English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Dark matter haloes play a fundamental role in cosmological structureformation. The most common approach to model their assembly mechanisms isthrough N-body simulations. In this work we present an innovative pathway topredict dark matter halo formation from the initial density field using a DeepLearning algorithm. We implement and train a Deep Convolutional Neural Network(DCNN) to solve the task of retrieving Lagrangian patches from which darkmatter halos will condense. The volumetric multi-label classification task isturned into a regression problem by means of the euclidean distancetransformation. The network is complemented by an adaptive version of thewatershed algorithm to form the entire protohalo identification pipeline. Weshow that splitting the segmentation problem into two distinct sub-tasks allowsfor training smaller and faster networks, while the predictive power of thepipeline remains the same. The model is trained on synthetic data derived froma single full N-body simulation and achieves deviations of ~10% whenreconstructing the dark matter halo mass function at z=0. This approachrepresents a promising framework for learning highly non-linear relations inthe primordial density field. As a practical application, our method can beused to produce mock dark matter halo catalogues directly from the initialconditions of N-body simulations.

Predicting dark matter halo formation in N-body simulations with deep regression networks