English
Related papers

Related papers: (U)NFV: Supervised and Unsupervised Neural Finite …

200 papers

We consider the design of structure-preserving discretization methods for the solution of systems of boundary controlled Partial Differential Equations (PDEs) thanks to the port-Hamiltonian formalism. We first provide a novel general…

Numerical Analysis · Mathematics 2020-09-30 Andrea Brugnoli , Ghislain Haine , Anass Serhani , Xavier Vasseur

Physics-informed neural networks (PINNs) have shown remarkable prospects in solving partial differential equations (PDEs) involving fluid mechanics. However, the method has so far succeeded only in inviscid flows and incompressible viscous…

Fluid Dynamics · Physics 2026-02-24 Jiahao Song , Wenbo Cao , Weiwei Zhang

Computational fluid dynamics (CFD) is a branch of fluid mechanics that uses numerical methods to solve fluid flows. The finite volume method (FVM) is an important one. In FVM, space is discretized to many grid cells. When the number of grid…

Trained neural networks (NN) have attractive features for closing governing equations. There are many methods that are showing promise, but all can fail in cases when small errors consequentially violate physical reality, such as a solution…

Machine Learning · Computer Science 2024-12-05 Seung Won Suh , Jonathan F MacArt , Luke N Olson , Jonathan B Freund

We present a new divergence-free and well-balanced hybrid FV/FE scheme for the incompressible viscous and resistive MHD equations on unstructured mixed-element meshes in 2 and 3 space dimensions. The equations are split into subsystems. The…

Numerical Analysis · Mathematics 2025-01-29 F. Fambri , E. Zampa , S. Busto , L. Río-Martín , F. Hindenlang , E. Sonnendrücker , M. Dumbser

Calibration of stochastic local volatility (SLV) models to their underlying local volatility model is often performed by numerically solving a two-dimensional non-linear forward Kolmogorov equation. We propose a novel finite volume (FV)…

Numerical Analysis · Mathematics 2016-11-10 Maarten Wyns , Jacques Du Toit

Solving high dimensional partial differential equations (PDEs) has historically posed a considerable challenge when utilizing conventional numerical methods, such as those involving domain meshes. Recent advancements in the field have seen…

Numerical Analysis · Mathematics 2024-02-05 Xiaokai Huo , Hailiang Liu

A general procedure to construct a class of simple and efficient high resolution Total Variation Diminishing (TVD) schemes for non-linear hyperbolic conservation laws by introducing anti-diffusive terms with the flux limiters is presented.…

Numerical Analysis · Mathematics 2007-05-23 Ritesh Kumar , M. K. Kadalbajoo

We propose an architecture that augments the Flux Neural Operator (Flux NO), which combines the classical finite volume method (FVM) with neural operators, with ViT-based context injection. Our model is formulated as a hypernetwork: it…

Machine Learning · Computer Science 2026-05-08 Taeyoung Kim , Joon-Hyuk Ko

We consider solving complex spatiotemporal dynamical systems governed by partial differential equations (PDEs) using frequency domain-based discrete learning approaches, such as Fourier neural operators. Despite their widespread use for…

Machine Learning · Computer Science 2024-07-17 Qingsong Xu , Nils Thuerey , Yilei Shi , Jonathan Bamber , Chaojun Ouyang , Xiao Xiang Zhu

High-order reconstruction schemes for the solution of hyperbolic conservation laws in orthogonal curvilinear coordinates are revised in the finite volume approach. The formulation employs a piecewise polynomial approximation to the…

Computational Physics · Physics 2015-06-19 A. Mignone

Numerical approximations of partial differential equations (PDEs) are routinely employed to formulate the solution of physics, engineering, and mathematical problems involving functions of several variables, such as the propagation of heat…

Machine learning methods have been lately used to solve partial differential equations (PDEs) and dynamical systems. These approaches have been developed into a novel research field known as scientific machine learning in which techniques…

Machine Learning · Computer Science 2022-12-12 Junho Choi , Namjung Kim , Youngjoon Hong

In this work we present an application of modern deep learning methodologies to the numerical solution of partial differential equations in transport models. More specifically, we employ a supervised deep neural network that takes into…

Numerical Analysis · Mathematics 2021-02-10 Eduardo Abreu , Joao B. Florindo

The purpose of this work is to propose a novel a posteriori finite volume subcell limiter technique for the Discontinuous Galerkin finite element method for nonlinear systems of hyperbolic conservation laws in multiple space dimensions that…

Numerical Analysis · Mathematics 2015-03-11 Michael Dumbser , Olindo Zanotti , Raphael Loubere , Steven Diot

This article focuses on the finite volume method (FVM) as an instrument tool to deal with the non-linear collisional-induced breakage equation (CBE) that arises in the particulate process. Notably, we consider the non-conservative…

Numerical Analysis · Mathematics 2024-11-27 Sanjiv Kumar Bariwal , Rajesh Kumar

Recent works have shown that deep neural networks can be employed to solve partial differential equations, giving rise to the framework of physics informed neural networks. We introduce a generalization for these methods that manifests as a…

Numerical Analysis · Mathematics 2021-03-25 Remco van der Meer , Cornelis Oosterlee , Anastasia Borovykh

We propose a concept of dissipative weak (DW) solutions for the Navier-Stokes-Korteweg (NSK) system and prove conditional convergence of a structure-preserving finite volume scheme towards such a solution. DW solutions provide a generalized…

Numerical Analysis · Mathematics 2026-04-20 Jan Giesselmann , Philipp Öffner , Robert Sauerborn

Many problems in electrical engineering or fluid mechanics can be modeled by parabolic-elliptic interface problems, where the domain for the exterior elliptic problem might be unbounded. A possibility to solve this class of problems…

Numerical Analysis · Mathematics 2018-05-15 Christoph Erath , Robert Schorr

The evolution of dynamical systems is generically governed by nonlinear partial differential equations (PDEs), whose solution, in a simulation framework, requires vast amounts of computational resources. In this work, we present a novel…

Machine Learning · Computer Science 2023-09-01 Michael Rotman , Amit Dekel , Ran Ilan Ber , Lior Wolf , Yaron Oz