FarNet-II: Application of Convolutional LSTM and attention mechanisms to solar far-side activity detection
Far-side helioseismology is the branch of astrophysics dedicated to inferring the activity on the far hemisphere of the Sun using the wave-field from the near-side surface. Recently, the neural network FarNet, with a U-net architecture widely used for semantic segmentation, has been proven to improve the activity predictions of phase-sensitive holography, the standard method for applying far-side helioseismology. This was achieved using as inputs temporal sequences of nearside phase-shift maps. The network returned far-side activity probability maps for the central date of each input.
We have developed FarNet-II, a new network that expands the capacities of FarNet by adding Convolutional LSTM modules and attention mechanisms to the model. This new tool uses the same phase-shift maps as inputs, but returns one activity probability map for each image date on the input sequence. We found that the prediction capabilities are greatly improved with respect to FarNet. Also, the outputs of this network keep better temporal coherence among them than those obtained with FarNet.
Improved predictions from FarNet-II can contribute to a great number of applications on space weather, such as spectral irradiance and solar wind forecasting.
Elena García Broock is a second year PhD student at Instituto de Astrofísica de Canarias. Her Master’s and Bachelor’s degree were both obtained from Universidad de La Laguna. The goal of her thesis, supervised by Tobías Felipe and Andrés Asensio Ramos, is building machine learning tools to improve the detections of activity on the far side of the sun achieved by helioseismology. Now she is staying in Boulder for a three months collaboration with Charlie Lindsey and Douglas Braun at North West Research Associates.