Physics-guided weak-form discovery of reduced-order models for trapped ultracold hydrodynamics

• URL: http://arxiv.org/abs/2406.07519v1
• Date: Tue, 11 Jun 2024 17:50:04 GMT
• Title: Physics-guided weak-form discovery of reduced-order models for trapped ultracold hydrodynamics
• Authors: Reuben R. W. Wang, Daniel Messenger,
• Abstract summary: We study the relaxation of a highly collisional, ultracold but nondegenerate gas of polar molecules. The gas is subject to fluid-gas coupled dynamics that lead to a breakdown of first-order hydrodynamics. We present substantially improved reduced-order models for these same observables.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the relaxation of a highly collisional, ultracold but nondegenerate gas of polar molecules. Confined within a harmonic trap, the gas is subject to fluid-gaseous coupled dynamics that lead to a breakdown of first-order hydrodynamics. An attempt to treat these higher-order hydrodynamic effects was previously made with a Gaussian ansatz and coarse-graining model parameter [R. R. W. Wang & J. L. Bohn, Phys. Rev. A 108, 013322 (2023)], leading to an approximate set of equations for a few collective observables accessible to experiments. Here we present substantially improved reduced-order models for these same observables, admissible beyond previous parameter regimes, discovered directly from particle simulations using the WSINDy algorithm (Weak-form Sparse Identification of Nonlinear Dynamics). The interpretable nature of the learning algorithm enables estimation of previously unknown physical quantities and discovery of model terms with candidate physical mechanisms, revealing new physics in mixed collisional regimes. Our approach constitutes a general framework for data-driven model identification leveraging known physics.

Related papers

• Parametric model reduction of mean-field and stochastic systems via higher-order action matching [1.1509084774278489]
  We learn models of population dynamics of physical systems that feature gradient and mean-field effects. We show that our approach accurately predicts population dynamics over a wide range of parameters and outperforms state-of-the-art diffusion-based and flow-based modeling.
  arXiv  Detail & Related papers  (2024-10-15T19:05:28Z)
• HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction [66.38369833561039]
  HelmFluid is an accurate and interpretable predictor for fluid. Inspired by Helmholtz theorem, we design a HelmDynamics block to learn Helmholtz dynamics. By embedding the HelmDynamics block into a Multiscale Multihead Integral Architecture, HelmFluid can integrate learned Helmholtz dynamics along temporal dimension in multiple spatial scales.
  arXiv  Detail & Related papers  (2023-10-16T16:38:32Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields [65.07940731309856]
  Deep learning has shown great potential for modeling the physical dynamics of complex particle systems such as fluids. In this paper, we consider a partially observable scenario known as fluid dynamics grounding. We propose a differentiable two-stage network named NeuroFluid. It is shown to reasonably estimate the underlying physics of fluids with different initial shapes, viscosity, and densities.
  arXiv  Detail & Related papers  (2022-03-03T15:13:29Z)
• CD-ROM: Complemented Deep-Reduced Order Model [2.02258267891574]
  This paper proposes a deep learning based closure modeling approach for classical POD-Galerkin reduced order models (ROM) The proposed approach is theoretically grounded, using neural networks to approximate well studied operators. The capabilities of the CD-ROM approach are demonstrated on two classical examples from Computational Fluid Dynamics, as well as a parametric case, the Kuramoto-Sivashinsky equation.
  arXiv  Detail & Related papers  (2022-02-22T09:05:06Z)
• Discovering hydrodynamic equations of many-body quantum systems [0.0]
  We develop a new machine-learning framework for automated discovery of effective equations from a limited set of available data. We reproduce previously known hydrodynamic equations, strikingly discover novel equations and provide their derivation. Our approach provides a new interpretable method to study properties of quantum materials and quantum simulators in non-perturbative regimes.
  arXiv  Detail & Related papers  (2021-11-03T17:55:07Z)
• Neural Ordinary Differential Equations for Data-Driven Reduced Order Modeling of Environmental Hydrodynamics [4.547988283172179]
  We explore the use of Neural Ordinary Differential Equations for fluid flow simulation. Test problems we consider include incompressible flow around a cylinder and real-world applications of shallow water hydrodynamics in riverine and estuarine systems. Our findings indicate that Neural ODEs provide an elegant framework for stable and accurate evolution of latent-space dynamics with a promising potential of extrapolatory predictions.
  arXiv  Detail & Related papers  (2021-04-22T19:20:47Z)
• Hybrid Physics and Deep Learning Model for Interpretable Vehicle State Prediction [75.1213178617367]
  We propose a hybrid approach combining deep learning and physical motion models. We achieve interpretability by restricting the output range of the deep neural network as part of the hybrid model. The results show that our hybrid model can improve model interpretability with no decrease in accuracy compared to existing deep learning approaches.
  arXiv  Detail & Related papers  (2021-03-11T15:21:08Z)
• Leveraging Global Parameters for Flow-based Neural Posterior Estimation [90.21090932619695]
  Inferring the parameters of a model based on experimental observations is central to the scientific method. A particularly challenging setting is when the model is strongly indeterminate, i.e., when distinct sets of parameters yield identical observations. We present a method for cracking such indeterminacy by exploiting additional information conveyed by an auxiliary set of observations sharing global parameters.
  arXiv  Detail & Related papers  (2021-02-12T12:23:13Z)
• Learning Unknown Physics of non-Newtonian Fluids [56.9557910899739]
  We extend the physics-informed neural network (PINN) method to learn viscosity models of two non-Newtonian systems. The PINN-inferred viscosity models agree with the empirical models for shear rates with large absolute values but deviate for shear rates near zero. We use the PINN method to solve the momentum conservation equation for non-Newtonian fluid flow using only the boundary conditions.
  arXiv  Detail & Related papers  (2020-08-26T20:41:36Z)

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.