Mapping Dark-Matter Clusters via Physics-Guided Diffusion Models

2026-03-15

AI Summary

This work addresses the challenge of scaling galaxy cluster mass reconstruction to the hundreds of thousands of systems expected from upcoming surveys, a task hindered by the lack of scalable methods and standardized benchmarks. We propose an end-to-end, fully automated, physics-driven framework that jointly leverages weak and strong gravitational lensing with photometric observations. Central to our approach is a physics-constrained diffusion model serving as a generative prior, enabling high-fidelity dark matter distribution reconstructions without manual tuning. To support multi-redshift, multi-simulation training, we introduce DarkClusters-15k—the largest simulated cluster dataset to date. Our method achieves expert-level accuracy on MACS 1206, surpasses traditional techniques in precision, delivers well-calibrated uncertainty estimates, and completes reconstructions in minutes. Code and dataset are publicly released.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Galaxy clusters are powerful probes of astrophysics and cosmology through gravitational lensing: the clusters' mass, dominated by 85% dark matter, distorts background light. Yet, mass reconstruction lacks the scalability and large-scale benchmarks to process the hundreds of thousands of clusters expected from forthcoming wide-field surveys. We introduce a fully automated method to reconstruct cluster surface mass density from photometry and gravitational lensing observables. Central to our approach is DarkClusters-15k, our new dataset of 15,000 simulated clusters with paired mass and photometry maps, the largest benchmark to date, spanning multiple redshifts and simulation frameworks. We train a plug-and-play diffusion prior on DarkClusters-15k that learns the statistical relationship between mass and light, and draw posterior samples constrained by weak- and strong-lensing observables; this yields principled reconstructions driven by explicit physics, alongside well-calibrated uncertainties. Our approach requires no expert tuning, runs in minutes rather than hours, achieves higher accuracy, and matches expertly-tuned reconstructions of the MACS 1206 cluster. We release our method and DarkClusters-15k to support development and benchmarking for upcoming wide-field cosmological surveys.

Problem

• dark matter
• mass reconstruction
• gravitational lensing
• galaxy clusters
• scalability

Innovation

• physics-guided diffusion models
• dark matter mapping
• gravitational lensing
• mass reconstruction
• DarkClusters-15k