NVIDIA Modulus Examples
This repository provides sample applications demonstrating use of specific Physics-ML model architectures that are easy to train and deploy. These examples aim to show how such models can help solve real world problems.
Use case |
Model |
Transient |
|---|---|---|
| Vortex Shedding | MeshGraphNet | YES |
| Ahmed Body Drag prediction | MeshGraphNet | NO |
| Navier-Stokes Flow | RNN | YES |
| Gray-Scott System | RNN | YES |
| Darcy Flow | FNO | NO |
| Darcy Flow using Nested-FNOs | Nested-FNO | NO |
| Darcy Flow (Data + Physics Driven) using DeepONet a pproach | FNO (branch) and MLP (trunk) | NO |
| Darcy Flow (Data + Physics Driven) using PINO approach (Numerical gra dients) | FNO | NO |
| `Stokes Flow (Physics Informed Fine-Tuning) < ./cfd/stokes_mgn/>`__ | MeshGraphNet and MLP | NO |
Use case |
Model |
AMP |
CUDA Graphs |
Multi-GPU |
M ulti-Node |
|---|---|---|---|---|---|
| Med ium-range global weather forecast using FCN-SFNO | FCN-SFNO | YES | NO | YES | YES |
| Med ium-range global weather forecast using GraphCas t | GraphCast | YES | NO | YES | YES |
| Med ium-range global weather forecast using FCN-AF NO | FCN-AFNO | YES | YES | YES | YES |
| Med ium-range and S2S global weather forecast using DLWP | DLWP | YES | YES | YES | YES |
Use case |
Model |
Transient |
|---|---|---|
| Cardiovascular Simul ations | MeshGraphNet | YES |
| Brain Anomaly Detection | FNO | YES |
Use case |
Model |
Transient |
|---|---|---|
| Force Prediciton for Lennard Jones syste m | MeshGraphNet | NO |
Use case |
Model |
Multi-GPU |
Multi-Node |
|---|---|---|---|
| Generative Correction Diffusion Model for Km-scale Atmospheric Downscali ng | CorrDiff | YES | YES |
In addition to the examples in this repo, more Physics-ML usecases and examples can be referenced from the Modulus-Sym examples.
In each of the example READMEs, we indicate the level of support that will be provided. Some examples are under active development/improvement and might involve rapid changes. For stable examples, please refer the tagged versions.
We’re posting these examples on GitHub to better support the community, facilitate feedback, as well as collect and implement contributions using GitHub issues and pull requests. We welcome all contributions!