Multi-height Doppler velocity maps from two layers separated by 50 km are obtained from combinations of currently recorded HMI filtergrams. Using synthetic data of spectral line profiles produced in a convective environment, we test the ability to recover vertical velocity fields at different heights.
We attempt to forecast M- and X-class solar flares using a support vector machine algorithm and 4 years of HMI vector magnetic field data. With the true skill statistic as the preferred metric to estimate the algorithm performances, we obtain good predictive abilities. This may be partly due to fine-tuning the algorithm for this purpose, and to a choice of 13 SHARP parameters obtained from vector magnetograms.