space.
In this work, we discuss the application of convolutional neural networks
(CNNs) as a tool to advantageously initialize Stokes profile inversions. To
demonstrate the usefulness of CNNs, we concentrate in this paper on the
inversion of LTE Stokes profiles. We use observations taken with the
spectropolarimeter onboard the Hinode spacecraft as a test benchmark. First, we
carefully analyze the data with the SIR inversion code using a given initial
atmospheric model. The code provides a set of atmospheric models that reproduce
the observations. These models are then used to train a CNN. Afterwards, the
same data are again inverted with SIR but using the trained CNN to provide the
initial guess atmospheric models for SIR. The CNNs allow us to significantly
reduce the number of inversion cycles when used to compute initial guess model
atmospheres, decreasing the computational time for LTE inversions by a factor
of two to four. CNN’s alone are much faster than assisted inversions, but the
latter are more robust and accurate. The advantages and limitations of machine
learning techniques for estimating optimum initial atmospheric models for
spectral line inversions are discussed. Finally, we describe a python wrapper
for the SIR and DeSIRe codes that allows for the easy setup of parallel
inversions. The assisted inversions can speed up the inversion process, but the
efficiency and accuracy of the inversion results depend strongly on the solar
scene and the data used for the CNN training. This method (assisted inversions)
will not obviate the need for analyzing individual events with the utmost care
but will provide solar scientists with a much better opportunity to sample
large amounts of inverted data, which will undoubtedly broaden the physical
discovery space.
http://arxiv.org/icons/sfx.gif
