NVIDIA PhysicsNeMoNVIDIA
|
STOCHOSPI Probaligence GmbH
|
|||||
Related Products
|
||||||
About
NVIDIA PhysicsNeMo is an open source Python deep-learning framework for building, training, fine-tuning, and inferring physics-AI models that combine physics knowledge with data to accelerate simulations, create high-fidelity surrogate models, and enable near-real-time predictions across domains such as computational fluid dynamics, structural mechanics, electromagnetics, weather and climate, and digital twin applications. It provides scalable, GPU-accelerated tools and Python APIs built on PyTorch and released under the Apache 2.0 license, offering curated model architectures including physics-informed neural networks, neural operators, graph neural networks, and generative AI–based approaches so developers can harness physics-driven causality alongside observed data for engineering-grade modeling. PhysicsNeMo includes end-to-end training pipelines from geometry ingestion to differential equations, reference application recipes to jump-start workflows.
|
About
STOCHOS is probabilistic AI for engineering and R&D. It learns from the simulation, test, and measurement data a team already has and predicts new variants in seconds, with an uncertainty on every prediction, so engineers know when to trust a result and when to run the solver instead. Built on DIM-GP, it works with small datasets, typically tens to a few hundred samples, and with scalars, signals, 2D and 3D fields, meshes, geometries, and images. Methods: surrogate modeling, uncertainty quantification, Bayesian and multi-objective optimization, multi-fidelity modeling, sensitivity analysis, and generative geometry. STOCHOS Flow, the visual workbench, builds the workflows without code and ships them to the team as web apps. Runs on your own hardware, installs offline. From PI Probaligence, founded 2018 in Grafing bei München, part of the CADFEM Group and an Ansys Technology Partner.
|
|||||
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
Platforms Supported
Windows
Supported
Mac
Not Supported
Linux
Supported
Cloud
Not Supported
On-Premises
Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Audience
Researchers, engineers, and developers who need an open source Python AI framework to build, train, fine-tune, and deploy physics-informed machine learning models for simulation, digital twins, and real-time prediction
|
Audience
Engineers, Researcher, Simulation Engineers, Lab Researcher
|
|||||
Support
Phone Support
Supported
24/7 Live Support
Not Supported
Online
Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
API
Offers API
Supported
|
API
Offers API
Not Supported
|
|||||
Screenshots and Videos |
Screenshots and VideosNo images available
|
|||||
Pricing
Free
Free Version
Supported
Free Trial
Not Supported
|
PricingQuote on request
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Supported
Webinars
Supported
Live Online
Supported
In Person
Not Supported
|
Training
Documentation
Supported
Webinars
Supported
Live Online
Supported
In Person
Supported
|
|||||
Company InformationNVIDIA
Founded: 1993
United States
developer.nvidia.com/physicsnemo
|
Company InformationPI Probaligence GmbH
Founded: 2018
Germany
probaligence.com
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
||||||
|
|
|
|||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
PyTorch
Not Supported
Python
Not Supported
|
||||||
|
|
|