Self-Supervised Representation Learning: From Spectral Foundation Models to Auroral Emission Spectra
A 1D Vision Transformer with a masked autoencoder is pretrain with a masked autoencoder on 223,000 unlabelled spectra to recover the emission-line intensity ratios that physicists use to diagnose the precipitating particles.
M. Le Lain, G. Cessateur, Sébastien Lefèvre
· 0 citations