Derivative-enhanced Deep Operator Network
The deep operator networks (DeepONet), a class of neural operators that learn mappings between function spaces, have recently been developed as surrogate models for parametric partial differential equations (PDEs). In this work we propose a derivative-enhanced deep operator network (DE-DeepONet), which leverages derivative information to enhance the solution prediction accuracy and provides a more accurate approximation of solution-to-parameter derivatives, especially when training data are limited. DE-DeepONet explicitly incorporates linear dimension reduction of high dimensional parameter input into DeepONet to reduce training cost and adds derivative loss in the loss function to reduce the number of required parameter-solution pairs. We further demonstrate that the use of derivative loss can be extended to enhance other neural operators, such as the Fourier neural operator (FNO). Numerical experiments validate the effectiveness of our approach.
Code (1)
Tasks
Dimensionality ReductionSimilar Papers 제목 키워드 기반
Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning
We propose derivative-informed neural operators (DINOs), a general family of neural networks to approximate operators as infinite-dimensional mappings from input function spaces to output function spaces or quantities of…
Dimensionality ReductionExperimental DesignDerivative-Informed Fourier Neural Operator: Universal Approximation and Applications to PDE-Constrained Optimization
We present approximation theories and efficient training methods for derivative-informed Fourier neural operators (DIFNOs) with applications to PDE-constrained optimization. A DIFNO is an FNO trained by minimizing its pr…
Dimensionality ReductionSetONet: A Deep Set-based Operator Network for Solving PDEs with permutation invariant variable input sampling
Neural operators, particularly the Deep Operator Network (DeepONet), have shown promise in learning mappings between function spaces for solving differential equations. However, standard DeepONet requires input functions…
Operator learningEmbedding derivatives and derivative Area operators of Hardy spaces into Lebesgue spaces
We characterize the compactness of embedding derivatives from Hardy space $H^p$ into Lebesgue space $L^q(\mu)$. We also completely characterize the boundedness and compactness of derivative area operators from $H^p$ into…
Dimension reduction for derivative-informed operator learning: An analysis of approximation errors
We study the derivative-informed learning of nonlinear operators between infinite-dimensional separable Hilbert spaces by neural networks. Such operators can arise from the solution of partial differential equations (PDE…
Dimensionality ReductionExperimental DesignOperator learning