Using Convolutional Neural Networks for the Helicity Classification of Magnetic Fields
This work addresses the detection of primordial magnetic fields in astrophysics, but it is incremental as it applies an existing deep learning method to a specific domain problem.
The paper tackled the problem of classifying helicity in intergalactic magnetic fields using Convolutional Neural Networks, showing that this method outperforms the existing Q estimator.
The presence of non-zero helicity in intergalactic magnetic fields is a smoking gun for their primordial origin since they have to be generated by processes that break CP invariance. As an experimental signature for the presence of helical magnetic fields, an estimator $Q$ based on the triple scalar product of the wave-vectors of photons generated in electromagnetic cascades from, e.g., TeV blazars, has been suggested previously. We propose to apply deep learning to helicity classification employing Convolutional Neural Networks and show that this method outperforms the $Q$ estimator.