AI Physics

Overview

The Rescale AI Physics Operating System (OS) provides a guided, end-to-end way to turn simulation data into high-accuracy surrogate models with fast and flexible inference. It is designed for simulation engineers — not AI experts — and supports a range of production-ready model architectures across multiple solvers.

A surrogate model is trained on your simulation data and provides faster approximations for design exploration and optimization. Once trained, a surrogate model can predict outputs for new inputs in seconds instead of hours, allowing you to explore more design candidates without running additional solver jobs.

Benefits

  • End-to-end guided workflow — The Rescale AI Physics OS manages the full lifecycle from simulation data preparation through model training, validation, and inference, with no custom scripts or machine learning pipelines required.
  • Designed for simulation engineers — built-in Jupyter Notebook templates, an AI copilot, and default training parameters make it accessible without deep AI expertise.
  • Fast inference, multiple environments — run inference interactively in AI Physics Training and AI Physics Inference, locally on any workstation or laptop via the local inference runner and client, or natively inside Blender and Autodesk Alias.
  • Broad solver support — AI Physics supports steady-state CFD and static FEA workflows today, with support for additional solvers and analysis types expanding over time. 

The AI Physics Workflow

The end-to-end process has four stages:

  1. Prepare Rescale Jobs — run your simulation jobs on Rescale with data preparation Automations enabled
  2. Create an AI Dataset — build a structured dataset from your completed simulation jobs
  3. Train the Surrogate Model — use AI Physics Training to select a model architecture, train, and validate
  4. Run Inference — use the trained model to predict outputs for new inputs and geometries instantly

Prerequisites

Before you begin:

  • AI Physics must be enabled for your organization. If you don’t see AI Datasets, Model Builder, or AI Models in the Rescale side navigation, contact your Rescale representative

Prepare Rescale Jobs

Before training a surrogate model, you need simulation data that covers the input space you want the model to predict over. The quality and coverage of your training data directly determines how well the surrogate model generalizes.

Run a parameter sweep or design of experiments (DOE) that samples a representative range of your inputs. Each completed run becomes one training sample or dataset case.

When setting up your Rescale jobs, enable two types of data preparation Automations so that your results are ready for AI training:

  • Metadata Extraction — extracts global input variable names and values from your solver files, and stores them as Custom Fields on each job. These become the global variables for your surrogate model.
  • AI Extraction — converts your solver output files to a standardized PyVista compatible format that AI Physics Training can ingest. 

Tip: Contact your Rescale representative if you do not see Automations for your solver of interest. 

To add Automations to a job:

  1. From the Rescale platform, open or create a job.
  2. Navigate to the Automations tab in the job configuration.
  3. Under the available Automations, locate and enable the Metadata Extraction Automation for your solver.
  4. Enable the AI Extraction Automation for your solver.
  5. Submit and run your jobs as usual.

Once your DOE is complete, verify that each run has finished successfully and that the expected output files and Custom Fields are present before proceeding.

How many jobs do I need? For problems with a small number of inputs and smooth, continuous outputs, a few dozen samples may be sufficient. High-dimensional inputs or highly non-linear responses typically require hundreds of samples. Start with what you have and expand if model accuracy is insufficient.

Create an AI Dataset

Once your simulation jobs are complete, you create an AI Dataset — a structured collection of simulation results that the surrogate model will be trained on.

AI Dataset creation happens inside a Training Session using a Jupyter Notebook template. The template guides you through collecting your job results, organizing them into the dataset structure, and validating that inputs and outputs are consistent across all runs.

