Machine Learning and Cosmology

Abstract

Methods based on machine learning have recently made substantial inroads in many corners of cosmology. Through this process, new computational tools, new perspectives on data collection, model development, analysis, and discovery, as well as new communities and educational pathways have emerged. Despite rapid progress, substantial potential at the intersection of cosmology and machine learning remains untapped. In this white paper, we summarize current and ongoing developments relating to the application of machine learning within cosmology and provide a set of recommendations aimed at maximizing the scientific impact of these burgeoning tools over the coming decade through both technical development as well as the fostering of emerging communities.

arXiv commentContribution to Snowmass 2021. 32 pages

References in corpus (78)

• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• The Simons Observatory: Science goals and forecasts
• Galaxy Zoo : Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey
• The Quijote simulations
• The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
• Discovering Symbolic Models from Deep Learning with Inductive Biases
• The Uchuu Simulations: Data Release 1 and Dark Matter Halo Concentrations
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• AbacusSummit: A Massive Set of High-Accuracy, High-Resolution $N$-Body Simulations
• Fast likelihood-free cosmology with neural density estimators and active learning
• Learning to Predict the Cosmological Structure Formation
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Massive optimal data compression and density estimation for scalable, likelihood-free inference in cosmology
• The Strong Gravitational Lens Finding Challenge
• Cosmological constraints with deep learning from KiDS-450 weak lensing maps
• Convolutional neural networks: a magic bullet for gravitational-wave detection?
• A new approach to observational cosmology using the scattering transform
• Non-Gaussian information from weak lensing data via deep learning
• Likelihood-free inference with neural compression of DES SV weak lensing map statistics
• Nuisance hardened data compression for fast likelihood-free inference
• Towards an Optimal Estimation of Cosmological Parameters with the Wavelet Scattering Transform
• Automatic physical inference with information maximising neural networks
• Finding high-redshift strong lenses in DES using convolutional neural networks
• Weak lensing cosmology with convolutional neural networks on noisy data
• AI-assisted super-resolution cosmological simulations
• Discovering New Strong Gravitational Lenses in the DESI Legacy Imaging Surveys
• SuperRAENN: A Semi-supervised Supernova Photometric Classification Pipeline Trained on Pan-STARRS1 Medium Deep Survey Supernovae
• Cosmological constraints from noisy convergence maps through deep learning
• Constraining the astrophysics and cosmology from 21cm tomography using deep learning with the SKA
• The CAMELS Multifield Dataset: Learning the Universe's Fundamental Parameters with Artificial Intelligence
• Super-resolution emulator of cosmological simulations using deep physical models
• Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
• Deep learning dark matter map reconstructions from DES SV weak lensing data
• deep21: a Deep Learning Method for 21cm Foreground Removal
• Detection and Parameter Estimation of Gravitational Waves from Binary Neutron-Star Mergers in Real LIGO Data using Deep Learning
• Anomaly detection in the Zwicky Transient Facility DR3
• Mining for Strong Gravitational Lenses with Self-supervised Learning
• LSST Target-of-Opportunity Observations of Gravitational Wave Events: Essential and Efficient
• Target of Opportunity Observations of Gravitational Wave Events with Vera C. Rubin Observatory
• Translation and Rotation Equivariant Normalizing Flow (TRENF) for Optimal Cosmological Analysis
• Hierarchical Inference With Bayesian Neural Networks: An Application to Strong Gravitational Lensing
• Convolutional Neural Networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis
• DeepMerge II: Building Robust Deep Learning Algorithms for Merging Galaxy Identification Across Domains
• From Images to Dark Matter: End-To-End Inference of Substructure From Hundreds of Strong Gravitational Lenses
• Direct Detection of Dark Matter Substructure in Strong Lens Images with Convolutional Neural Networks
• AI-assisted super-resolution cosmological simulations II: Halo substructures, velocities and higher order statistics
• Differentiable Strong Lensing: Uniting Gravity and Neural Nets through Differentiable Probabilistic Programming
• Weak-lensing shear measurement with machine learning: teaching artificial neural networks about feature noise
• Extracting the Subhalo Mass Function from Strong Lens Images with Image Segmentation
• Image segmentation for analyzing galaxy-galaxy strong lensing systems
• Towards constraining warm dark matter with stellar streams through neural simulation-based inference
• Foreground modelling via Gaussian process regression: an application to HERA data
• Parameter Inference for Weak Lensing using Gaussian Processes and MOPED
• Analyzing interferometric observations of strong gravitational lenses with recurrent and convolutional neural networks
• Cleaning our own Dust: Simulating and Separating Galactic Dust Foregrounds with Neural Networks
• Inferring Astrophysics and Dark Matter Properties from 21cm Tomography using Deep Learning
• Preparing to discover the unknown with Rubin LSST -- I: Time domain
• Mass Estimation of Galaxy Clusters with Deep Learning II: CMB Cluster Lensing
• Multifield Cosmology with Artificial Intelligence
• Fast and Accurate Non-Linear Predictions of Universes with Deep Learning
• DeepSZ: Identification of Sunyaev-Zel'dovich Galaxy Clusters using Deep Learning
• Decoding Dark Matter Substructure without Supervision
• Modeling assembly bias with machine learning and symbolic regression
• Cosmological Parameter Estimation and Inference using Deep Summaries
• Weak lensing shear estimation beyond the shape-noise limit: a machine learning approach
• DeepZipper: A Novel Deep Learning Architecture for Lensed Supernovae Identification
• Flow-Based Likelihoods for Non-Gaussian Inference
• FOBOS: A Next-Generation Spectroscopic Facility at the W. M. Keck Observatory
• Reconstructing Cosmic Polarization Rotation with ResUNet-CMB
• Targeted Likelihood-Free Inference of Dark Matter Substructure in Strongly-Lensed Galaxies
• Mass Estimation of Planck Galaxy Clusters using Deep Learning
• Transformation Importance with Applications to Cosmology
• Variational Inference for Deblending Crowded Starfields
• Joint survey processing: combined resampling and convolution for galaxy modelling and deblending
• Modeling the galaxy-halo connection with machine learning
• Simulation-Based Inference of Strong Gravitational Lensing Parameters
• Domain Adaptation for Simulation-Based Dark Matter Searches Using Strong Gravitational Lensing
• The Growing Importance of a Tech Savvy Astronomy and Astrophysics Workforce

Cited by in corpus (9)

• A thorough investigation of the prospects of eLISA in addressing the Hubble tension: Fisher Forecast, MCMC and Machine Learning
• AI-assisted super-resolution cosmological simulations III: Time evolution
• Optimal, fast, and robust inference of reionization-era cosmology with the 21cmPIE-INN
• Constraining cosmological parameters from N-body simulations with Variational Bayesian Neural Networks
• SKATR: A Self-Supervised Summary Transformer for SKA
• Deep learning approach for identification of HII regions during reionization in 21-cm observations -- III. image recovery
• Clusternets: A deep learning approach to probe clustering dark energy
• Neural Networks for cosmological model selection and feature importance using Cosmic Microwave Background data
• Large Language Models -- the Future of Fundamental Physics?