An official website of the United States government
Abstract The rapid advancement of large-scale cosmological simulations has opened new avenues for cosmological and astrophysical research. However, the increasing diversity among cosmological simulation models presents a challenge to therobustness. In this work, we develop the Model-Insensitive ESTimator (Miest), a machine that canrobustlyestimate the cosmological parameters, Ωmandσ8, from neural hydrogen maps of simulation models in the Cosmology and Astrophysics with MachinE Learning Simulations project—IllustrisTNG,SIMBA, Astrid, and SWIFT-Eagle. An estimator is consideredrobustif it possesses a consistent predictive power across all simulations, including those used during the training phase. We train our machine using multiple simulation models and ensure that it only extracts common features between the models while disregarding the model-specific features. This allows us to develop a novel model that is capable of accurately estimating parameters across a range of simulation models, without being biased toward any particular model. Upon the investigation of the latent space—a set of summary statistics, we find that the implementation ofrobustnessleads to the blending of latent variables across different models, demonstrating the removal of model-specific features. In comparison to a standard machine lackingrobustness, the average performance of Mieston the unseen simulations during the training phase has been improved by ∼17% for Ωmand 38% forσ8. By using a machine learning approach that can extractrobust, yet physical features, we hope to improve our understanding of galaxy formation and evolution in a (subgrid) model-insensitive manner, and ultimately, gain insight into the underlying physical processes responsible forrobustness.
more »
« less
This content will become publicly available on October 27, 2026
Detecting model misspecification in cosmology with scale-dependent normalizing flows
Abstract Current and upcoming cosmological surveys will produce unprecedented amounts of high-dimensional data, which require complex high-fidelity forward simulations to accurately model both physical processes and systematic effects which describe the data generation process. However, validating whether our theoretical models accurately describe the observed datasets remains a fundamental challenge. An additional complexity to this task comes from choosing appropriate representations of the data which retain all the relevant cosmological information, while reducing the dimensionality of the original dataset. In this work we present a novel framework combining scale-dependent neural summary statistics with normalizing flows to detect model misspecification in cosmological simulations through Bayesian evidence estimation. By conditioning our neural network models for data compression and evidence estimation on the smoothing scale, we systematically identify where theoretical models break down in a data-driven manner. We demonstrate a first application of our approach using simulated total matter and gas density fields from three hydrodynamic simulation suites with different subgrid physics implementations.
more »
« less
- Award ID(s):
- 2019786
- PAR ID:
- 10648151
- Publisher / Repository:
- IOP Publishing
- Date Published:
- Journal Name:
- Machine Learning: Science and Technology
- Volume:
- 6
- Issue:
- 4
- ISSN:
- 2632-2153
- Page Range / eLocation ID:
- 045020
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
ABSTRACT We present a new suite of over 1500 cosmological N-body simulations with varied warm dark matter (WDM) models ranging from 2.5 to 30 keV. We use these simulations to train Convolutional Neural Networks (CNNs) to infer WDM particle masses from images of DM field data. Our fiducial setup can make accurate predictions of the WDM particle mass up to 7.5 keV with an uncertainty of ±0.5 keV at a 95 per cent confidence level from (25 h−1Mpc)2 maps. We vary the image resolution, simulation resolution, redshift, and cosmology of our fiducial setup to better understand how our model is making predictions. Using these variations, we find that our models are most dependent on simulation resolution, minimally dependent on image resolution, not systematically dependent on redshift, and robust to varied cosmologies. We also find that an important feature to distinguish between WDM models is present with a linear size between 100 and 200 h−1 kpc. We compare our fiducial model to one trained on the power spectrum alone and find that our field-level model can make two times more precise predictions and can make accurate predictions to two times as massive WDM particle masses when used on the same data. Overall, we find that the field-level data can be used to accurately differentiate between WDM models and contain more information than is captured by the power spectrum. This technique can be extended to more complex DM models and opens up new opportunities to explore alternative DM models in a cosmological environment.more » « less
