Machine learning initialization to accelerate Stokes profile inversions

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.