To create an AI Dataset:

  1. From the Rescale platform, navigate to Model Builder in the left sidebar and click New Training Session.
  2. Click Continue without selecting a Dataset or Model.
  3. Click New Storage Device to create and configure a storage device to hold your dataset and model files and click Continue.
  4. Add a Workstation and configure the workstation hardware. Click Create to create the Training Session and launch the workstation. 
  5. Once the Training Session is ready, click Open Session, then click Open App to launch AI Physics Training.
  6. From AI Physics Training, click New Dataset. This opens a Jupyter Notebook template with step-by-step instructions for loading your completed Rescale job results and building the dataset.
  7. Follow the notebook instructions. The notebook will walk you through running commands to collect cases, initialize the dataset, and validate it. Once validation passes, your new AI Dataset appears in the AI Datasets table in Rescale.
  8. From AI Physics Training, you can merge, split, duplicate, and delete AI Datasets. You can also review the dataset cases and inspect the input and output variables. 

Mesh decimation: For high-resolution meshes, you can perform mesh decimation in AI Physics Training to reduce the mesh size and shorten training time. This is optional but can significantly speed up training for datasets with large meshes.

Tip: If you’re new to AI Physics, follow the end-to-end tutorials listed in the Tutorials section below before setting up your own jobs. The tutorials use pre-prepared job results so you can practice dataset creation and model training without running a full DOE first.

Notebook Copilot: The Notebook Copilot uses the Qwen2.5-Coder-14B large language model from Alibaba, licensed under Apache 2.0. No data is sent from the Notebook Copilot to Alibaba or third parties.

Train the Surrogate Model

With an AI Dataset ready, you can train a surrogate model from inside AI Physics Training. Training runs locally or as a managed Rescale job on optimized GPU hardware — you configure the settings in AI Physics Training, and Rescale handles infrastructure provisioning and job execution.

To train a model:

  1. In AI Physics Training, navigate to Models and click New Model.
  2. Select the AI Dataset you created and review the input and output parameters. Confirm that the correct variables are included.
  3. Choose how to split your data: you can automatically split into training and test sets, or use separate dedicated datasets for each.
  4. Select a model architecture. AI Physics includes several production-ready architectures. DoMINO, GeoTransolver, and MeshGraphNet are provided by NVIDIA PhysicsNeMo.  PhysicsNeMo is built on top of PyTorch and is released under the Apache 2.0 license.
    • DoMINO — recommended for steady-state CFD surface variable prediction (e.g., surface pressure, wall shear stress, drag and lift coefficients)
    • TwoStream Transformer — highly efficient and suitable for both CFD and FEA use cases
    • GeoTransolver — a geometry-aware transformer architecture designed for predictions over complex 3D geometries on unstructured meshes, where accurately capturing geometric relationships between mesh points is important
    • MeshGraphNet — a graph neural network architecture well-suited for FEA problems with complex deformation and stress field predictions

For most use cases, the default architecture and parameters are a good starting point. If you want to adjust learning rates, batch sizes, or other settings, expand Advanced Parameters.

  1. Select a GPU hardware configuration and click Submit Training Job. You can monitor the associated Rescale job from the platform while training is in progress.
  2. When training completes, review the built-in evaluation dashboards to verify model quality. Dashboards show R² scores, residual distributions, and 3D error visualizations so you can understand where the model performs well and where it has limitations.
  3. The trained model is saved as an AI Model and appears in the AI Models table in Rescale.

Fine-tuning an existing model: To refine a model rather than starting from scratch, go to Models > Training Approach and select Fine-tune Existing. This resumes training from a previous model checkpoint. If you switch to a different dataset for fine-tuning, make sure it uses the same input and output variable schema as the original dataset.

Running multiple training sessions: You can train multiple models on the same dataset to compare architectures or hyperparameter settings. Use the evaluation dashboards to compare results before committing to a model for inference.

Run Inference on the Surrogate Model

Once a model is trained, you can run inference to predict simulation outputs for new input configurations — without launching a solver. AI Physics offers several inference options depending on your workflow and environment.

