Learning Closed-form Equations for Subgrid-scale Closures from High-fidelity Data: Promises and Challenges
- URL: http://arxiv.org/abs/2306.05014v3
- Date: Sun, 7 Jul 2024 13:40:20 GMT
- Title: Learning Closed-form Equations for Subgrid-scale Closures from High-fidelity Data: Promises and Challenges
- Authors: Karan Jakhar, Yifei Guan, Rambod Mojgani, Ashesh Chattopadhyay, Pedram Hassanzadeh,
- Abstract summary: We learn closures from filtered numerical simulations of 2D turbulence and Rayleigh-B'enard convection.
We show that discovered closures are consistent with the leading term of the Taylor-series.
These findings are relevant to closure modeling of any multi-scale system.
- Score: 1.2582887633807602
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: There is growing interest in discovering interpretable, closed-form equations for subgrid-scale (SGS) closures/parameterizations of complex processes in Earth systems. Here, we apply a common equation-discovery technique with expansive libraries to learn closures from filtered direct numerical simulations of 2D turbulence and Rayleigh-B\'enard convection (RBC). Across common filters (e.g., Gaussian, box), we robustly discover closures of the same form for momentum and heat fluxes. These closures depend on nonlinear combinations of gradients of filtered variables, with constants that are independent of the fluid/flow properties and only depend on filter type/size. We show that these closures are the nonlinear gradient model (NGM), which is derivable analytically using Taylor-series. Indeed, we suggest that with common (physics-free) equation-discovery algorithms, for many common systems/physics, discovered closures are consistent with the leading term of the Taylor-series (except when cutoff filters are used). Like previous studies, we find that large-eddy simulations with NGM closures are unstable, despite significant similarities between the true and NGM-predicted fluxes (correlations $> 0.95$). We identify two shortcomings as reasons for these instabilities: in 2D, NGM produces zero kinetic energy transfer between resolved and subgrid scales, lacking both diffusion and backscattering. In RBC, potential energy backscattering is poorly predicted. Moreover, we show that SGS fluxes diagnosed from data, presumed the ''truth'' for discovery, depend on filtering procedures and are not unique. Accordingly, to learn accurate, stable closures in future work, we propose several ideas around using physics-informed libraries, loss functions, and metrics. These findings are relevant to closure modeling of any multi-scale system.
Related papers
- Beyond Closure Models: Learning Chaotic-Systems via Physics-Informed Neural Operators [78.64101336150419]
Predicting the long-term behavior of chaotic systems is crucial for various applications such as climate modeling.
An alternative approach to such a full-resolved simulation is using a coarse grid and then correcting its errors through a temporalittext model.
We propose an alternative end-to-end learning approach using a physics-informed neural operator (PINO) that overcomes this limitation.
arXiv Detail & Related papers (2024-08-09T17:05:45Z) - Weak Collocation Regression for Inferring Stochastic Dynamics with
L\'{e}vy Noise [8.15076267771005]
We propose a weak form of the Fokker-Planck (FP) equation for extracting dynamics with L'evy noise.
Our approach can simultaneously distinguish mixed noise types, even in multi-dimensional problems.
arXiv Detail & Related papers (2024-03-13T06:54:38Z) - Closed-form Filtering for Non-linear Systems [83.91296397912218]
We propose a new class of filters based on Gaussian PSD Models, which offer several advantages in terms of density approximation and computational efficiency.
We show that filtering can be efficiently performed in closed form when transitions and observations are Gaussian PSD Models.
Our proposed estimator enjoys strong theoretical guarantees, with estimation error that depends on the quality of the approximation and is adaptive to the regularity of the transition probabilities.
arXiv Detail & Related papers (2024-02-15T08:51:49Z) - An invariance constrained deep learning network for PDE discovery [7.7669872521725525]
In this study, we propose an invariance constrained deep learning network (ICNet) for the discovery of partial differential equations (PDEs)
We embedded the fixed and possible terms into the loss function of neural network, significantly countering the effect of sparse data with high noise.
We select the 2D Burgers equation, the equation of 2D channel flow over an obstacle, and the equation of 3D intracranial aneurysm as examples to verify the superiority of the ICNet for fluid mechanics.
arXiv Detail & Related papers (2024-02-06T06:28:17Z) - Machine learning of hidden variables in multiscale fluid simulation [77.34726150561087]
Solving fluid dynamics equations often requires the use of closure relations that account for missing microphysics.
In our study, a partial differential equation simulator that is end-to-end differentiable is used to train judiciously placed neural networks.
We show that this method enables an equation based approach to reproduce non-linear, large Knudsen number plasma physics.
arXiv Detail & Related papers (2023-06-19T06:02:53Z) - Score-based Diffusion Models in Function Space [140.792362459734]
Diffusion models have recently emerged as a powerful framework for generative modeling.
We introduce a mathematically rigorous framework called Denoising Diffusion Operators (DDOs) for training diffusion models in function space.
We show that the corresponding discretized algorithm generates accurate samples at a fixed cost independent of the data resolution.
arXiv Detail & Related papers (2023-02-14T23:50:53Z) - A piece-wise constant approximation for non-conjugate Gaussian Process
models [0.0]
This paper proposes to approximate the inverse-link function, which is necessary when working with non-Gaussian likelihoods.
It will be shown that this yields a closed form solution for the corresponding SVGP lower bound.
In addition, it is demonstrated how the piece-wise constant function itself can be optimized, resulting in an inverse-link function that can be learnt from the data at hand.
arXiv Detail & Related papers (2022-04-22T08:53:54Z) - Gradient flows and randomised thresholding: sparse inversion and
classification [0.0]
Sparse inversion and classification problems are ubiquitous in modern data science and imaging.
In classification, we consider, e.g., the sum of a data fidelity term and a non-smooth Ginzburg--Landau energy.
Standard (sub)gradient descent methods have shown to be inefficient when approaching such problems.
arXiv Detail & Related papers (2022-03-22T09:21:14Z) - The Schr\"odinger Bridge between Gaussian Measures has a Closed Form [101.79851806388699]
We focus on the dynamic formulation of OT, also known as the Schr"odinger bridge (SB) problem.
In this paper, we provide closed-form expressions for SBs between Gaussian measures.
arXiv Detail & Related papers (2022-02-11T15:59:01Z) - Large-Scale Wasserstein Gradient Flows [84.73670288608025]
We introduce a scalable scheme to approximate Wasserstein gradient flows.
Our approach relies on input neural networks (ICNNs) to discretize the JKO steps.
As a result, we can sample from the measure at each step of the gradient diffusion and compute its density.
arXiv Detail & Related papers (2021-06-01T19:21:48Z) - A machine learning framework for LES closure terms [0.0]
We derive a consistent framework for LES closure models, with special emphasis laid upon the incorporation of implicit discretization-based filters and numerical approximation errors.
We compute the exact closure terms for the different LES filter functions from direct numerical simulation results of decaying homogeneous isotropic turbulence.
For the given application, the GRU architecture clearly outperforms the networks in terms of accuracy.
arXiv Detail & Related papers (2020-10-01T08:42:37Z)
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.