Generating astronomical spectra from photometry with conditional diffusion models

TL;DR

This paper introduces a novel method using conditional diffusion models to generate detailed astronomical spectra from easily obtained photometric data, bridging the gap between quick observations and detailed analysis.

Contribution

It presents a new multi-modal diffusion model approach for converting photometry into spectra, improving efficiency in astronomical data analysis.

Findings

Initial experiments show promising spectral generation results.

The method effectively estimates spectral details from photometric data.

Contrastive networks improve the selection of best generated spectra.

Abstract

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 their intricacies from easily acquired images. This is done by using multi-modal 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.