A flow-matching generative model reconstructs 3D cosmic baryon fields from galaxy surveys and yields per-sightline FRB dispersion-measure posteriors
The work introduces a flow-matching generative model that reconstructs the posterior distribution of 3D gas density fields from redshift-space galaxy density fields, conditioned on cosmological parameters, a minimum stellar mass threshold, and the baryon suppression power spectrum, and validates on CAMELS50 (IllustrisTNG) test boxes that the reconstructed dispersion measures agree with the truth both sightline by sightline and in overall distribution, with generalization to TNG300-1 at roughly 43 times the training volume.