Nvidia Announces Digital Twin Platform

Image credit: iStockphoto/Ekkasit919

AI specialist NVIDIA has announced a platform for scientific digital twins that accelerates physics machine-learning models to solve million-x scale science and engineering problems thousands of times faster.

Details of the platform were announced at the company’s GTC 2022 event in a keynote from founder Jensen Huang.

The accelerated digital twins platform for scientific computing consists of the NVIDIA Modulus AI framework for developing physics-ML neural network models and the NVIDIA Omniverse 3D virtual world simulation platform.

The platform can create interactive AI simulations in real-time that are physics-informed 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. It enables researchers to model complex systems, such as extreme weather events, with higher speed and accuracy when compared to previous AI models.

The company showed two example applications of the technology at the event. The NVIDIA 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. In addition, Siemens Gamesa Renewable Energy uses AI to optimize wind turbine design.

"Accelerated computing with AI at data center 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.

"NVIDIA's AI-enabled framework for scientific digital twins equips researchers to pursue solutions to these massive problems."

NVIDIA Modulus 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 behavior 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 integrates ML models with weather and climate data, such as the ERA5 dataset from the European Centre for Medium-Range Weather Forecasts.

Complementing Modulus, NVIDIA Omniverse is a real-time virtual world simulation and 3D design collaboration platform. It enables the real-time visualization and interactive exploration of digital twins using the output surrogate model from Modulus.

The digital twins platform is also turbocharging simulation research for the layout of wind farms equipped with Siemens Gamesa Renewable Energy wind turbines, making it possible for the first time to use AI 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%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.

Image credit: iStockphoto/Ekkasit919