On the locality of local neural operator in learning fluid dynamics

• URL: http://arxiv.org/abs/2312.09820v1
• Date: Fri, 15 Dec 2023 14:18:54 GMT
• Title: On the locality of local neural operator in learning fluid dynamics
• Abstract summary: Local neural operator (LNO) is the core that enables LNO great flexibility in solving transient partial differential equations (PDEs) We investigate the locality of LNO by looking into its receptive field and receptive range. We deem rules found in this paper general when applying LNO to learn and solve transient PDEs in diverse fields.
• Score: 7.773086303468703
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper launches a thorough discussion on the locality of local neural operator (LNO), which is the core that enables LNO great flexibility on varied computational domains in solving transient partial differential equations (PDEs). We investigate the locality of LNO by looking into its receptive field and receptive range, carrying a main concern about how the locality acts in LNO training and applications. In a large group of LNO training experiments for learning fluid dynamics, it is found that an initial receptive range compatible with the learning task is crucial for LNO to perform well. On the one hand, an over-small receptive range is fatal and usually leads LNO to numerical oscillation; on the other hand, an over-large receptive range hinders LNO from achieving the best accuracy. We deem rules found in this paper general when applying LNO to learn and solve transient PDEs in diverse fields. Practical examples of applying the pre-trained LNOs in flow prediction are presented to confirm the findings further. Overall, with the architecture properly designed with a compatible receptive range, the pre-trained LNO shows commendable accuracy and efficiency in solving practical cases.

Related papers

• Towards Universal Solvers: Using PGD Attack in Active Learning to Increase Generalizability of Neural Operators as Knowledge Distillation from Numerical PDE Solvers [3.780792537808271]
  PDE solvers require fine space-time discretizations and local linearizations, leading to high memory cost and slow runtimes.<n>We propose an adversarial teacher-student distillation framework in which a differentiable numerical solver supervises a compact neural operator.<n>Experiments on Burgers and Navier-Stokes systems demonstrate that adversarial distillation substantially improves OOD while preserving the low parameter cost and fast inference of neural operators.
  arXiv  Detail & Related papers  (2025-10-21T18:13:05Z)
• Component Fourier Neural Operator for Singularly Perturbed Differential Equations [3.9482103923304877]
  Solving Singularly Perturbed Differential Equations (SPDEs) poses computational challenges arising from the rapid transitions in their solutions within thin regions. In this manuscript, we introduce Component Fourier Neural Operator (ComFNO), an innovative operator learning method that builds upon Fourier Neural Operator (FNO) Our approach is not limited to FNO and can be applied to other neural network frameworks, such as Deep Operator Network (DeepONet)
  arXiv  Detail & Related papers  (2024-09-07T09:40:51Z)
• Spectral-Refiner: Fine-Tuning of Accurate Spatiotemporal Neural Operator for Turbulent Flows [6.961408873053586]
  We propose a new Stemporal Neural Operator (SFNO) that learns maps between Bochner spaces, and a new learning framework to address these issues. This new paradigm leverages wisdom from traditional numerical PDE theory and techniques to refine the pipeline of commonly adopted end-to-end neural operator training and evaluations. Numerical experiments on commonly used benchmarks for the 2D NSE demonstrate significant improvements in both computational efficiency and accuracy, compared to end-to-end evaluation and traditional numerical PDE solvers.
  arXiv  Detail & Related papers  (2024-05-27T14:33:06Z)
• Neural Operators with Localized Integral and Differential Kernels [77.76991758980003]
  We present a principled approach to operator learning that can capture local features under two frameworks. We prove that we obtain differential operators under an appropriate scaling of the kernel values of CNNs. To obtain local integral operators, we utilize suitable basis representations for the kernels based on discrete-continuous convolutions.
  arXiv  Detail & Related papers  (2024-02-26T18:59:31Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• LNO: Laplace Neural Operator for Solving Differential Equations [0.0]
  We introduce the Laplace neural operator (LNO), which leverages the Laplace transform to decompose the input space. LNO incorporates the pole-residue relationship between the input and the output space, enabling greater interpretability. We show that LNO represents a promising new approach for learning neural operators that map functions between infinite-dimensional spaces.
  arXiv  Detail & Related papers  (2023-03-19T01:41:45Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• On Feature Learning in Neural Networks with Global Convergence Guarantees [49.870593940818715]
  We study the optimization of wide neural networks (NNs) via gradient flow (GF) We show that when the input dimension is no less than the size of the training set, the training loss converges to zero at a linear rate under GF. We also show empirically that, unlike in the Neural Tangent Kernel (NTK) regime, our multi-layer model exhibits feature learning and can achieve better generalization performance than its NTK counterpart.
  arXiv  Detail & Related papers  (2022-04-22T15:56:43Z)
• Local neural operator for solving transient partial differential equations on varied domains [8.905324065830861]
  We propose local neural operator (LNO) for solving transient partial differential equations (PDEs) on varied domains. It comes together with a handy strategy including boundary treatments, enabling one pre-trained LNO to predict solutions on different domains. For demonstration, LNO learns Navier-Stokes equations from randomly generated data samples, and then the pre-trained LNO is used as an explicit numerical time-marching scheme.
  arXiv  Detail & Related papers  (2022-03-11T06:41:51Z)
• LyaNet: A Lyapunov Framework for Training Neural ODEs [59.73633363494646]
  We propose a method for training ordinary differential equations by using a control-theoretic Lyapunov condition for stability. Our approach, called LyaNet, is based on a novel Lyapunov loss formulation that encourages the inference dynamics to converge quickly to the correct prediction.
  arXiv  Detail & Related papers  (2022-02-05T10:13:14Z)
• Incorporating NODE with Pre-trained Neural Differential Operator for Learning Dynamics [73.77459272878025]
  We propose to enhance the supervised signal in learning dynamics by pre-training a neural differential operator (NDO) NDO is pre-trained on a class of symbolic functions, and it learns the mapping between the trajectory samples of these functions to their derivatives. We provide theoretical guarantee on that the output of NDO can well approximate the ground truth derivatives by proper tuning the complexity of the library.
  arXiv  Detail & Related papers  (2021-06-08T08:04:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.