Saved in:
Bibliographic Details
Main Authors: Xia, Bin, Ramachandra, Nesar, Wells, Azton I., Habib, Salman, Wise, John
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.07684
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918157115981824
author Xia, Bin
Ramachandra, Nesar
Wells, Azton I.
Habib, Salman
Wise, John
author_facet Xia, Bin
Ramachandra, Nesar
Wells, Azton I.
Habib, Salman
Wise, John
contents We present a multi-modal foundation model for astrophysical galaxy data, designed to map between simulation- and observation-based galactic features. Our encoder-only transformer flexibly ingests scalar quantities (e.g., redshifts, galaxy masses) and vectors (e.g., star formation histories, spectra), supporting multi-task training that includes within-modality reconstruction and cross-modality prediction. With a dynamic masking strategy, the model can query arbitrary galaxy properties from partial inputs -- including predicting spectra from redshift and mass, or estimating photometric redshifts from broadband magnitudes -- while also recovering missing segments within a modality. Trained on 185,000 simulated galaxies from a gigaparsec-scale Cosmology simulation, the model yields a 50% improvement in redshift estimation when combining LSST and SPHEREx photometry over LSST photometry alone, and a 63% improvement in stellar mass inference when combining late-time SFH with LSST photometry over early-time SFH with LSST photometry. The model demonstrates strong generalization across multi-modal tasks and lays the groundwork for future integration of higher-dimensional and structured data such as images, merger trees, and 3D fields. This approach provides a unified framework for connecting simulations and observations, advancing the development of generalizable astrophysical foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07684
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-modal Foundation Model for Cosmological Simulation Data
Xia, Bin
Ramachandra, Nesar
Wells, Azton I.
Habib, Salman
Wise, John
Astrophysics of Galaxies
We present a multi-modal foundation model for astrophysical galaxy data, designed to map between simulation- and observation-based galactic features. Our encoder-only transformer flexibly ingests scalar quantities (e.g., redshifts, galaxy masses) and vectors (e.g., star formation histories, spectra), supporting multi-task training that includes within-modality reconstruction and cross-modality prediction. With a dynamic masking strategy, the model can query arbitrary galaxy properties from partial inputs -- including predicting spectra from redshift and mass, or estimating photometric redshifts from broadband magnitudes -- while also recovering missing segments within a modality. Trained on 185,000 simulated galaxies from a gigaparsec-scale Cosmology simulation, the model yields a 50% improvement in redshift estimation when combining LSST and SPHEREx photometry over LSST photometry alone, and a 63% improvement in stellar mass inference when combining late-time SFH with LSST photometry over early-time SFH with LSST photometry. The model demonstrates strong generalization across multi-modal tasks and lays the groundwork for future integration of higher-dimensional and structured data such as images, merger trees, and 3D fields. This approach provides a unified framework for connecting simulations and observations, advancing the development of generalizable astrophysical foundation models.
title Multi-modal Foundation Model for Cosmological Simulation Data
topic Astrophysics of Galaxies
url https://arxiv.org/abs/2510.07684