--- license: other license_name: nvidia-open-model-license license_link: >- https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-agreement/ --- # DoMINO DrivAerML DoMINO (Decomposable Multi-scale Iterative Neural Operator) DrivAerML is a point cloud-based deep learning surrogate model for large-scale automotive external aerodynamics simulations. The model predicts surface pressure and wall shear stress fields, as well as volumetric velocity, pressure, and turbulent viscosity fields on 3D vehicle geometries for computational fluid dynamics (CFD) applications. This model is available for commercial use. ### License/Terms of Use: Use of this model is governed by the [NVIDIA Open Model Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-agreement/). ### Deployment Geography: Global ### Use Case: Computational Fluid Dynamics (CFD) engineers accelerating automotive external aerodynamics with AI. ### Release Date: 05/01/2026 Hugging Face: https://huggingface.co/nvidia/domino_drivaerml ## Reference(s): [Code](https://github.com/NVIDIA/physicsnemo/tree/main/examples/cfd/external_aerodynamics/domino) [DoMINO: A Decomposable Multi-scale Iterative Neural Operator for Modeling Large Scale Engineering Simulations](https://arxiv.org/abs/2501.13350) [DrivAerML: High-Fidelity Computational Fluid Dynamics Dataset for Road-Car External Aerodynamics](https://arxiv.org/abs/2408.11969) ## Model Architecture: **Architecture Type:** Point cloud-based multi-scale neural operator with global geometry encoding, local geometry extraction, and basis function aggregation. **Network Architecture:** DoMINO consists of three sub-networks: (1) a Global Geometry Representation Network that projects the input point cloud onto a structured latent grid using learnable multi-scale point convolution kernels processed by CNN blocks, augmented with signed distance field (SDF) values and gradients; (2) a Local Geometry Representation that extracts subregion features from the global grid around computational stencils via additional point convolution kernels and fully connected layers; and (3) an Aggregation Network that uses basis function neural networks to predict and aggregate solution fields via inverse distance weighting. Separate network instances handle surface and volume predictions while sharing the geometry encoding. Point convolution kernels use GPU-accelerated dynamic ball queries via NVIDIA Warp. **Number of model parameters:** 19.7M ## Input: **Input Type(s):** - Tensor (3D point cloud coordinates on vehicle surface and volume) **Input Format(s):** PyTorch Tensor
**Input Parameters:** - Surface: mesh node coordinates (M_s, 3), surface normals (M_s, 3), SDF values and gradients - Volume: uniformly sampled 3D point coordinates (M_v, 3) **Other Properties Related to Input:** - Input geometry is derived from STL (Standard Tessellation Language) files - Surface sampling is area-weighted; volume sampling is uniform random - Coordinates normalized to the vehicle bounding box ## Output: **Output Type(s):** Tensor (Surface and volume aerodynamic fields)
**Output Format:** PyTorch Tensor
**Output Parameters:** - Surface: pressure (M_s, 1), wall shear stress (M_s, 3) - Volume: velocity (M_v, 3), pressure (M_v, 1), turbulent viscosity (M_v, 1) **Other Properties Related to Output:** - Outputs are non-dimensionalized and normalized using mean and standard deviation computed from the training dataset - Drag force can be derived via surface integration of pressure and wall shear stress predictions Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. ## Software Integration **Runtime Engine(s):** PyTorch
**Supported Hardware Microarchitecture Compatibility:**
* NVIDIA Ampere
* NVIDIA Blackwell
* NVIDIA Hopper
* NVIDIA Turing
**Supported Operating System(s):** * Linux
The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment. ## Model Version(s): **Model Version:** 1.0.0
# Training, Testing, and Evaluation Datasets: The DrivAerML dataset is used for training and evaluation, which is a publicly available, high-fidelity dataset comprising aerodynamic data for 500 parametrically morphed variants of the DrivAer notchback vehicle. The dataset was generated using hybrid RANS/LES (HRLES), a scale-resolving CFD method, which provides time-averaged quantities for each variant. The available data includes surface pressure, wall shear stress, and flow-field quantities, provided in formats compatible with mesh-based analysis (.vtp for surface data and .vtu for flow-field data). 48 samples (~10%) are used as the test set, with approximately 20% of the test set consisting of out-of-distribution samples based on drag coefficients. These samples represent extreme cases with the lowest and highest drag coefficients in the entire dataset, which remain unseen by the model during training. Models are trained for up to 500 epochs on a single NVIDIA GB200 node using the Muon optimizer. ## Training Dataset: **Data Modality:** - Other: 3D Point Cloud (surface and volume) **Training Data Size:** - 436 files in VTP format (surface meshes) and VTU format (volume flow fields) with corresponding physical quantities **Link:** [DrivAerML Dataset](https://arxiv.org/abs/2408.11969)
*Data Collection Method by dataset:*
* Synthetic CFD Simulation
*Labeling Method by dataset:*
* Automated
**Properties:** The data is a simulation/synthetic dataset generated using hybrid RANS/LES scale-resolving CFD simulations, providing time-averaged surface and volumetric flow fields for different car geometries. Each case contains approximately 150 million volume elements and 10 million surface elements. ## Testing Dataset: **Link:** [DrivAerML Dataset](https://arxiv.org/abs/2408.11969)
*Data Collection Method by dataset:*
* Synthetic CFD Simulation
*Labeling Method by dataset:*
* Synthetic CFD Simulation
**Properties:** Test split from DrivAerML dataset with vehicle geometries held out from training. 48 samples (~10%) are used as the test set, with approximately 20% consisting of out-of-distribution samples based on drag coefficients. ## Evaluation Dataset: **Link:** [DrivAerML Dataset](https://arxiv.org/abs/2408.11969)
*Data Collection Method by dataset:*
* Synthetic CFD Simulation
*Labeling Method by dataset:*
* Automated
**Properties:** Validation split from DrivAerML dataset with vehicle geometries held out from training. The full DrivAerML dataset is split as 90% for training and 10% for validation. ## Inference: **Acceleration Engine:** PyTorch
**Test Hardware:** * H100
* GB200
## Ethical Considerations: NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Model Card++ subcards: [Bias](https://huggingface.co/nvidia/domino_drivaerml/blob/main/bias.md), [Explainability](https://huggingface.co/nvidia/domino_drivaerml/blob/main/explainability.md), [Privacy](https://huggingface.co/nvidia/domino_drivaerml/blob/main/privacy.md), and [Safety & Security](https://huggingface.co/nvidia/domino_drivaerml/blob/main/safety.md). Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).