ncsa / GeomDeepONetLinks
A novel DeepONet architecture that is specifically designed for generating predictions on different 3D geometries discretized by different number of mesh nodes.
☆18Updated last year
Alternatives and similar repositories for GeomDeepONet
Users that are interested in GeomDeepONet are comparing it to the libraries listed below
Sorting:
- ☆31Updated 2 years ago
- Physics-informed radial basis network☆31Updated last year
- Multifidelity deep neural operators for efficient learning of partial differential equations with application to fast inverse design of n…☆35Updated 2 years ago
- Neural operator learning of heterogeneous mechanobiological insults contributing to aortic aneurysms☆11Updated 9 months ago
- MIONet: Learning multiple-input operators via tensor product☆37Updated 2 years ago
- PDE Preserved Neural Network☆54Updated 2 months ago
- ☆37Updated last month
- Implementation of a ResUNet-based DeepONet for predicting stress distribution on variable input geometries subject to variable loads. A R…☆14Updated 2 years ago
- Deep finite volume method☆22Updated last year
- GCA-ROM is a library which implements graph convolutional autoencoder architecture as a nonlinear model order reduction strategy.☆36Updated last month
- This repository contains code, which was used to generate large-scale results in the HINTS paper.☆30Updated 9 months ago
- Implementation of 'Physics-Informed Neural Networks for Shell Structures' (European Journal of Mechanics A)☆39Updated 11 months ago
- Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems☆56Updated 3 years ago
- Learning two-phase microstructure evolution using neural operators and autoencoder architectures☆23Updated last year
- In this repository, you will find the different python scripts to train the available models on the AirfRANS dataset proposed at the Neur…☆56Updated 6 months ago
- Coupled-Automatic-Numerical differentiation scheme for physics-informed neural network (can-PINN)