---
license: apache-2.0
language:
- en
tags:
- OneScience
- fluid dynamics
- Lagrangian particle simulation
- graph neural networks
- long-horizon physical prediction
frameworks: PyTorch
---
<p align="center">
  <strong>
    <span style="font-size: 30px;">LagrangianMGN</span>
  </strong>
</p>

# Model Overview
LagrangianMGN is a graph-network model developed by researchers at DeepMind for simulating complex physical systems. It rapidly predicts the dynamics of particle-based systems, including fluids, rigid bodies, and deformable materials.

Paper: Learning to simulate complex physics with graph networks
https://arxiv.org/abs/2002.09405

# Model Description
LagrangianMGN uses a message-passing graph-network architecture trained on the Lagrangian particle simulation dataset to perform long-horizon dynamical simulations of complex systems involving fluids, rigid bodies, and deformable materials.


## Use Cases

| Use Case | Description |
| ------- | --------------------------- |
| Multi-material interaction simulation | Model interactions among fluids, particles, rigid bodies, and deformable materials |
| Long-horizon physical prediction | Use autoregressive rollouts to predict system evolution over hundreds or thousands of steps |
| Rapid local validation | Use synthetic data to validate data loading, model training, inference, and result visualization |


# Usage

## 1. OneCode

Use the online OneCode environment for an intelligent, one-click AI for Science (AI4S) programming experience:

[Launch OneCode for one-click AI4S programming](https://web-2069360198568017922-iaaj.ksai.scnet.cn:58043/home)

## 2. Manual Setup

**Hardware Requirements**

- A GPU or DCU is recommended.
- A CPU can be used for import checks and small-scale pipeline validation, but full training and inference will be slow.
- DCU users must install DTK in advance. DTK 25.04.2 or later, or the OneScience-recommended version for the target cluster, is recommended.

### Download the Model Package

```bash
modelscope download --model OneScience/LagrangianMGN --local_dir ./LagrangianMGN
cd LagrangianMGN
```

### Set Up the Runtime Environment


**DCU Environment**

```bash
# Activate DTK and Conda first
conda create -n onescience311 python=3.11 -y
conda activate onescience311
# Installation with uv is also supported
pip install onescience[cfd-dcu] -i http://mirrors.onescience.ai:3141/pypi/simple/  --trusted-host mirrors.onescience.ai
```

**GPU Environment**
```bash
# Activate Conda first
conda create -n onescience311 python=3.11 -y libstdcxx-ng=12 libgcc-ng=12 gcc_linux-64=12 gxx_linux-64=12
conda activate onescience311
# Installation with uv is also supported
pip install onescience[cfd-gpu] -i http://mirrors.onescience.ai:3141/pypi/simple/  --trusted-host mirrors.onescience.ai
```

### Training Data
The OneScience community provides the DeepMind Lagrangian dataset for training. Download it with the command below and verify that the data path in `conf/config.yaml` is configured correctly:

```bash
modelscope download --dataset OneScience/lagrangian --local_dir ./data/
```

### Training

Single GPU:

```bash
python scripts/train.py
```

Multiple GPUs:

```bash
torchrun --nproc_per_node=8 --nnodes=1 --rdzv_id=1000 --rdzv_backend=c10d --max_restarts=0 --master_addr="localhost" --master_port=29500 scripts/train.py
```

### Model Weights
This repository will provide weights trained on the DeepMind Lagrangian dataset in the `weights/` directory. The weights will be uploaded soon.

### Inference

```bash
python scripts/inference.py
```

The inference script loads a checkpoint from `resume_dir`, whose default value is `weight/checkpoints`.

### Evaluation and Visualization

```bash
python scripts/result.py
```


# Official OneScience Resources

| Platform | OneScience Repository | Skills Repository |
| --- | --- | --- |
| Gitee | https://gitee.com/onescience-ai/onescience | https://gitee.com/onescience-ai/oneskills |
| GitHub | https://github.com/onescience-ai/OneScience | https://github.com/onescience-ai/oneskills |

# Citations and License
- Original LagrangianMGN paper: [Learning to simulate complex physics with graph networks](https://arxiv.org/abs/2002.09405).
- This repository retains the relevant source and attribution notices. Follow all applicable license requirements when using, modifying, or distributing its contents.