Machine Discovery’s AI-powered Discovery Platform delivers acceleration for compute-intensive optimization and prediction tasks and will be deployed by world-leading teams to support research aimed at the realization of commercial fusion power plants. The Prosperity Partnership project is a multi-year collaboration between First Light Fusion, the University of Oxford, the University of York, Imperial College London, and Machine Discovery. The objective is to explore a new method for creating fusion power that could eventually be scaled to provide safe, clean, and abundant energy.
The AI-Powered platform from Machine Discovery is being deployed to accelerate compute-intensive tasks.
Machine Discovery’s unique AI platform offers the partnership members the ability to manage complex collaborative projects across large teams, with a large number of simulation runs. The platform’s novel emulation technology creates, from the simulation output results, rapid neural-network-based models for prediction, delivering many orders of magnitude faster prediction with high accuracy. The platform’s optimization engine uses AI algorithms for optimization and sampling and combines simulation and neural-network model outputs to enable the exploration of a significantly larger design space at a record speed.
Under the new partnership, researchers from across the three universities and two companies will work together to study the flow of heat, matter, and radiation in First Light Fusion’s unique targets, which have complex interfaces between vastly different pressures and temperatures.
“Our objective is to enable the delivery of fusion energy as fast as possible by providing an AI-powered solution for compute-intensive tasks to achieve significant productivity,” said Professor Gianluca Gregori co-founder of Machine Discovery. “We are pleased to be a member of this Prosperity Partnership, as the scope of the project is well aligned with our strategy of leveraging AI technology to accelerate the development of low-cost clean energy.”
SOURCE: PR Newswire