TY - JOUR
T1 - The CAMELS Multifield Data Set: Learning the Universe's Fundamental Parameters with Artificial Intelligence
AU - Villaescusa-Navarro, Francisco
AU - Genel, Shy
AU - Angles-Alcazar, Daniel
AU - Thiele, Leander
AU - Dave, Romeel
AU - Narayanan, Desika
AU - Nicola, Andrina
AU - Li, Yin
AU - Villanueva-Domingo, Pablo
AU - Wandelt, Benjamin
AU - Spergel, David N.
AU - Somerville, Rachel S.
AU - Matilla, Jose Manuel Zorrilla
AU - Mohammad, Faizan G.
AU - Hassan, Sultan
AU - Shao, Helen
AU - Wadekar, Digvijay
AU - Eickenberg, Michael
AU - Wong, Kaze W. K.
AU - Contardo, Gabriella
AU - Jo, Yongseok
AU - Moser, Emily
AU - Lau, Erwin T.
AU - Valle, Luis Fernando Machado Poletti
AU - Perez, Lucia A.
AU - Nagai, Daisuke
AU - Battaglia, Nicholas
AU - Vogelsberger, Mark
N1 - Funding Information:
We thank the referee for his/her constructive report. F.V.N. acknowledges funding from the WFIRST program through NNG26PJ30C and NNN12AA01C. D.A.A. was supported in part by NSF grants AST-2009687 and AST-2108944. The work of D.N.S., S.G., D.A.A., L.T., Y.L., A.N., S.H., and B.D.W. has been supported by the Simons Foundation. The work of P.V.D. is supported by CIDEGENT/2018/019, CPI-21-108. The 2D maps and 3D grids have been created using the Pylians3 libraries and voxelize. CMD has been created using the Rusty cluster of the Flatiron Institute. Details on the CAMELS simulations can be found in https://www.camel-simulations.org .
Publisher Copyright:
© 2022. The Author(s). Published by the American Astronomical Society.
PY - 2022/4/7
Y1 - 2022/4/7
N2 - We present the Cosmology and Astrophysics with Machine Learning Simulations (CAMELS) Multifield Data set (CMD), a collection of hundreds of thousands of 2D maps and 3D grids containing many different properties of cosmic gas, dark matter, and stars from more than 2000 distinct simulated universes at several cosmic times. The 2D maps and 3D grids represent cosmic regions that span ∼100 million light-years and have been generated from thousands of state-of-the-art hydrodynamic and gravity-only N-body simulations from the CAMELS project. Designed to train machine-learning models, CMD is the largest data set of its kind containing more than 70 TB of data. In this paper we describe CMD in detail and outline a few of its applications. We focus our attention on one such task, parameter inference, formulating the problems we face as a challenge to the community. We release all data and provide further technical details at https://camels-multifield-dataset.readthedocs.io.
AB - We present the Cosmology and Astrophysics with Machine Learning Simulations (CAMELS) Multifield Data set (CMD), a collection of hundreds of thousands of 2D maps and 3D grids containing many different properties of cosmic gas, dark matter, and stars from more than 2000 distinct simulated universes at several cosmic times. The 2D maps and 3D grids represent cosmic regions that span ∼100 million light-years and have been generated from thousands of state-of-the-art hydrodynamic and gravity-only N-body simulations from the CAMELS project. Designed to train machine-learning models, CMD is the largest data set of its kind containing more than 70 TB of data. In this paper we describe CMD in detail and outline a few of its applications. We focus our attention on one such task, parameter inference, formulating the problems we face as a challenge to the community. We release all data and provide further technical details at https://camels-multifield-dataset.readthedocs.io.
U2 - 10.3847/1538-4365/ac5ab0
DO - 10.3847/1538-4365/ac5ab0
M3 - Article
SN - 0067-0049
VL - 259
SP - 1
EP - 14
JO - Astrophysical Journal Supplement
JF - Astrophysical Journal Supplement
IS - 2
M1 - 61
ER -