SuperAdjoint: super-resolution neural networks in adjoint-based error estimation

DOI10.1016/J.CAM.2023.115722MaRDI QIDQ6489238

Thomas P. Hunter, Steven J. Hulshoff

Publication date: 19 April 2024

Published in: Journal of Computational and Applied Mathematics (Search for Journal in Brave)

zbMATH Keywords

adjoint methodoutput error estimationgoal-oriented mesh adaptationsuper-resolution neural networks

Mathematics Subject Classification ID

Basic methods in fluid mechanics (76Mxx) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65Mxx) Numerical methods for partial differential equations, boundary value problems (65Nxx)

Cites Work

• Progress in adjoint error correction for integral functionals
• An adaptive finite element scheme for transient problems in CFD
• Adjoint-based \textit{hp}-adaptivity on anisotropic meshes for high-order compressible flow simulations
• Anisotropic grid adaptation for functional outputs: application to two-dimensional viscous flows.
• An enhanced algorithm for online proper orthogonal decomposition and its parallelization for unsteady simulations
• A robust framework for identification of PDEs from noisy data
• An artificial neural network framework for reduced order modeling of transient flows
• Output-based adaptive aerodynamic simulations using convolutional neural networks
• A new approach to computational turbulence modeling
• Machine Learning for Fluid Mechanics
• A POD goal‐oriented error measure for mesh optimization
• Unsupervised deep learning for super-resolution reconstruction of turbulence

This page was built for publication: SuperAdjoint: super-resolution neural networks in adjoint-based error estimation