Skip to yearly menu bar Skip to main content

Workshop: Machine Learning and the Physical Sciences

Generating astronomical spectra from photometry with conditional diffusion models

Lars Doorenbos · Stefano Cavuoti · Giuseppe Longo · Massimo Brescia · Raphael Sznitman · Pablo Márquez Neila


A trade-off between speed and information controls our understanding of astronomical objects. Fast-to-acquire photometric observations provide global properties, while costly and time-consuming spectroscopic measurements enable a better understanding of the physics governing their evolution. Here, we tackle this problem by generating spectra directly from photometry, through which we obtain an estimate of an object's intricacies from easily acquired images. This is achieved by using multimodal conditional diffusion models, where the best out of the generated spectra is selected with a contrastive network. Initial experiments on minimally processed SDSS galaxy data show promising results.

Chat is not available.