miscellaneous-4

PDE Surrogate Modeling

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in pde-surrogate-modeling-4

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find pde-surrogate-modeling-4 models and implementations

Datasets

DrivAerNet

Vibrating Plates

Representative PDE Benchmarks

HEMEW^S-3D

FSI

Subtasks

No subtasks available.

Most implemented papers

Towards Multi-spatiotemporal-scale Generalized PDE Modeling

Jayesh K. Gupta, Johannes Brandstetter•Thu Sep 29 2022

This work makes a comprehensive comparison between various FNO, ResNet, and U-Net like approaches to fluid mechanics problems in both vorticity-stream and velocity function form and shows promising results on generalization to different PDE parameters and time-scales with a single surrogate model.

191

Content

0

Paper Graph

Convolutional Neural Operators for robust and accurate learning of PDEs

Bogdan Raoni'c, R. Molinaro, T. D. Ryck, Tobias Rohner, Francesca Bartolucci, Rima Alaifari, Siddhartha Mishra, Emmanuel de B'ezenac•Wed Feb 01 2023

Novel adaptations for convolutional neural networks are presented to demonstrate that they are indeed able to process functions as inputs and outputs, and it is proved a universality theorem to show that CNOs can approximate operators arising in PDEs to desired accuracy.

173 0

Paper Graph

Learning Neural PDE Solvers with Parameter-Guided Channel Attention

M. Takamoto, F. Alesiani, Mathias Niepert•Wed Apr 26 2023

A Channel Attention mechanism guided by PDE Parameter Embeddings (CAPE) component for neural surrogate models and a simple yet effective curriculum learning strategy that provides a seamless transition between teacher-forcing and fully auto-regressive training.

38 0

Paper Graph

Learning to Predict Structural Vibrations

J. V. Delden, Julius Schultz, Christopher Blech, Sabine C. Langer, Timo Lüddecke•Sun Oct 08 2023

A new network architecture is proposed, named Frequency-Query Operator, which predicts vibration patterns of plate geometries given a specific excitation frequency and outperforms DeepONets, Fourier Neural Operators and more traditional neural network architectures and can be used for design optimization.

4 0

Paper Graph

Scalable Transformer for PDE Surrogate Modeling

A. Farimani, Zijie Li, Dule Shu•Fri May 26 2023

Factorized Transformer(FactFormer), which is based on an axial factorized kernel integral, is proposed, which is able to simulate 2D Kolmogorov flow on a 256 by 256 grid and 3D smoke buoyancy on a 64 by64 by 64 grid with good accuracy and efficiency.

127 0

Paper Graph

Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems

Maksim Zhdanov, Max Welling, Jan-Willem van de Meent•Sun Feb 23 2025

Erwin is a hierarchical transformer inspired by methods from computational many-body physics, which combines the efficiency of tree-based algorithms with the expressivity of attention mechanisms and demonstrates Erwin's effectiveness across multiple domains, including cosmology, molecular dynamics, PDE solving, and particle fluid dynamics.

15 0

Paper Graph

Adding a benchmark result helps the community track progress.