OptionBest for
AI Physics TrainingQuick interactive exploration while actively developing a model
AI Physics InferenceDedicated inference sessions on AI Models, without requiring a storage device
Local inference runner and clientRunning inference on a local workstation or laptop, including offline and on-premises environments
CAD plug-ins (Blender, Autodesk Alias)Running inference natively inside your CAD tool

Run Inference in AI Physics Training

You can run inference directly in AI Physics Training while reviewing a trained model. This is the quickest way to explore model predictions during model development.

  1. In AI Physics Training, navigate to the Inference tab
  2. In the Model panel, click Change to select the Model you would like to run inference on
  3. Configure the global input variables you want to vary using the input controls.
  4. Click Run Inference to generate a prediction. Results are displayed as an interactive 3D visualization and you can change the output displayed. 
  5. Adjust inputs and re-run to explore how outputs change across your design space.

Run Inference in AI Physics Inference

AI Physics Inference is a dedicated inference environment that does not require a storage device to run inference on your AI Models. 

  1. From the AI Models page in Rescale, click Run Inference.
  2. In the create workstation page, select the workstation hardware to run AI Physics Inference and click Submit.
  3. Once the workstation is launched, select Open App from the workstation status page.
  4. Running inference is the same as with AI Physics Training.

Run Inference Locally

The local inference runner and client let you download trained models from Rescale and run inference on any workstation or laptop — including offline and on-premises environments. The rescale-ai-client Python package provides access to the local inference runner and a standard API for building custom interfaces.

Note: For access to the local inference runner and client, contact your Rescale representative. 

Run Inference in CAD Tools

Rescale provides inference plug-ins for Blender and Autodesk Alias so designers can run surrogate model predictions natively within their CAD environment.

  1. To run inference on a given Model with Blender, navigate to Models from AI Physics Training or AI Physics Inference. 
  2. Navigate to the Model and version that you want to run inference on and click Run Inference in Blender. This launches Blender with the Model loaded and the Rescale AI Physics plug-in installed. 
  3. Adjust global inputs and geometry directly in the Blender environment, then run inference to see predicted outputs overlaid on your geometry in near real time.

Note: Surrogate predictions are most reliable within the range of inputs covered by your training data. Extrapolating beyond that range will produce less accurate results. It is good practice to validate a sample of predictions against full solver results before using the model for critical decisions.

Note: For access to the Autodesk Alias inference plug-in, contact your Rescale representative. 

Tutorials

Follow the tutorials below to train your first surrogate model end-to-end. Each tutorial uses pre-prepared job results so you can walk through the full AI Physics workflow — dataset creation, model training, and inference — without setting up your own DOE first.

FAQs

What is a surrogate model, and why would I use one? A surrogate model is trained on completed simulation results. Once trained, it can predict outputs for new inputs in seconds rather than hours. Surrogate models are useful for design space exploration, sensitivity analysis, and optimization studies where running a full solver for every configuration would be too expensive or slow.

Do I need AI or machine learning experience to use AI Physics? No. AI Physics is designed for simulation engineers. The Jupyter Notebook templates, default model parameters, and built-in evaluation dashboards guide you through each step. An AI copilot is also available in the notebook interface to help answer questions and suggest next steps using natural language.

How do I know if my trained model is accurate enough to use? After training, review the evaluation dashboards in AI Physics Training. These show R² scores broken down by output variable, residual distributions, and 3D error visualizations across your test cases. A high R² and low residuals across your test set indicate the model generalizes well. Always validate a sample of predictions against full solver runs before using the model for critical decisions.

Can I retrain or fine-tune a model after the initial training run? Yes. In AI Physics Training, go to Models > Training Approach and select Fine-tune Existing to resume training from a previous checkpoint. This is useful when you want to improve accuracy without starting from scratch, or when you have new training data to add.

What if I’m using a solver that isn’t listed as supported? AI Physics requires Metadata Extraction and AI Extraction Automations to be available for your solver. If your solver is not yet supported, contact your Rescale representative. Solver support is expanding over time, and your use case may inform the roadmap.

×