Probing the baryonic--dark matter connection in galaxy clusters using X-rays with gated recurrent unit neural networks
Abstract
Accurate cluster mass measurements are crucial for cosmology, yet conventional hydrostatic equilibrium (HSE) methods can suffer from systematic biases, particularly in dynamically disturbed systems. We present a gated recurrent unit (GRU) based deep learning framework for predicting three-dimensional mass profiles of galaxy clusters from spherically averaged intra-cluster medium (ICM) radial profiles. By treating ICM profiles as sequential data, the GRU captures radial dependencies and naturally handles profiles with different radial samplings. We train and validate the model using high-resolution hydrodynamical simulations from The Three Hundred Project, achieving unbiased mass predictions with a typical 1σ scatter of ∼5% over most of the cluster region, significantly improving upon HSE estimates. The model provides radius-dependent uncertainty estimates and remains robust against variations in data quality and cluster morphology. When trained jointly on independent simulation suites (GIZMO-SIMBA and GADGET-X), it successfully generalises across both simulations. Feature importance analysis shows that enclosed gas mass is the dominant predictor, with pressure and temperature providing additional information on the radial mass distribution. We further apply the GRU model to X-ray observations of the REXCESS and X-COP cluster samples from XMM-Newton and compare the inferred mass profiles with HSE estimates. The GRU and HSE mass estimates show close agreement for the lower-mass REXCESS sample, while HSE masses are systematically lower than the GRU predictions for the higher-mass X-COP sample, an offset consistent with hydrostatic mass bias. This work provides a data-driven framework for cluster mass inference that bridges simulations and observations and can be extended to multi-wavelength datasets, including Sunyaev-Zel'dovich and optical observations.
Related
- BIND (Baryonic INpainting with Deep learning): A Field-level Emulator for Galaxy Groups and Clusters
- Baryonic assembly bias in X-ray-selected galaxy groups and clusters: insights from the Magneticum simulation
- Probing the γ -ray emission region and the connection to jet ejections in NRAO 150
- Probing Globular Clusters using Gravitational Waves from Inspiraling Stellar-mass Binary Black Holes in Space-based Detector
- Probing Projection Effects in Optically-Selected Clusters with Velocity Dispersions Outliers
BibTeX
@misc{iqbal2026probing,
title = {{Probing the baryonic--dark matter connection in galaxy clusters using X-rays with gated recurrent unit neural networks}},
author = {Asif Iqbal and Subhabrata Majumdar and Weiguang Cui and Elena Rasia and Gabriel W. Pratt and Daniel de Andres},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2607.20721},
eprint = {2607.20721},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.20721},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Probing the baryonic--dark matter connection in galaxy clusters using X-rays with gated recurrent unit neural networks
AU - Asif Iqbal
AU - Subhabrata Majumdar
AU - Weiguang Cui
AU - Elena Rasia
AU - Gabriel W. Pratt
AU - Daniel de Andres
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2607.20721
UR - https://arxiv.org/abs/2607.20721
AB - Accurate cluster mass measurements are crucial for cosmology, yet conventional hydrostatic equilibrium (HSE) methods can suffer from systematic biases, particularly in dynamically disturbed systems. We present a gated recurrent unit (GRU) based deep learning framework for predicting three-dimensional mass profiles of galaxy clusters from spherically averaged intra-cluster medium (ICM) radial profiles. By treating ICM profiles as sequential data, the GRU captures radial dependencies and naturally handles profiles with different radial samplings. We train and validate the model using high-resolution hydrodynamical simulations from The Three Hundred Project, achieving unbiased mass predictions with a typical 1σ scatter of ∼5% over most of the cluster region, significantly improving upon HSE estimates. The model provides radius-dependent uncertainty estimates and remains robust against variations in data quality and cluster morphology. When trained jointly on independent simulation suites (GIZMO-SIMBA and GADGET-X), it successfully generalises across both simulations. Feature importance analysis shows that enclosed gas mass is the dominant predictor, with pressure and temperature providing additional information on the radial mass distribution. We further apply the GRU model to X-ray observations of the REXCESS and X-COP cluster samples from XMM-Newton and compare the inferred mass profiles with HSE estimates. The GRU and HSE mass estimates show close agreement for the lower-mass REXCESS sample, while HSE masses are systematically lower than the GRU predictions for the higher-mass X-COP sample, an offset consistent with hydrostatic mass bias. This work provides a data-driven framework for cluster mass inference that bridges simulations and observations and can be extended to multi-wavelength datasets, including Sunyaev-Zel'dovich and optical observations.
ER -