The Multimodal Universe: 100 TB of Machine Learning Ready Astronomical Data

Abstract We present the Multimodal Universe , a new framework collating over 100 TB of multimodal astronomical data for its first release, spanning images, spectra, time series, tabular and hyper-spectral data. This unified collection enables a wide variety of machine learning (ML) applications and research across astronomical domains. The dataset brings together observations from multiple surveys, facilities, and wavelength regimes, providing standardized access to diverse data types. By providing uniform access to this diverse data, the Multimodal Universe aims to accelerate the development of ML methods for observational astronomy that can work across the large differences in astronomical datasets. The framework is actively supported and is designed to be extended whilst enforcing minimal self consistent conventions making contributing data as simple and practical as possible.

Authors

Publication Details

Journal
Research Notes of the AAS
Published
2024-12-10
DOI
https://doi.org/10.3847/2515-5172/ad9a63
Primary Topic
Astronomical Observations and Instrumentation
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

The Multimodal Universe: 100 TB of Machine Learning Ready Astronomical Data

Erin E. Hayes, Micah Bowles, François Lanusse, Lucas Meyer et al.
Research Notes of the AAS
Astronomical Observations and Instrumentation
article

The Multimodal Universe: 100 TB of Machine Learning Ready Astronomical Data

Erin E. Hayes, Micah Bowles, François Lanusse, Lucas Meyer, Eirini Angeloudi, Kaisey S. Mandel, Jeff Shen, Liam Parker, Helen Qu, Benjamin M. Boyd, Matthew Grayling, Brian Cherinka, M. Jabłońska, Jeroen Audenaert, Aaron Do, Kartheik G. Iyer, P. Melchior, Michael J. Smith, Mike Walmsley, John F. Wu, Henry Leung, Miles Cranmer, Juan Rafael Martínez-Galarza, Shirley S. Ho, Ioana Ciucă, Tom Hehir, David Chemaly
article en

Abstract

Abstract We present the Multimodal Universe , a new framework collating over 100 TB of multimodal astronomical data for its first release, spanning images, spectra, time series, tabular and hyper-spectral data. This unified collection enables a wide variety of machine learning (ML) applications and research across astronomical domains. The dataset brings together observations from multiple surveys, facilities, and wavelength regimes, providing standardized access to diverse data types. By providing uniform access to this diverse data, the Multimodal Universe aims to accelerate the development of ML methods for observational astronomy that can work across the large differences in astronomical datasets. The framework is actively supported and is designed to be extended whilst enforcing minimal self consistent conventions making contributing data as simple and practical as possible.

Research Notes of the AASVol. 8(12)
Openalex Percentile: Top 75%
Astronomical Observations and Instrumentation
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.