Estimating the triaxiality of massive clusters from 2D observables in MillenniumTNG with machine learning

TL;DR

This paper introduces a deep learning model combining CNN and GNN to estimate the 3D triaxiality and orientations of massive galaxy clusters from 2D observables, improving accuracy over spherical assumptions.

Contribution

It presents a novel multi-modal fusion neural network that accurately infers galaxy cluster geometry from multi-wavelength images and graph-based observables.

Findings

Improves cluster geometry estimation by 30% compared to spherical assumption.

Achieves an R^2 score of 0.85 for major axis length estimation.

Correctly classifies 71% of prolate clusters with elongated line-of-sight orientations.

Abstract

Properties of massive galaxy clusters, such as mass abundance and concentration, are sensitive to cosmology, making cluster statistics a powerful tool for cosmological studies. However, favoring a more simplified, spherically symmetric model for galaxy clusters can lead to biases in the estimates of cluster properties. In this work, we present a deep-learning approach for estimating the triaxiality and orientations of massive galaxy clusters (those with masses $\gtrsim 10^{14}\,M_\odot h^{-1}$) from 2D observables. We utilize the flagship hydrodynamical volume of the suite of cosmological-hydrodynamical MillenniumTNG (MTNG) simulations as our ground truth. Our model combines the feature extracting power of a convolutional neural network (CNN) and the message passing power of a graph neural network (GNN) in a multi-modal, fusion network. Our model is able to extract 3D geometry information from 2D idealized cluster multi-wavelength images (soft X-ray, medium X-ray, hard X-ray and tSZ effect) and mathematical graph representations of 2D cluster member observables (line-of-sight radial velocities, 2D projected positions and V-band luminosities). Our network improves cluster geometry estimation in MTNG by $30\%$ compared to assuming spherical symmetry. We report an $R^2 = 0.85$ regression score for estimating the major axis length of triaxial clusters and correctly classifying $71\%$ of prolate clusters with elongated orientations along our line-of-sight.