Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence

• URL: http://arxiv.org/abs/2606.01470v1
• Date: Sun, 31 May 2026 22:07:38 GMT
• Title: Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence
• Abstract summary: We test whether foundation models can be usefully deployed on laboratory experiments.<n>We investigate the Rayleigh-Taylor instability (RTI), a ubiquitous and demanding fluid instability seen from tabletop flows to supernova explosions.<n>We finetune Walrus, a foundation model for continuum dynamics, on three or fewer DNS realizations and recover key RTI physics over long rollouts.
• Score: 38.48877618728378
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Whether physics foundation models can be usefully deployed on laboratory experiments remains an open question for scientific machine learning (ML). We test this question on the Rayleigh-Taylor instability (RTI), a ubiquitous and demanding fluid instability seen from tabletop flows to supernova explosions, in which small perturbations at a density interface grow into chaotic, multiscale mixing as a lighter fluid accelerates into a heavier one. Standard ML models struggle with RTI, and despite over a century of theoretical, numerical, and experimental work, it carries an unresolved discrepancy between simulation and experiment: the late-time mixing growth rate, $α$, measured in most laboratory experiments ($\sim$ 0.06-0.07), is roughly three times the value from idealized direct numerical simulations (DNS, $\sim$ 0.02). The gap's origin remains debated. These properties make RTI a stringent test for a question that matters well beyond RTI: can foundation models trained only on simulations generalise to sparse, messy, and noisy laboratory settings? We finetune Walrus, a foundation model for continuum dynamics, on three or fewer DNS realizations and recover key RTI physics over long rollouts. Applied zero-shot to sliding-barrier laboratory data, the finetuned model leaves the DNS-like regime and enters the observed growth band, having never seen a single experimental sample. These results provide independent, data-driven evidence that initial conditions play a crucial role in the longstanding sim-experiment gap in $α$. The model also generalises zero-shot to stable stratification, a buoyancy regime absent from training, correctly slowing mixing-layer growth. Together, our results show that foundation models can generalise well beyond their training data, predicting laboratory behavior and unseen physical regimes, opening new ways to probe longstanding simulation-experiment gaps.

Related papers

• Bridging the Simulation-to-Experiment Gap with Generative Models using Adversarial Distribution Alignment [51.246114581338865]
  A fundamental challenge in science and engineering is the simulation-to-experiment gap.<n>We propose a data-driven distribution alignment framework that bridges this gap.<n>We prove that our method recovers the target observable distribution, even with multiple, potentially correlated observables.
  arXiv  Detail & Related papers  (2026-04-01T17:21:33Z)
• Differentiable Physics-Neural Models enable Learning of Non-Markovian Closures for Accelerated Coarse-Grained Physics Simulations [0.11874952582465602]
  This work presents a hybrid physics-neural model that predicts scalar transport in a complex domain orders of magnitude faster than the 3D simulation.<n>Overall results show that this differentiable physics-neural framework enables fast, accurate, and generalizable coarse-grained surrogates for physical phenomena.
  arXiv  Detail & Related papers  (2025-11-26T13:13:30Z)
• Beyond Force Metrics: Pre-Training MLFFs for Stable MD Simulations [5.913538953257869]
  Machine-learning force fields (MLFFs) have emerged as a promising solution for speeding up ab initio molecular dynamics (MD) simulations.<n>In this work, we employ GemNet-T, a graph neural network model, as an MLFF and investigate two training strategies.<n>We find that lower force errors do not necessarily guarantee stable MD simulations.
  arXiv  Detail & Related papers  (2025-06-17T00:58:56Z)
• MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback [136.27567671480156]
  We introduce experiment-guided ranking, which prioritizes hypotheses based on feedback from prior tests.<n>We frame experiment-guided ranking as a sequential decision-making problem.<n>Our approach significantly outperforms pre-experiment baselines and strong ablations.
  arXiv  Detail & Related papers  (2025-05-23T13:24:50Z)
• Surrogate-based multiscale analysis of experiments on thermoplastic composites under off-axis loading [0.0]
  We present a surrogate-based multiscale approach to model constant strain-rate and creep experiments on unidirectional thermoplastic composites under off-axis loading.<n>Results show better agreement with experiments than the single-scale micromechanical approach over a wide range settings.
  arXiv  Detail & Related papers  (2025-01-17T13:39:10Z)
• Physics-enhanced Neural Operator for Simulating Turbulent Transport [9.923888452768919]
  This paper presents a physics-enhanced neural operator (PENO) that incorporates physical knowledge of partial differential equations (PDEs) to accurately model flow dynamics. The proposed method is evaluated through its performance on two distinct sets of 3D turbulent flow data.
  arXiv  Detail & Related papers  (2024-05-31T20:05:17Z)
• Fusing Neural and Physical: Augment Protein Conformation Sampling with Tractable Simulations [27.984190594059868]
  generative models have been leveraged as a surrogate sampler to obtain conformation ensembles with orders of magnitude faster. In this work, we explore the few-shot setting of such pre-trained generative sampler which incorporates MD simulations in a tractable manner.
  arXiv  Detail & Related papers  (2024-02-16T03:48:55Z)
• A Multi-Grained Symmetric Differential Equation Model for Learning Protein-Ligand Binding Dynamics [73.35846234413611]
  In drug discovery, molecular dynamics (MD) simulation provides a powerful tool for predicting binding affinities, estimating transport properties, and exploring pocket sites. We propose NeuralMD, the first machine learning (ML) surrogate that can facilitate numerical MD and provide accurate simulations in protein-ligand binding dynamics. We demonstrate the efficiency and effectiveness of NeuralMD, achieving over 1K$times$ speedup compared to standard numerical MD simulations.
  arXiv  Detail & Related papers  (2024-01-26T09:35:17Z)
• Machine learning enabled experimental design and parameter estimation for ultrafast spin dynamics [54.172707311728885]
  We introduce a methodology that combines machine learning with Bayesian optimal experimental design (BOED) Our method employs a neural network model for large-scale spin dynamics simulations for precise distribution and utility calculations in BOED. Our numerical benchmarks demonstrate the superior performance of our method in guiding XPFS experiments, predicting model parameters, and yielding more informative measurements within limited experimental time.
  arXiv  Detail & Related papers  (2023-06-03T06:19:20Z)
• Deep Bayesian Active Learning for Accelerating Stochastic Simulation [74.58219903138301]
  Interactive Neural Process (INP) is a deep active learning framework for simulations and with active learning approaches. For active learning, we propose a novel acquisition function, Latent Information Gain (LIG), calculated in the latent space of NP based models. The results demonstrate STNP outperforms the baselines in the learning setting and LIG achieves the state-of-the-art for active learning.
  arXiv  Detail & Related papers  (2021-06-05T01:31:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.