Reconstructing Galaxy Cluster Mass Maps using Score-based Generative Modeling

2024-10-03

arXiv.org

AI Summary

This study addresses the challenge of reconstructing galaxy cluster mass distributions—specifically, projected thermal gas and dark matter densities—from multi-wavelength observations. We introduce, for the first time, a score-based fractional diffusion generative model to enable end-to-end, nonlinear, unbiased, and multi-scale mapping from Sunyaev–Zeldovich (SZ) and X-ray surface brightness images to physical density fields. The method leverages fractional score matching and conditional sampling, trained and validated on hydrodynamical cosmological simulations producing realistic mock observations. Experiments demonstrate radial density profile reconstruction errors below 5%, negligible spectral-domain bias (cross-correlation coefficient ≈ 1), robust discrimination of structural differences across cluster masses, and promising transferability to real observational data. Our key contribution is the development of the first score-based generative framework tailored to galaxy cluster mass map reconstruction, overcoming fundamental limitations of conventional linear or assumption-driven approaches.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

We present a novel approach to reconstruct gas and dark matter projected density maps of galaxy clusters using score-based generative modeling. Our diffusion model takes in mock SZ and X-ray images as conditional observations, and generates realizations of corresponding gas and dark matter maps by sampling from a learned data posterior. We train and validate the performance of our model by using mock data from a hydrodynamical cosmological simulation. The model accurately reconstructs both the mean and spread of the radial density profiles in the spatial domain to within 5%, indicating that the model is able to distinguish between clusters of different sizes. In the spectral domain, the model achieves close-to-unity values for the bias and cross-correlation coefficients, indicating that the model can accurately probe cluster structures on both large and small scales. Our experiments demonstrate the ability of score models to learn a strong, nonlinear, and unbiased mapping between input observables and fundamental density distributions of galaxy clusters. These diffusion models can be further fine-tuned and generalized to not only take in additional observables as inputs, but also real observations and predict unknown density distributions of galaxy clusters.

Problem

• Reconstruct galaxy cluster mass maps using generative modeling
• Generate gas and dark matter maps from mock images
• Learn unbiased mapping between observables and density distributions

Innovation

• Uses score-based generative modeling for reconstruction
• Incorporates mock SZ and X-ray images as inputs
• Learns nonlinear mapping between observables and densities