Toward AI-based Classification of Ground-based Auroral Emission Spectra
Co-authored poster (presented by G. Cessateur) extending our supervised spectra classifier to an unsupervised exploration of 328,281 ASIS spectra.
gael-cessateur
•
Aug 24, 2026 — Aug 28, 2026
•
1 min read
Reading the Aurora: What Transformer Attention Sees in Auroral Spectra
A 1D Vision Transformer classifies auroral emission spectra, and its attention maps rediscover known emission lines without any physics prior.
Multi-label Classification of Ground-based Auroral Emission Spectra Using 1D Vision Transformers
We examine whether Vision Transformer attention can serve as a built-in interpretability mechanism on ordered 1D scientific signals, where physical ground truth enables direct …
Multi-label Classification of Ground-based Auroral Emission Spectra Using 1D Vision Transformers
Poster on classifying auroral emission spectra with a 1D Vision Transformer, whose attention maps recover known emission lines without spectroscopic priors.