Multifield Cosmology with Artificial Intelligence

Abstract

Astrophysical processes such as feedback from supernovae and active galactic nuclei modify the properties and spatial distribution of dark matter, gas, and galaxies in a poorly understood way. This uncertainty is one of the main theoretical obstacles to extract information from cosmological surveys. We use 2,000 state-of-the-art hydrodynamic simulations from the CAMELS project spanning a wide variety of cosmological and astrophysical models and generate hundreds of thousands of 2-dimensional maps for 13 different fields: from dark matter to gas and stellar properties. We use these maps to train convolutional neural networks to extract the maximum amount of cosmological information while marginalizing over astrophysical effects at the field level. Although our maps only cover a small area of $(25h^{-1}\mathrm{Mpc}{)}^2$, and the different fields are contaminated by astrophysical effects in very different ways, our networks can infer the values of ${\Omega }_{\mathrm{m}}$ and ${\sigma }_8$ with a few percent level precision for most of the fields. We find that the marginalization performed by the network retains a wealth of cosmological information compared to a model trained on maps from gravity-only N-body simulations that are not contaminated by astrophysical effects. Finally, we train our networks on multifields -- 2D maps that contain several fields as different colors or channels -- and find that not only they can infer the value of all parameters with higher accuracy than networks trained on individual fields, but they can constrain the value of ${\Omega }_{\mathrm{m}}$ with higher accuracy than the maps from the N-body simulations.

arXiv comment11 pages, 7 figures. First paper of a series of four. All 2D maps, codes, and networks weights publicly available at https://camels-multifield-dataset.readthedocs.io

References in corpus (15)

• Decoupled Weight Decay Regularization
• E pur si muove: Galiliean-invariant cosmological hydrodynamical simulations on a moving mesh
• Simulating Galaxy Formation with the IllustrisTNG Model
• Simulating galaxy formation with black hole driven thermal and kinetic feedback
• GIZMO: A New Class of Accurate, Mesh-Free Hydrodynamic Simulation Methods
• Simba: Cosmological Simulations with Black Hole Growth and Feedback
• Cosmological constraints with deep learning from KiDS-450 weak lensing maps
• Non-Gaussian information from weak lensing data via deep learning
• Likelihood-free inference with neural compression of DES SV weak lensing map statistics
• Towards an Optimal Estimation of Cosmological Parameters with the Wavelet Scattering Transform
• Weak lensing cosmology with convolutional neural networks on noisy data
• Constraining the astrophysics and cosmology from 21cm tomography using deep learning with the SKA
• Interpreting deep learning models for weak lensing
• Cosmological model discrimination with Deep Learning
• The unequal-time matter power spectrum: impact on weak lensing observables

Cited by in corpus (13)

• Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation
• Breaking baryon-cosmology degeneracy with the electron density power spectrum
• Wavelet Moments for Cosmological Parameter Estimation
• Cosmology with Persistent Homology: a Fisher Forecast
• Machine Learning and Cosmology
• Fast likelihood-free inference in the LSS Stage IV era
• Learning the Universe: Cosmological and Astrophysical Parameter Inference with Galaxy Luminosity Functions and Colours
• Field-level simulation-based inference with galaxy catalogs: the impact of systematic effects
• Predictive uncertainty on improved astrophysics recovery from multifield cosmology
• Clusternets: A deep learning approach to probe clustering dark energy
• Detecting Modeling Bias with Continuous Time Flow Models on Weak Lensing Maps
• An Observationally Driven Multifield Approach for Probing the Circum-Galactic Medium with Convolutional Neural Networks
• Cosmology with Persistent Homology: Parameter Inference via Machine Learning