arrow
Return

Numerical error estimation with physics informed neural network

delete2025-06-09
delete0
PRE
AI
A
Adhika Satyadharma
H
Heng-Chuan Kan
M
Ming‐Jyh Chern
C
Chunying Yu
DOI:10.1016/j.compfluid.2025.106700delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• Develop a framework that utilize PINN to estimate numerical error of a simulation data. • Demonstrate that the estimation does work accurately and reliably. • The estimation works with a single simulation dataset. • The estimation works on fine mesh, coarse mesh and even if it is outside the asymptotic range.

Journal

C
Computers and Fluids
IF:
3
Papers:
333
Citations:
1.4W

Organization

No organization information available
Cited Papers

Cited Papers

errShare
errSave
Algorithm 778: L-BFGS-B
err1997-12-01
err0
errOAAI
errCiyou Zhu; Richard H. Byrd; Peihuang Lu; Jorge Nocedal
errShare
errSave
Limitations of Richardson Extrapolation and Some Possible Remedies
err2005-04-28
err0
PREAI
errIsmail Celik; Jun Li; Gusheng Hu; Christian Shaffer
errShare
errSave
Physics-informed neural networks for inverse problems in supersonic flows
err2022-10-01
err152
errOAAI
errJagtap, Ameya D.; Mao, Zhiping; Adams, Nikolaus; Karniadakis, George Em
errShare
errSave
researcher View more