Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 44 for “"Neural Operators"”.

  1. Neural Operators for Learning Complex Nonlocal Mappings in Fluid Dynamics

    … in machine learning and develop novel neural operator-based methods that not only possess strong representational capabilities but also preserve critical physical and mathematical principles. With the developed tools, we have demonstrated promising preliminary results in addressing …

    vt Repository record for Neural Operators for Learning Complex Nonlocal Mappings in Fluid Dynamics (opens in a new tab)

  2. ADAPTIVE WAVELETS AND FOURIER NEURAL OPERATORS FOR ACCELERATING VARIATIONAL DATA ASSIMILATION

    … based on adaptive wavelet methods and Fourier neural operators (FNOs). First, an adaptive wavelet multigrid method is developed for solving the 4D-Var Hessian system to estimate the optimal initial condition from sparse observations distributed in space and time. By exploiting the natural …

    mcmaster Repository record for ADAPTIVE WAVELETS AND FOURIER NEURAL OPERATORS FOR ACCELERATING VARIATIONAL DATA ASSIMILATION (opens in a new tab)

  3. A Meteorological Forecasting Method Driven by Linear Convolutional Recurrent Spatiotemporal Neural Operators

    … of global weather forecasting. While previous neural models such as FourCastNet and Pangu-Weather have demonstrated promising accuracy, most adopt frame-wise prediction strategies without explicitly modeling temporal evolution. This limits their ability to represent the multiscale and …

    unsw Repository record for A Meteorological Forecasting Method Driven by Linear Convolutional Recurrent Spatiotemporal Neural Operators (opens in a new tab)

  4. Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation

    … computing. Architectures like Deeponet and Neural Operators have showcased their potential in approximating operators defined by partial differential equations (PDEs). While these architectures have shown practical success, there remains a compelling need to delve deeper into their …

    rice Repository record for Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation (opens in a new tab)

  5. Learning seismic wave propagation with Fourier Neural Operators: Advantages, limitations, and Physics-Informed implementation

    … simulations are needed. In this context, Fourier Neural Operators (FNOs) have become a promising data-driven alternative for learning solution operators of partial differential equations. Their ability to approximate mappings between function spaces offers po-tential benefits in terms of …

    calgary Repository record for Learning seismic wave propagation with Fourier Neural Operators: Advantages, limitations, and Physics-Informed implementation (opens in a new tab)

  6. Generalization of Urban Wind Field Using Fourier Neural Operators Across Different Wind Directions and Cities

    … process. In this paper, we apply the Fourier Neural Operator (FNO) method based on deep learning technology to simulate the wind field in a two-dimensional urban environment. The method uses a Fourier module to extract and learn features in the Fourier frequency domain of the input data. …

    concordia Download PDF for Generalization of Urban Wind Field Using Fourier Neural Operators Across Different Wind Directions and Cities (opens in a new tab)

  7. Ocean parameterizations in an idealized model using machine learning

    … significantly, it delves into the use of Fourier Neural Operators for modeling subgrid-scale process contributions. These neural networks were recently introduced by Li et al., 2020, and have already exhibited impressive results in many areas of computational fluid dynamics. Hence, while building …

    liege Repository record for Ocean parameterizations in an idealized model using machine learning (opens in a new tab) Download PDF for Ocean parameterizations in an idealized model using machine learning (opens in a new tab)

  8. Leveraging intrinsic model and data structures for predictive physics-based modeling and uncertainty quantification

    … deep operator network (L-DeepONet), to train neural operators in latent spaces which significantly improves predictive accuracy for time-dependent PDEs of varying degrees of complexity. The final component of this dissertation focuses on transfer learning (TL) for conditional shift in PDE …

    jhu Repository record for Leveraging intrinsic model and data structures for predictive physics-based modeling and uncertainty quantification (opens in a new tab)

  9. Redes neurais para propagação de ondas

    … in machine learning, and more specifically in neural networks, have emerged as promising tools to assist in addressing such complex tasks. Through the use of physics-informed neural networks and neural operators, we explore distinct applications of wave propagation, incorporating prior …

    brazil-ufrn Repository record for Redes neurais para propagação de ondas (opens in a new tab)

