Ongoing and future surveys will surprise us, but only if our methods have the speed and flexibility to take advantage of vast quantities of data. Dr. Melchior presents a neural network architecture that is specifically designed for galaxy spectra at variable redshifts. It is trained with an invariance-promoting loss function and can create superresolution reconstructions and infer the physical properties of galaxies with few-shot learning.

The representations of optical spectra provide accurate prediction of IR photometry, a connection that is not captured by current physical spectrum modeling methods. Dr. Melchior discusses extensions of this work to exoplanet and quasar spectra to demonstrate the strengths and versatility of this approach.