Separable physics-informed DeepONet: breaking the curse of dimensionality in physics-informed machine learning

DOI10.1016/J.CMA.2024.117586MaRDI QIDQ6669073zbMATH OpenFDO

Authors Luis Mandl, Somdatta Goswami, Tim Ricken

Publication date 22 January 2025

Published in Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

zbMATH Keywords

separation of variablesscientific machine learningphysics-informedneural operator

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX) Quantum theory (81-XX)

Recommendations

• A dimension-augmented physics-informed neural network (DaPINN) with high level accuracy and efficiency
• Navigating PINNs via maximum residual-based continuous distribution
• Hutchinson trace estimation for high-dimensional and high-order physics-informed neural networks
• Diminishing spectral bias in physics-informed neural networks using spatially-adaptive Fourier feature encoding

Cites work

• scientific article; zbMATH DE number 6982909 (Why is no real title available?)
• A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data
• A physics-informed variational DeepONet for predicting crack path in quasi-brittle materials
• A tensor approximation method based on ideal minimal residual formulations for the solution of high-dimensional problems
• Energy-dissipative evolutionary deep operator neural networks
• General theory of three-dimensional consolidation.
• MIONet: Learning Multiple-Input Operators via Tensor Product
• Multifidelity deep operator networks for data-driven and physics-informed problems
• On the influence of over-parameterization in manifold based surrogates and deep neural operators
• PGD reduced-order modeling for structural dynamics applications
• Phase-field DeepONet: physics-informed deep operator neural network for fast simulations of pattern formation governed by gradient flows of free-energy functionals
• Respecting causality for training physics-informed neural networks
• SimLivA-modeling ischemia-reperfusion injury in the liver: a first step towards a clinical decision support tool
• Tensor Rank and the Ill-Posedness of the Best Low-Rank Approximation Problem
• Understanding and Mitigating Gradient Flow Pathologies in Physics-Informed Neural Networks
• Wavelet neural operator for solving parametric partial differential equations in computational mechanics problems
• Zero coordinate shift: whetted automatic differentiation for physics-informed operator learning

Cited in

(1)

• Hutchinson trace estimation for high-dimensional and high-order physics-informed neural networks

This page was built for publication: Separable physics-informed DeepONet: breaking the curse of dimensionality in physics-informed machine learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6669073)