Energy-dissipative evolutionary deep operator neural networks

DOI10.1016/J.JCP.2023.112638arXiv2306.06281OpenAlexW4388907411MaRDI QIDQ6187616FDOQ6187616

Authors:

Publication date: 31 January 2024

Published in: Journal of Computational Physics (Search for Journal in Brave)

Abstract: Energy-Dissipative Evolutionary Deep Operator Neural Network is an operator learning neural network. It is designed to seed numerical solutions for a class of partial differential equations instead of a single partial differential equation, such as partial differential equations with different parameters or different initial conditions. The network consists of two sub-networks, the Branch net and the Trunk net. For an objective operator G, the Branch net encodes different input functions u at the same number of sensors, and the Trunk net evaluates the output function at any location. By minimizing the error between the evaluated output q and the expected output G(u)(y), DeepONet generates a good approximation of the operator G. In order to preserve essential physical properties of PDEs, such as the Energy Dissipation Law, we adopt a scalar auxiliary variable approach to generate the minimization problem. It introduces a modified energy and enables unconditional energy dissipation law at the discrete level. By taking the parameter as a function of time t, this network can predict the accurate solution at any further time with feeding data only at the initial state. The data needed can be generated by the initial conditions, which are readily available. In order to validate the accuracy and efficiency of our neural networks, we provide numerical simulations of several partial differential equations, including heat equations, parametric heat equations and Allen-Cahn equations.

Full work available at URL: https://arxiv.org/abs/2306.06281

zbMATH Keywords

deep learningparametric equationevolutionary neural networksscalar auxiliary variableoperator learningenergy dissipative

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Numerical methods for partial differential equations, boundary value problems (65Nxx) Miscellaneous topics in partial differential equations (35Rxx)

Cites Work

• DIFFUSE-INTERFACE METHODS IN FLUID MECHANICS
• TWO-PHASE BINARY FLUIDS AND IMMISCIBLE FLUIDS DESCRIBED BY AN ORDER PARAMETER
• Free energy of a nonuniform system. I: Interfacial free energy
• Multilayer feedforward networks are universal approximators
• Approximation by superpositions of a sigmoidal function
• A diffuse-interface method for simulating two-phase flows of complex fluids
• Convergence of the phase field model to its sharp interface limits
• A rapidly converging phase field model
• Solving parametric PDE problems with artificial neural networks
• The scalar auxiliary variable (SAV) approach for gradient flows
• Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
• Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ
• ConvPDE-UQ: convolutional neural networks with quantified uncertainty for heterogeneous elliptic partial differential equations on varied domains
• A physics-informed operator regression framework for extracting data-driven continuum models
• Data-driven deep learning of partial differential equations in modal space
• The Random Feature Model for Input-Output Maps between Banach Spaces
• DEEP LEARNING OF PARAMETERIZED EQUATIONS WITH APPLICATIONS TO UNCERTAINTY QUANTIFICATION

Cited In (1)

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

This page was built for publication: Energy-dissipative evolutionary deep operator neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6187616)