Nvidia has launched a platform for creating scientific digital twins that accelerates physics machine-learning models, with Siemens Gamesa as a lead developer for its wind farm modelling.
The accelerated digital twins platform consists of the Modulus AI framework for developing physics-ML neural network models, and the Omniverse 3D virtual world simulation platform.
The platform can create interactive AI simulations in real time that are more realistic with the physics engines to accurately reflect the real world, accelerating simulations such as computational fluid dynamics up to 10,000x faster than traditional methods for engineering simulation and design optimization workflows. This enables researchers to model complex systems, such as extreme weather events, with higher speed and accuracy when compared to previous AI models.
Siemens Gamesa Renewable Energy is using the system to optimize the design of wind turbines and wind farms.
This uses AI models to accurately model the effects of turbine placement on their performance in a wide variety of weather scenarios. This is expected to lead to optimized wind park layouts capable of producing up to 20 percent more power than previous designs.
“The collaboration between Siemens Gamesa and Nvidia has meant a great step forward in accelerating both the computational speed and the deployment speed of our latest algorithms development in such a complex field as computational fluid dynamics, and set the foundations for a strong partnership in the future,” said Sergio Dominguez, onshore digital portfolio manager at Siemens Gamesa.
Another platform, the FourCastNet physics-ML model, emulates global weather patterns and predicts extreme weather events, such as hurricanes, with greater confidence and up to 45,000x faster than traditional numerical prediction models.
This is trained on 10Tbytes of date from Earth observations and part of Nvidia’s project to build a digital twin of the Earth in Omniverse.
“Accelerated computing with AI at data centre scale has the potential to deliver millionfold increases in performance to tackle challenges, such as mitigating climate change, discovering drugs and finding new sources of renewable energy,” said Ian Buck, vice president of Accelerated Computing at Nvidia. “The AI-enabled framework for scientific digital twins equips researchers to pursue solutions to these massive problems.”
Modulus also takes both data and the governing physics into account to train a neural network that creates an AI surrogate model for digital twins. The surrogate can then infer new system behaviour in real time, enabling dynamic and iterative workflows. Integration with Omniverse brings visualization and real-time interactive exploration.
The latest release of Modulus allows data-driven training using the Fourier neural operator, a framework enabling AI to solve related partial differential equations simultaneously. It also integrates ML models with weather and climate data, such as the ERA5 dataset from the European Centre for Medium-Range Weather Forecasts.
“Digital twins allow researchers and decision-makers to interact with data and rapidly explore what-if scenarios, which are nearly impossible with traditional modeling techniques because they’re expensive and time consuming,” said Karthik Kashinath, senior developer technology scientist and engineer at Nvidia. “Central to Earth-2, FourCastNet enables the development of Earth’s digital twin by emulating the physics and dynamics of global weather faster and more accurately.”
The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network.
The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user.
The technical storage or access that is used exclusively for statistical purposes.The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you.
The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes.