PDE Operator Learning

PDE: Partial Differential Equation

Overview

PDE operator learning studies how to approximate solution maps that take functions or physical parameters—such as initial conditions, coefficients, and boundary data—and return PDE solution fields. It aims to make repeated simulation faster for tasks including forecasting, design, inverse problems, and control, using approaches such as Fourier neural operators, DeepONets, attention and graph models, and kernel methods. Researchers also use physics-informed losses, multiscale representations, and structure-preserving constraints to improve accuracy, efficiency, and physical consistency. A central challenge is reliable generalization across unseen geometries, resolutions, frequencies, and parameter regimes while maintaining stable long-term predictions; strong in-distribution accuracy alone does not guarantee it.

Latest papers

CardsList

251 papers17 papers in the last four weeks, down 57% on the four weeks before. 0.1% of all new papers.

  1. RheOFormer: A generative transformer model for simulation of complex fluids and flows

    Oct 1, 2025Maedeh Saberi, Amir Barati Farimani, Safa JamaliNeural Surrogate ModelingTransformer

  2. Learning Greens Operators through Hierarchical Neural Networks Inspired by the Fast Multipole Method

    Sep 24, 2025Emilio McAllister Fognini, Marta M. Betcke, Ben T. CoxPDE Operator LearningOperator Learning

  3. Discretization-independent operator learning for partial differential equations

    Jul 9, 2025Jacob Hauck, Yanzhi ZhangPDE Operator LearningNeural Network Approximation Theory

  4. A Neural Operator based on Dynamic Mode Decomposition

    Jul 1, 2025Nikita Sakovich, Dmitry Aksenov, Ekaterina Pleshakova +1PDE Operator LearningNeural Operators

  5. Latent Evolution Operator (LEO): State-to-State Forecasting of Parametric PDEs

    May 14, 2025Khalid Rafiq, Wenjing Liao, Aditya G. NairPDE Surrogate ModelingPDE Operator Learning

  6. From Theory to Application: A Practical Introduction to Neural Operators in Scientific Computing

    Mar 7, 2025Prashant K. JhaNeural Surrogate ModelingFourier Neural Operator

  7. Data-Efficient Kernel Methods for Learning Differential Equations and Their Solution Operators: Algorithms and Error Analysis

    Mar 2, 2025Bamdad Hosseini, Alexander Hsu, Yasamin Jalalian +2PDE Operator LearningKernel Methods

  8. Active Learning with Bayesian Multi-Fidelity Laplace Neural Operators for Oscillatory Parametric PDEs

    Feb 1, 2025Bongseok Kim, Haoyang Zheng, Michael Penwarden +1Dynamical SystemsSurrogate Modeling

  9. Graph Fourier Neural Kernels: Learning Full PDE Trajectories Across Geometries and Anisotropic Parameter Fields

    Oct 6, 2024Shane E. Loeffler, Zan Ahmad, Shiyi Chen +8PDE Operator LearningNeural Operators

  10. Exponential Convergence of Deep Operator Networks for Elliptic Partial Differential Equations

    Dec 15, 2021Carlo Marcati, Christoph SchwabPDE SolvingPDE Operator Learning