DoMINO-Automotive-Aero NIM

DoMINO is a pre-trained AI model for automotive external aerodynamics. This model has been trained using data from 1500 steady-state RANS simulations of road-cars of varying geometries, at speeds from 20m/s to 50m/s. This pre-trained model works by taking the input from a single STL (Standard Tessellation Language) geometry of a road-car together with a target streamwise velocity and evaluates a solution on the surface of your vehicle as well as the volume surrounding it.

The DoMINO model evaluates solution fields within a computational domain by leveraging geometry representations in STL file format. It encodes global geometry information on a fixed-size grid, defined in the computational domain, through a combination of learnable point convolution kernels, CNNs, and dense networks. Local geometric encoding is extracted, using point convolution kernels, from the global encoding by dynamically constructing local subdomains around sampled points where the solution fields are evaluated. This approach enables the prediction of volume and surface solutions by combining local geometry encoding with basis functions computed for sampled points and their neighboring points.

Key features of DoMINO:

• Highly scalable: Predicts high-fidelity flow fields on point clouds sampled on the vehicle surface and in the volume around it.
• Efficient geometry representation for better generality: Learns multi-scale global encodings directly from STLs.
• Localized learning for improved accuracy: Local geometry encodings are extracted from global representations in subdomains dynamically constructed around each point where the solution is desired.
• Basis in traditional numerical methods: Dynamically constructs local computational stencils around sampled points in the domain where the solution is desired. The size of the stencil is user controlled and provides a trade-off between accuracy and speed.

This pre-trained model serves as a demonstration of the potential of foundation models for early stage design evaluation in automotive aerodynamics and is ready for use as a starting point for finetuning to datasets with larger geometric and boundary condition variations.

What is NVIDIA NIM?

NVIDIA NIM, part of NVIDIA AI Enterprise, is a set of easy-to-use microservices designed to accelerate deployment of generative AI across cloud, data center, and workstations.

Benefits of self-hosted NIMs:

• Deploy anywhere and maintain control of generative AI applications and data
• Streamline AI application development with industry standard APIs and tools tailored for enterprise environments
• Prebuilt containers for the latest generative AI models, offering a diverse range of options and flexibility right out of the gate
• Industry-leading latency and throughput for cost-effective scaling
• Support for custom models out of the box so models can be trained on domain specific data
• Enterprise-grade software with dedicated feature branches, rigorous validation processes, and robust support structures

Getting Started with Domino-Automotive-Aero NIM

Please visit the NIM Documentation on how to get started.

Security Vulnerabilities in Open Source Packages

Please review the Security Scanning tab to view the latest security scan results.

For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.

Get Help

Enterprise Support

Get access to knowledge base articles and support cases or submit a ticket.

NVIDIA AI Enterprise Documentation

Visit the NVIDIA AI Enterprise Documentation Hub for release documentation, deployment guides and more.

Governing Terms

The NIM container is governed by the NVIDIA Software License Agreement and Product-Specific Terms for AI Products; and the use of this model is governed by the NVIDIA Community Model License.

You are responsible for ensuring that your use of NVIDIA AI Foundation Models complies with all applicable laws.