The CAMELS Multifield Dataset: Learning the Universe's Fundamental Parameters with Artificial Intelligence

Abstract

We present the Cosmology and Astrophysics with MachinE Learning Simulations (CAMELS) Multifield Dataset, 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 2,000 distinct simulated universes at several cosmic times. The 2D maps and 3D grids represent cosmic regions that span $\sim$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 dataset of its kind containing more than 70 Terabytes 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.

17 pages, 1 figure. Third paper of a series of four. Hundreds of thousands of labeled 2D maps and 3D grids from thousands of simulated universes publicly available at https://camels-multifield-dataset.readthedocs.io

References in corpus (21)

• Simulating galaxy formation with black hole driven thermal and kinetic feedback
• Simba: Cosmological Simulations with Black Hole Growth and Feedback
• Introducing the Illustris Project: the evolution of galaxy populations across cosmic time
• The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
• Likelihood-free inference with neural compression of DES SV weak lensing map statistics
• AI-assisted super-resolution cosmological simulations
• deep21: a Deep Learning Method for 21cm Foreground Removal
• Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian Deep Learning
• From Dark Matter to Galaxies with Convolutional Networks
• Removing Astrophysics in 21 cm maps with Neural Networks
• AI-assisted super-resolution cosmological simulations II: Halo substructures, velocities and higher order statistics
• Anomaly detection in Hyper Suprime-Cam galaxy images with generative adversarial networks
• Probabilistic Autoencoder
• HInet: Generating neutral hydrogen from dark matter with neural networks
• Investigating Cosmological GAN Emulators Using Latent Space Interpolation
• Fast and Accurate Non-Linear Predictions of Universes with Deep Learning
• Hybrid analytic and machine-learned baryonic property insertion into galactic dark matter haloes
• Teaching neural networks to generate Fast Sunyaev Zel'dovich Maps
• Modeling assembly bias with machine learning and symbolic regression
• Learning the Evolution of the Universe in N-body Simulations
• dm2gal: Mapping Dark Matter to Galaxies with Neural Networks

Cited by in corpus (35)

• The CAMELS project: public data release
• Learning cosmology and clustering with cosmic graphs
• Robust Field-level Likelihood-free Inference with Galaxies
• The Bacco Simulation Project: Bacco Hybrid Lagrangian Bias Expansion Model in Redshift Space
• Probabilistic Mass Mapping with Neural Score Estimation
• Machine Learning for Observational Cosmology
• HIFlow: Generating Diverse HI Maps and Inferring Cosmology while Marginalizing over Astrophysics using Normalizing Flows
• Large-scale density and velocity field reconstructions with neural networks
• Measuring the Hubble Constant with cosmic chronometers: a machine learning approach
• Data Compression and Inference in Cosmology with Self-Supervised Machine Learning
• Machine Learning and Cosmology
• Machine-learning cosmology from void properties
• Exploration of 3D wavelet scattering transform coefficients for line-intensity mapping measurements
• CGM${}^2$ $+$ CASBaH: The Mass Dependence of H~I Ly$\alpha$-Galaxy Clustering and the Extent of the CGM
• Bayesian Control Variates for optimal covariance estimation with pairs of simulations and surrogates
• Diffusion-HMC: Parameter Inference with Diffusion-model-driven Hamiltonian Monte Carlo
• Field-level simulation-based inference with galaxy catalogs: the impact of systematic effects
• Inference of the optical depth to reionization $\tau$ from $\text{Planck}$ CMB maps with convolutional neural networks
• Inpainting hydrodynamical maps with deep learning
• Cosmology from Point Clouds with Dark Matter Halos from the Quijote Simulations
• Predictive uncertainty on improved astrophysics recovery from multifield cosmology
• Deep Forest: Neural Network reconstruction of intergalactic medium temperature
• Non-Linearity-Free prediction of the growth-rate $f{\sigma }_8$ using Convolutional Neural Networks
• Tackling the Problem of Distributional Shifts: Correcting Misspecified, High-Dimensional Data-Driven Priors for Inverse Problems
• Reconstructing axion-like particles from beam dumps with simulation-based inference
• Field-Level Comparison and Robustness Analysis of Cosmological N-body Simulations
• Clusternets: A deep learning approach to probe clustering dark energy
• The Cosmological analysis of X-ray cluster surveys VII. Bypassing scaling relations with Lagrangian Deep Learning and Simulation-based inference
• Inferring halo masses with Graph Neural Networks
• Interpreting Cosmological Information from Neural Networks in the Hydrodynamic Universe
• Large, fast and accurate HI intensity maps with latent overlap diffusion
• An Observationally Driven Multifield Approach for Probing the Circum-Galactic Medium with Convolutional Neural Networks
• Weighing the Milky Way and Andromeda with Artificial Intelligence
• Towards an optimal extraction of cosmological parameters from galaxy cluster surveys using convolutional neural networks
• Exploring Machine Learning Regression Models for Advancing Foreground Mitigation and Global 21cm Signal Parameter Extraction