Energy-dissipative evolutionary deep operator neural networks
From MaRDI portal
(Redirected from Publication:6187616)
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.
Recommendations
Cites work
- A diffuse-interface method for simulating two-phase flows of complex fluids
- A physics-informed operator regression framework for extracting data-driven continuum models
- A rapidly converging phase field model
- Approximation by superpositions of a sigmoidal function
- Convergence of the phase field model to its sharp interface limits
- ConvPDE-UQ: convolutional neural networks with quantified uncertainty for heterogeneous elliptic partial differential equations on varied domains
- Data-driven deep learning of partial differential equations in modal space
- Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ
- DEEP LEARNING OF PARAMETERIZED EQUATIONS WITH APPLICATIONS TO UNCERTAINTY QUANTIFICATION
- DIFFUSE-INTERFACE METHODS IN FLUID MECHANICS
- Free energy of a nonuniform system. I: Interfacial free energy
- Multilayer feedforward networks are universal approximators
- Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
- Solving parametric PDE problems with artificial neural networks
- The Random Feature Model for Input-Output Maps between Banach Spaces
- The scalar auxiliary variable (SAV) approach for gradient flows
- TWO-PHASE BINARY FLUIDS AND IMMISCIBLE FLUIDS DESCRIBED BY AN ORDER PARAMETER
Cited in
(8)- Wavelet neural operator for solving parametric partial differential equations in computational mechanics problems
- Separable physics-informed DeepONet: breaking the curse of dimensionality in physics-informed machine learning
- An energy stable implicit-explicit finite element method/BDF-k scheme for the Ginzburg-Landau equation
- SAV-based entropy-dissipative schemes for a class of kinetic equations
- Weak neural Galerkin method for nonlinear time-dependent partial differential equations
- Basis-to-basis operator learning using function encoders
- Accelerating particle-based energetic variational inference
- Modified approach for linear and non-linear IBVPs with fractional dynamics
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)
