Reconstruction of Continuous Cosmological Fields from Discrete Tracers with Graph Neural Networks

TL;DR

This paper introduces a hybrid GNN-CNN model that accurately reconstructs 3D cosmological matter fields from discrete galaxy data, enhancing analysis of unobservable cosmic structures.

Contribution

A novel hybrid GNN-CNN architecture with learned grid assignment for improved reconstruction of continuous cosmological fields from discrete tracers.

Findings

Accurate reconstruction of dark matter and electron density fields.

Outperforms traditional cloud-in-cell method.

Applicable to unobservable cosmic fields from observable galaxy data.

Abstract

We develop a hybrid GNN-CNN architecture for the reconstruction of 3-dimensional continuous cosmological matter fields from discrete point clouds, provided by observed galaxy catalogs. Using the CAMELS hydrodynamical cosmological simulations we demonstrate that the proposed architecture allows for an accurate reconstruction of both the dark matter and electron density given observed galaxies and their features. Our approach includes a learned grid assignment scheme that improves over the traditional cloud-in-cell method. Our method can improve cosmological analyses in situations where non-luminous (and thus unobservable) continuous fields need to be estimated from luminous (observable) discrete point cloud tracers.