A deep learning approach to member identification and mass estimation in galaxy clusters
Abstract
Accurate dynamical mass estimates of galaxy clusters are essential for studies of cluster formation and evolution and for cosmological applications. However, interloper galaxies, which are not gravitationally bound to the cluster but are incorrectly identified as members, can bias dynamical mass measurements and increase uncertainties. We developed a probabilistic deep-learning framework for cluster member identification and dynamical mass estimation and tested sensitivity to cluster miscentring and radially dependent incompleteness in controlled mock experiments. We used mock galaxy cluster catalogues to train a two-stage model. A long short-term memory (LSTM) network assigns membership probabilities to galaxies arranged by projected phase-space proximity. These probabilities construct membership-weighted projected phase-space density maps, from which a Bayesian neural network (BNN) infers cluster masses and predictive uncertainties. The LSTM membership probabilities are well calibrated and form an isoprobability envelope in projected phase space, with the ⟨ pmem⟩ = 0.5 contour broadly tracing the empirical member--interloper transition. A threshold of pth = 0.5 balances member completeness and purity, with high completeness within Rproj < r200. Membership weighting lowers the residual scatter of the fiducial BNN mass estimator, BNNMem2D, to σε= 0.120, a 19.5% reduction relative to the unweighted baseline, although predictive uncertainties are not uniformly calibrated across BNN models. Using the brightest cluster galaxy rather than the gravitational centre lowers the median inferred mass by up to 47.6%, with larger reductions at larger centring offsets. By contrast, removing 40% of eligible non-central galaxies within r200 lowers it by 6.1% relative to complete catalogues.
Related
- Galaxy Clusters from the DESI Legacy Imaging Surveys. IV. Alignment of Member Galaxy Orientations at z < 0.5
- Galaxy Clusters from the DESI Legacy Imaging Surveys. IV. Alignment of Member Galaxy Orientations at z < 0.5
- The Deep Learning Halo Definer: A Multimodal Framework for Halo Mass and Gas Fraction Inference on Galaxy Groups and Clusters
- BIND (Baryonic INpainting with Deep learning): A Field-level Emulator for Galaxy Groups and Clusters
- Optimizing Color Selection for Cluster-Member Identification with SuperBIT
BibTeX
@misc{wang2026deep,
title = {{A deep learning approach to member identification and mass estimation in galaxy clusters}},
author = {Zicheng Wang and Liping Fu and Wei Du and Wentao Luo and Wenxiang Pei and Zhu Chen and Zhijian Luo and Yicheng Li and Jiachen Qiu and Haoran Zhao and Kaiwen Mai and Weiming Ren},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.39546},
eprint = {2610.39546},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.39546},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - A deep learning approach to member identification and mass estimation in galaxy clusters
AU - Zicheng Wang
AU - Liping Fu
AU - Wei Du
AU - Wentao Luo
AU - Wenxiang Pei
AU - Zhu Chen
AU - Zhijian Luo
AU - Yicheng Li
AU - Jiachen Qiu
AU - Haoran Zhao
AU - Kaiwen Mai
AU - Weiming Ren
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2610.39546
UR - https://arxiv.org/abs/2610.39546
AB - Accurate dynamical mass estimates of galaxy clusters are essential for studies of cluster formation and evolution and for cosmological applications. However, interloper galaxies, which are not gravitationally bound to the cluster but are incorrectly identified as members, can bias dynamical mass measurements and increase uncertainties. We developed a probabilistic deep-learning framework for cluster member identification and dynamical mass estimation and tested sensitivity to cluster miscentring and radially dependent incompleteness in controlled mock experiments. We used mock galaxy cluster catalogues to train a two-stage model. A long short-term memory (LSTM) network assigns membership probabilities to galaxies arranged by projected phase-space proximity. These probabilities construct membership-weighted projected phase-space density maps, from which a Bayesian neural network (BNN) infers cluster masses and predictive uncertainties. The LSTM membership probabilities are well calibrated and form an isoprobability envelope in projected phase space, with the ⟨ p_mem⟩ = 0.5 contour broadly tracing the empirical member--interloper transition. A threshold of p_th = 0.5 balances member completeness and purity, with high completeness within R_proj < r_200. Membership weighting lowers the residual scatter of the fiducial BNN mass estimator, BNN^Mem_2D, to σ_ε= 0.120, a 19.5% reduction relative to the unweighted baseline, although predictive uncertainties are not uniformly calibrated across BNN models. Using the brightest cluster galaxy rather than the gravitational centre lowers the median inferred mass by up to 47.6%, with larger reductions at larger centring offsets. By contrast, removing 40% of eligible non-central galaxies within r_200 lowers it by 6.1% relative to complete catalogues.
ER -