English
Related papers

Related papers: Physics-Consistent Neural Networks for Learning De…

200 papers

Neural networks are a central technique in machine learning. Recent years have seen a wave of interest in applying neural networks to physical systems for which the governing dynamics are known and expressed through differential equations.…

Computational Physics · Physics 2020-01-31 M. Mattheakis , P. Protopapas , D. Sondak , M. Di Giovanni , E. Kaxiras

In the present work, the applicability of physics-augmented neural network (PANN) constitutive models for complex electro-elastic finite element analysis is demonstrated. For the investigations, PANN models for electro-elastic material…

Computational Engineering, Finance, and Science · Computer Science 2024-02-13 Dominik K. Klein , Rogelio Ortigosa , Jesús Martínez-Frutos , Oliver Weeger

The dynamical stability of the iterates during training plays a key role in determining the minima obtained by optimization algorithms. For example, stable solutions of gradient descent (GD) correspond to flat minima, which have been…

Machine Learning · Computer Science 2026-02-17 Rotem Mulayoff , Sebastian U. Stich

Due to divergence instability, the accuracy of low-order conforming finite element methods for nearly incompressible elasticity equations deteriorates as the Lam\'e coefficient $\lambda\to\infty$, or equivalently as the Poisson ratio…

Numerical Analysis · Mathematics 2025-10-24 Josef Dick , Seungchan Ko , Quoc Thong Le Gia , Kassem Mustapha , Sanghyeon Park

We investigate the existence of minimizers of variational models with Eulerian-Lagrangian formulations. We consider energy functionals depending on the deformation of a body, defined on its reference configuration, and an Eulerian map…

Analysis of PDEs · Mathematics 2025-07-22 Marco Bresciani , Manuel Friedrich , Carlos Mora-Corral

The goal of this work is to train a neural network which approximates solutions to the Navier-Stokes equations across a region of parameter space, in which the parameters define physical properties such as domain shape and boundary…

Computational Physics · Physics 2021-06-02 Christopher J Arthurs , Andrew P King

A promising approach to improve climate-model simulations is to replace traditional subgrid parameterizations based on simplified physical models by machine learning algorithms that are data-driven. However, neural networks (NNs) often lead…

Atmospheric and Oceanic Physics · Physics 2021-04-07 Janni Yuval , Paul A. O'Gorman , Chris N. Hill

We consider the dynamics of gradient descent (GD) in overparameterized single hidden layer neural networks with a squared loss function. Recently, it has been shown that, under some conditions, the parameter values obtained using GD achieve…

Machine Learning · Computer Science 2021-05-17 Siddhartha Satpathi , R Srikant

To fully understand, analyze, and determine the behavior of dynamical systems, it is crucial to identify their intrinsic modal coordinates. In nonlinear dynamical systems, this task is challenging as the modal transformation based on the…

Machine Learning · Computer Science 2025-03-13 Abdolvahhab Rostamijavanani , Shanwu Li , Yongchao Yang

Understanding how complex systems respond to perturbations, such as whether they will remain stable or what their most sensitive patterns are, is a fundamental challenge across science and engineering. Traditional stability and receptivity…

Fluid Dynamics · Physics 2026-04-28 Chengyun Wang , Liwei Chen , Nils Thuerey

In this work we present a hybrid physics-based and data-driven learning approach to construct surrogate models for concurrent multiscale simulations of complex material behavior. We start from robust but inflexible physics-based…

Numerical Analysis · Mathematics 2023-02-01 I. B. C. M. Rocha , P. Kerfriden , F. P. van der Meer

Neural surrogate solvers can estimate solutions to partial differential equations in physical problems more efficiently than standard numerical methods, but require extensive high-resolution training data. In this paper, we break this…

We present an approach to numerical homogenization of the elastic response of microstructures. Our work uses deep neural network representations trained on data obtained from direct numerical simulation (DNS) of martensitic phase…

Computational Physics · Physics 2019-01-04 K. Sagiyama , K. Garikipati

Anisotropy in the mechanical response of materials with microstructure is common and yet is difficult to assess and model. To construct accurate response models given only stress-strain data, we employ classical representation theory, novel…

Materials Science · Physics 2022-09-07 Jan N. Fuhg , Nikolaos Bouklas , Reese E. Jones

Shells are ubiquitous thin structures that can undergo large nonlinear elastic deformations while exhibiting combined modes of bending and stretching, and have profound modern applications. In this paper, we have proposed a new Isogeometric…

Soft Condensed Matter · Physics 2022-06-22 Nikhil Padhye , Subodh Kalia

We describe N-body networks, a neural network architecture for learning the behavior and properties of complex many body physical systems. Our specific application is to learn atomic potential energy surfaces for use in molecular dynamics…

Machine Learning · Computer Science 2018-03-06 Risi Kondor

An image-based deep learning framework is developed in this paper to predict damage and failure in microstructure-dependent composite materials. The work is motivated by the complexity and computational cost of high-fidelity simulations of…

Machine Learning · Computer Science 2022-06-07 Reza Sepasdar , Anuj Karpatne , Maryam Shakiba

A growing number of applications in particle physics and beyond use neural networks as unbinned likelihood ratio estimators applied to real or simulated data. Precision requirements on the inference tasks demand a high-level of stability…

High Energy Physics - Phenomenology · Physics 2025-03-04 G. Bruno De Luca , Benjamin Nachman , Eva Silverstein , Henry Zheng

Accurate simulation of fluid flow in porous media is challenging due to complex pore-space geometries and the computational cost of solving the Navier-Stokes equations. This difficulty is particularly important when repeated simulations are…

Machine Learning · Computer Science 2026-05-21 Rafał Topolnicki , Paweł Dłotko , Maciej Matyka

In this paper we present a new strategy to model the subgrid-scale scalar flux in a three-dimensional turbulent incompressible flow using physics-informed neural networks (NNs). When trained from direct numerical simulation (DNS) data,…

Fluid Dynamics · Physics 2021-03-03 Hugo Frezat , Guillaume Balarac , Julien Le Sommer , Ronan Fablet , Redouane Lguensat