  10. Electromagnetic Problems Dataset for Machine Learning

    … for future research on data-driven methods like neural operators or foundation models.

    ethz Repository record for Electromagnetic Problems Dataset for Machine Learning (opens in a new tab)

  11. Assessment of AI Tools for CFD Acceleration and Generalization

    … Different AI architectures such as Graph Neural Networks (GNNs), MeshGraphNet, Physics Informed Neural Networks (PINNs), and Fourier Neural Operators (FNOs) are studied using CFD datasets generated from ANSYS Fluent and STAR-CCM+. Two study cases are considered in the present work, namely …

    chalmers Repository record for Assessment of AI Tools for CFD Acceleration and Generalization (opens in a new tab)

  12. LEARNING PDE SOLUTION OPERATORS VIA DIFFEOMORPHIC MAPPINGS: APPLICATIONS IN FLUID DYNAMICS

    … numerous scientific and engineering disciplines. Neural operators have emerged as a powerful tool for predicting these solution operators when trained on high-quality ground truth data, such as results from numerical simulations. However, their ability to generalize to unseen spatial domains is …

    jhu Repository record for LEARNING PDE SOLUTION OPERATORS VIA DIFFEOMORPHIC MAPPINGS: APPLICATIONS IN FLUID DYNAMICS (opens in a new tab)

  13. Surrogate modelling for complex physical systems

    … in tractable time frames. Physics-informed neural networks are developed for a realistic 17-vessel model of systemic circulation, where, by embedding conservation laws and bifurcation conditions into the training objective, they achieve improved accuracy over purely data-driven alternatives …

    glasgow Repository record for Surrogate modelling for complex physical systems (opens in a new tab) Download PDF for Surrogate modelling for complex physical systems (opens in a new tab)

  14. Data-Driven Algorithms for Accelerating Discovery & Optimization in Complex Dynamical Systems

    … by learning governing dynamics (i.e. emergent neural operators) directly from messy, unstructured datasets, bypassing the need for curated labels or explicit mechanistic models, and (3) accelerating optimization (derivative-free Bayesian optimization) by clarifying when global vs. local solvers …

    jhu Repository record for Data-Driven Algorithms for Accelerating Discovery & Optimization in Complex Dynamical Systems (opens in a new tab)

  15. Neural Operator–Based Thermal Modeling for Electric Motor and Power Electronics Systems

    … thesis develops a load-memory-enhanced Fourier Neural Operator (FNO) as a computationally efficient surrogate for predicting twodimensional transient temperature fields in a 15 kW squirrel-cage induction motor. The available FEM data are converted from an irregular mesh to a common 512×512 …

    chalmers Repository record for Neural Operator–Based Thermal Modeling for Electric Motor and Power Electronics Systems (opens in a new tab)

  16. Learning the Evolution of Time-dependent Partial Differential Equations

    … of using deep learning models, specifically Neural Operators, to predict the long-term temporal evolution of complex physical systems governed by Partial Differential Equations (PDEs). While deep learning surrogate models can offer significant computational speedups over traditional numerical …

    whiterose Download PDF for Learning the Evolution of Time-dependent Partial Differential Equations (opens in a new tab)

  17. Hybrid learning models for statistical continuum mechanics

    … papers: an exploratory study applying iterative neural networks to elastic localization, a thermodynamically-informed iterative neural operator which generalizes these ideas to work over a wider range of microstructure classes and loading directions, and an extrapolation study which explores how …

    gatech Repository record for Hybrid learning models for statistical continuum mechanics (opens in a new tab)

  18. Deep learning for fast aerodynamic estimation of road vehicles

    … performance of PointNet and Geometry-Informed Neural Operators (GINO) is evaluated for predicting global drag coefficients (Cd) and local pressure distributions over complex automotive geometries. Using the DrivAerNet dataset, systematic experiments investigate the influence of total sample …

    chalmers Repository record for Deep learning for fast aerodynamic estimation of road vehicles (opens in a new tab)

Page 1 of 3