-
Abstract The modeling of multi-scale and multi-physics complex systems typically involves the use of scientific software that can optimally leverage extreme scale computing. Despite major developments in recent years, these simulations continue to be computationally intensive and time consuming. Here we explore the use of AI to accelerate the modeling of complex systems at a fraction of the computational cost of classical methods, and present the first application of physics informed neural operators (NOs) (PINOs) to model 2D incompressible magnetohydrodynamics (MHD) simulations. Our AI models incorporate tensor Fourier NOs as their backbone, which we implemented with theTensorLYpackage. Our results indicate that PINOs can accurately capture the physics of MHD simulations that describe laminar flows with Reynolds numbers . We also explore the applicability of our AI surrogates for turbulent flows, and discuss a variety of methodologies that may be incorporated in future work to create AI models that provide a computationally efficient and high fidelity description of MHD simulations for a broad range of Reynolds numbers. The scientific software developed in this project is released with this manuscript.more » « less
-
ABSTRACT Arkenstone is a new scheme that allows multiphase, stellar feedback-driven winds to be included in coarse resolution cosmological simulations. The evolution of galactic winds and their subsequent impact on the circumgalactic medium are altered by exchanges of mass, energy, momentum, and metals between their component phases. These exchanges are governed by complex, small-scale physical processes that cannot be resolved in cosmological simulations. In this second presentation paper, we describe Arkenstone’s novel cloud particle approach for modelling unresolvable cool clouds entrained in hot, fast winds. This general framework allows models of the cloud–wind interaction, derived from state-of-the-art high-resolution simulations, to be applied in a large-scale context. In this work, we adopt a cloud evolution model that captures simultaneous cloud mass loss to and gain from the ambient hot phase via turbulent mixing and radiative cooling, respectively. We demonstrate the scheme using non-cosmological idealized simulations of a galaxy with a realistic circumgalactic medium component, using the arepo code. We show that the ability of a high-specific energy wind component to perform preventative feedback may be limited by heavy loading of cool clouds coupled into it. We demonstrate that the diverging evolution of clouds of initially differing masses leads to a complex velocity field for the cool phase and a cloud mass function that varies both spatially and temporally in a non-trivial manner. These latter two phenomena can manifest in the simulation because of our choice of a Lagrangian discretization of the cloud population, in contrast to other proposed schemes.more » « less
-
Abstract Traditional star formation subgrid models implemented in cosmological galaxy formation simulations, such as that of V. Springel & L. Hernquist (hereafter SH03), employ adjustable parameters to satisfy constraints measured in the local Universe. In recent years, however, theory and spatially resolved simulations of the turbulent, multiphase, star-forming interstellar medium (ISM) have begun to produce new first-principles models, which when fully developed can replace traditional subgrid prescriptions. This approach has advantages of being physically motivated and predictive rather than empirically tuned, and allowing for varying environmental conditions rather than being tied to local-Universe conditions. As a prototype of this new approach, by combining calibrations from the TIGRESS numerical framework with the pressure-regulated feedback-modulated (PRFM) theory, simple formulae can be obtained for both the gas depletion time and an effective equation of state. Considering galaxies in TNG50, we compare the “native” simulation outputs with postprocessed predictions from PRFM. At TNG50 resolution, the total midplane pressure is nearly equal to the total ISM weight, indicating that galaxies in TNG50 are close to satisfying vertical equilibrium. The measured gas scale height is also close to theoretical equilibrium predictions. The slopes of the effective equations of states are similar, but with effective velocity dispersion normalization from SH03 slightly larger than that from current TIGRESS simulations. Because of this and the decrease in PRFM feedback yield at high pressure, the PRFM model predicts shorter gas depletion times than the SH03 model at high densities and redshift. Our results represent a first step toward implementing new, numerically calibrated subgrid algorithms in cosmological galaxy formation simulations.more » « less
