ASTROLABE: A 3D Particle-Level Surrogate for Cosmology Simulation with Physical Flow Matching
Abstract
The microphysics of dark matter (DM) is imprinted on cosmological structure across an enormous dynamic range. Nonlinear cosmological observables are most reliably modeled with N-body and hydrodynamic simulations. However, systematic N-body scans over DM theory space are prohibitively expensive. Machine learning emulators provide a possible solution, but are currently limited by either low resolution or only the ability to emulate specific observables. We introduce Astrolabe, a flow-matching-based generative emulator designed to be free of both constraints. Astrolabe acts directly on the 6N phase-space coordinates of N individual particles. With no voxel grid in the output, there is no voxel-resolution ceiling, and in principle any observable can be measured from inference. Astrolabe is computationally tractable via a field-particle hybrid transformer in which every particle cross-attends to multiscale field tokens, so compute and memory are linear in N. Astrolabe incorporates physical flow matching by taking the prior distribution for the flow to be approximate COmoving Lagrangian Acceleration (COLA)-based coordinates rather than unphysical noise, with momentum and mass conservation enforced at all points along flow time. In the Lambda-CDM cases we test, Astrolabe produces realistic fields with accurate power spectra, halo mass functions, velocity profiles, and halo density profiles. We also observe out-of-distribution generalization, with accurate emulation of dark-acoustic oscillation initial conditions. Astrolabe is also capable of being fine-tuned to simulate very large N and we demonstrate this by emulating a TNG50-3-dark simulation at a fraction of the cost. This method represents a first step toward a general and powerful cosmology simulation surrogate, which may eventually permit the inclusion of baryonic physics and a systematic exploration of richer dark sector interactions.
Related
- A space of inference spaces in the space sciences - parametric Bayesian inference in astronomy, cosmology and particle physics
- Linear Dilaton in Cosmology and Particle Physics
- Merlin: Fast and flexible 3x2pt cosmology with simulation-based inference
- Field-level weak lensing cosmology with $60$ simulations using multifidelity simulation-based inference
- Benchmarking Exact, GP-Emulated, and Simulation-Based Inference for Late-Time Cosmology
BibTeX
@misc{elsharkawy2026astrolabe,
title = {{ASTROLABE: A 3D Particle-Level Surrogate for Cosmology Simulation with Physical Flow Matching}},
author = {Ibrahim Elsharkawy and David Curtin and Yonatan Kahn and Neal Weiner},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.27068},
eprint = {2610.27068},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.27068},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - ASTROLABE: A 3D Particle-Level Surrogate for Cosmology Simulation with Physical Flow Matching
AU - Ibrahim Elsharkawy
AU - David Curtin
AU - Yonatan Kahn
AU - Neal Weiner
PY - 2026
DA - 2026/10/19
PB - arXiv
DO - 10.48550/arxiv.2610.27068
UR - https://arxiv.org/abs/2610.27068
AB - The microphysics of dark matter (DM) is imprinted on cosmological structure across an enormous dynamic range. Nonlinear cosmological observables are most reliably modeled with N-body and hydrodynamic simulations. However, systematic N-body scans over DM theory space are prohibitively expensive. Machine learning emulators provide a possible solution, but are currently limited by either low resolution or only the ability to emulate specific observables. We introduce Astrolabe, a flow-matching-based generative emulator designed to be free of both constraints. Astrolabe acts directly on the 6N phase-space coordinates of N individual particles. With no voxel grid in the output, there is no voxel-resolution ceiling, and in principle any observable can be measured from inference. Astrolabe is computationally tractable via a field-particle hybrid transformer in which every particle cross-attends to multiscale field tokens, so compute and memory are linear in N. Astrolabe incorporates physical flow matching by taking the prior distribution for the flow to be approximate COmoving Lagrangian Acceleration (COLA)-based coordinates rather than unphysical noise, with momentum and mass conservation enforced at all points along flow time. In the Lambda-CDM cases we test, Astrolabe produces realistic fields with accurate power spectra, halo mass functions, velocity profiles, and halo density profiles. We also observe out-of-distribution generalization, with accurate emulation of dark-acoustic oscillation initial conditions. Astrolabe is also capable of being fine-tuned to simulate very large N and we demonstrate this by emulating a TNG50-3-dark simulation at a fraction of the cost. This method represents a first step toward a general and powerful cosmology simulation surrogate, which may eventually permit the inclusion of baryonic physics and a systematic exploration of richer dark sector interactions.
ER -