Generating astronomical spectra from photometry with conditional diffusion models

Doorenbos, Lars; Cavuoti, Stefano; Longo, Giuseppe; Brescia, Massimo; Sznitman, Raphael; Márquez-Neila, Pablo (3 December 2022). Generating astronomical spectra from photometry with conditional diffusion models (In Press). In: Machine Learning and the Physical Sciences.

[img] Text
_NeurIPS_2022__Multimodal_Astronomy__1_.pdf - Accepted Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (1MB) | Request a copy

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 galaxy spectra directly from photometry, through which we obtain an estimate of their intricacies from easily acquired images. This is done 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 data show promising results.

Item Type:

Conference or Workshop Item (Paper)


10 Strategic Research Centers > ARTORG Center for Biomedical Engineering Research

Graduate School:

Graduate School for Cellular and Biomedical Sciences (GCB)

UniBE Contributor:

Doorenbos, Lars Jelte, Sznitman, Raphael, Márquez Neila, Pablo


000 Computer science, knowledge & systems
500 Science > 520 Astronomy




Lars Jelte Doorenbos

Date Deposited:

15 Nov 2022 10:09

Last Modified:

06 Dec 2022 16:28




Actions (login required)

Edit item Edit item
Provide Feedback