Overview#

NVIDIA PhysicsNeMo is an open-source deep-learning framework for building, training, fine-tuning and inferring Physics AI models using state-of-the-art SciML methods for AI4science and engineering.

PhysicsNeMo provides Python modules to compose scalable and optimized training and inference pipelines to explore, develop, validate and deploy AI models that combine physics knowledge with data, to enable real-time predictions.

Whether you are exploring the use of Neural operators, GNNs, or transformers or are interested in Physics-informed Neural Networks or a hybrid approach in between, PhysicsNeMo provides you with an optimized stack that will enable you to train your models at scale.

PhysicsNeMo is developed as modular functionality that are packaged into few key components:

Table 1 PhysicsNeMo Components#
Component	Description
physicsnemo.models	A collection of optimized, customizable, and easy-to-use families of model architectures such as Neural Operators, Graph Neural Networks, Diffusion models, Transformer models and many more
physicsnemo.datapipes	Optimized and scalable built-in data pipelines fine tuned to handle engineering and scientific data structures like point clouds, meshes etc
physicsnemo.distributed	A distributed computing sub-module built on top of `torch.distributed` to enable parallel training with just a few steps
physicsnemo.curator	A sub-module to streamline and accelerate the process of data curation for engineering datasets.
physicsnemo.sym.geometry	A sub-module to handle geometry for DL training using the Constructive Solid Geometry modeling and CAD files in STL format.
physicsnemo.sym.eq	A sub-module to use PDEs in your DL training with several implementations of commonly observed equations and easy ways for customization.

AI4Science Library#

This library is:

A complementary tool to Pytorch, when exploring AI for SciML and AI4Science applications.
A deep learning research platform that provides scale and optimal performance on NVIDIA GPUs.

Domain Specific Packages#

The following are packages dedicated for domain experts of specific communities catering to their unique exploration needs.

PhysicsNeMo CFD: Inference sub-module of PhysicsNeMo to enable CFD domain experts to explore, experiment and validate using pretrained AI models for CFD use cases.
PhysicsNeMo Curator: Inference sub-module of PhysicsNeMo to streamline and accelerate the process of data curation for engineering datasets.
Earth-2 Studio: Inference sub-module of PhysicsNeMo to enable climate researchers and scientists to explore and experiment with pretrained AI models for weather and climate.

Scalable GPU-optimized Training Library#

PhysicsNeMo provides a highly optimized and scalable training library for maximizing the power of NVIDIA GPUs. Distributed Computing utilities allow for efficient scaling from a single GPU to multi-node GPU clusters with a few lines of code, ensuring that large-scale. physics-informed machine learning (ML) models can be trained quickly and effectively. The framework includes support for advanced optimization utilities, tailor made datapipes and validation utilities that enhance end-to-end training speed.

Physics Informed ML Examples#

PhysicsNeMo offers a library of state-of-the-art examples specifically designed for physics-ML applications. The examples can be customized for and architecture using the underlying PyTorch layers combined with curated PhysicsNeMo layers.

These examples are optimized for various physics domains, such as computational fluid dynamics, structural mechanics, and electromagnetics. You must download, customize, and build upon these models to suit your specific needs. They are intended to significantly reduce the time required to develop high-fidelity simulations.

Each of the examples is built using components of the PhysicsNeMo API model class. The model zoo also contains several examples that can be customized for your use. Other examples include:

Seamless PyTorch Integration#

PhysicsNeMo is built on top of PyTorch, which provides a familiar and user-friendly experience for those already proficient with PyTorch. This includes a basic Python interface and modular design, so that PhysicsNeMo can be used with existing PyTorch workflows. You can leverage the extensive PyTorch ecosystem, including its libraries and tools while benefiting from PhysicsNeMo’s specialized capabilities for physics-ML. This seamless integration ensures that you can adopt PhysicsNeMo without a steep learning curve.

For more information, refer to Converting PyTorch Models to PhysicsNeMo Models.

Customization and Extension#

PhysicsNeMo is designed to be highly extensible, allowing you to add new functionality with minimal effort. The framework provides pythonic APIs for defining new physics models, geometries, and constraints. You can extend its capabilities to new use cases. The adaptability of PhysicsNeMo includes key features such as:

ONNX support for flexible model deployment
robust logging utilities for streamlined error handling
efficient checkpointing for model loading and saving

This extensibility ensures that PhysicsNeMo can adapt to the evolving needs of researchers and engineers, facilitating the development of innovative solutions in the field of physics-ML.

Reference samples included in PhysicsNeMo Examples cover a broad spectrum of physics-constrained and data-driven workflows to suit the diversity of use cases in the science and engineering disciplines.

[!TIP] Have questions about how PhysicsNeMo can assist you? Try our [Experimental] PhysicsNeMo Guide chatbot, for answers.

Who is Using and Contributing to PhysicsNeMo?#

PhysicsNeMo is an open source project and gets contributions from researchers in the SciML and AI4science fields. While the PhysicsNeMo team works on optimizing the underlying software stack, the community collaborates and contributes model architectures, datasets, and reference applications so we can innovate in the pursuit of developing generalizable model architectures and algorithms.

Some examples of community contributors are:

Some research teams using PhysicsNeMo are:

For a list of research work leveraging PhysicsNeMo and a list of enterprises using PhysicsNeMo, refer to PhysicsNeMo Latest News.

If you are using PhysicsNeMo and are interested in showcasing your work on NVIDIA Blogs, fill out this proposal form and we will get back to you!

Why Use PhysicsNeMo?#

Here are some of the key benefits of PhysicsNeMo for SciML model development:

SciML Benchmarking and validation	Ease of using generalized SciML recipes with heterogenous datasets	Out of the box performance and scalability
PhysicsNeMo enables researchers to benchmark their AI model against proven architectures for standard benchmark problems with detailed domain-specific validation criteria.	PhysicsNeMo enables researchers to pick from SOTA SciML architectures and use built-in data pipelines for their use case.	PhysicsNeMo provides out-of-the-box performant training pipelines including optimized ETL pipelines for heterogenous engineering and scientific datasets and out of the box scaling across multi-GPU and multi-node GPUs.