Classifying the Large Scale Structure of the Universe with Deep Neural Networks

Abstract

We present the first application of deep neural networks to the semantic segmentation of cosmological filaments and walls in the Large Scale Structure of the Universe. Our results are based on a deep Convolutional Neural Network (CNN) with a U-Net architecture trained using an existing state-of-the-art manually-guided segmentation method. We successfully trained an tested an U-Net with a Voronoi model and an N-body simulation. The predicted segmentation masks from the Voronoi model have a Dice coefficient of 0.95 and 0.97 for filaments and mask respectively. The predicted segmentation masks from the N-body simulation have a Dice coefficient of 0.78 and 0.72 for walls and filaments respectively. The relatively lower Dice coefficient in the filament mask is the result of filaments that were predicted by the U-Net model but were not present in the original segmentation mask. Our results show that for a well-defined dataset such as the Voronoi model the U-Net has excellent performance. In the case of the N-body dataset the U-Net produced a filament mask of higher quality than the segmentation mask obtained from a state-of-the art method. The U-Net performs better than the method used to train it, being able to find even the tenuous filaments that the manually-guided segmentation failed to identify. The U-Net presented here can process a $512^3$ volume in a few minutes and without the need of complex pre-processing. Deep CNN have great potential as an efficient and accurate analysis tool for the next generation large-volume computer N-body simulations and galaxy surveys.

Submitted to MNRA. More images at www.dataviz.science/research_machinelearning.html

References in corpus (6)

• Properties of Dark Matter Haloes in Clusters, Filaments, Sheets and Voids
• The Cosmic Ballet: spin and shape alignments of haloes in the cosmic web
• Cascaded V-Net using ROI masks for brain tumor segmentation
• Alignments of Voids in the Cosmic Web
• Bayesian optimisation for likelihood-free cosmological inference
• The cosmic spiderweb: equivalence of cosmic, architectural, and origami tessellations

Cited by in corpus (38)

• Reconstructing Functions and Estimating Parameters with Artificial Neural Networks: A Test with the Hubble Parameter and SNe Ia
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• Identifying Reionization Sources from 21cm Maps using Convolutional Neural Networks
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• ECoPANN: A Framework for Estimating Cosmological Parameters using Artificial Neural Networks
• Predicting dark matter halo formation in N-body simulations with deep regression networks
• Baryon acoustic oscillations reconstruction using convolutional neural networks
• Simulation-based inference of dynamical galaxy cluster masses with 3D convolutional neural networks
• Neural Network Reconstruction of $H^{\prime }(z)$ and its application in Teleparallel Gravity
• Recovering the CMB Signal with Machine Learning
• Supervised machine learning on Galactic filaments Revealing the filamentary structure of the Galactic interstellar medium
• A black box for dark sector physics: Predicting dark matter annihilation feedback with conditional GANs
• Likelihood-free Inference with Mixture Density Network
• Comparison of Observed Galaxy Properties with Semianalytic Model Predictions using Machine Learning
• (DarkAI) Mapping the large-scale density field of dark matter using artificial intelligence
• Deep learning for Sunyaev-Zel'dovich detection in Planck
• Self-supervised Learning with Physics-aware Neural Networks I: Galaxy Model Fitting
• Probabilistic cosmic web classification using fast-generated training data
• Classification and reconstruction of optical quantum states with deep neural networks
• Solving the Pulsar Equation using Physics-Informed Neural Networks
• The problem of dust attenuation in photometric decomposition of edge-on galaxies and possible solutions
• Classification of cosmic structures for galaxies with deep learning: connecting cosmological simulations with observations
• Foreground Removal of CO Intensity Mapping Using Deep Learning
• A deep learning approach to halo merger tree construction
• The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
• Statistical properties of filaments in the cosmic web
• HIKER: a halo-finding method based on kernel-shift algorithm
• Visualization in Astrophysics: Developing New Methods, Discovering Our Universe, and Educating the Earth
• Artificial Neural Networks for Galaxy Clustering. Learning from the two-point correlation function of BOSS galaxies
• DeepMerge: Classifying High-redshift Merging Galaxies with Deep Neural Networks
• Predicting halo occupation and galaxy assembly bias with machine learning
• Prediction of Individual Halo Concentrations Across Cosmic Time Using Neural Networks
• DeepVoid: A Deep Learning Void Detector
• A novel Cosmic Filament catalogue from SDSS data
• Deep Learning generated observations of galaxy clusters from dark-matter-only simulations
• Predicting large scale cosmological structure evolution with generative adversarial network-based autoencoders