A General Atomics-led team has secured a three-year, $7.4 million grant from the Department of Energy to to build an integrated artificial intelligence and machine learning tool researchers can use to analyze fusion science data.
The partnership seeks to help scientists access big data sets through the FDP and create AI/ML models intended for demonstrating fusion energy on a decadal timescale.
UC San Diego and Sapientai, a software developer headquartered in Austin, will provide a suite of modeling tools for integration with the platform to be deployed at the university’s supercomputer center.
General Atomics will equip the FDP with its TokSearch data processing tool, while HPE will contribute its Common Metadata Framework to the effort.
Brian Sammuli, deputy director of General Atomics’ Advanced Computing Center of Excellence, noted he believes AI/ML research advancements are key to accelerating the development of fusion reactors.
“The success of the FDP will be measured by how well we serve the needs of the fusion and broader data science community, including students and researchers from universities, national laboratories and industry,” added Raffi Nazikian, a General Atomics senior director.