Second round of Genesis Mission selections includes 12 Phase II awards

The Department of Energy has announced the selection of 12 new Phase II awards and six new Phase I awards through its Genesis Mission, including projects related to fusion energy and high-radiation environments.

In July, the DOE announced the selection of 278 projects under the Genesis Mission, most of which were Phase I projects. Phase II awards are intended to scale up and expand projects that have already demonstrated potential for transformative scientific capability through multi-year funding.

Extreme environments: Nhan Tran, a Wilson Fellow at Fermilab, is leading a Phase II project titled "AXESS: Accelerating Extreme Environment Specs-to-Silicon." It aims to accelerate the development of rugged, high-performance microchips capable of operating in extreme conditions including space, ultra-cold environments, and high-radiation settings such as fusion machines.

According to Fermilab, the research team is building a framework that uses AI to speed up the chip-design process, dramatically reducing the time from chip specification to fabrication from months to weeks.

It is intended to help designers make decisions throughout what is typically a multistage process that relies on slow, manually operated tools. For electronics operating in extreme environments, this can require years of specialized work.

"Particle detectors must function in some of the most extreme environments in terms of radiation, cryogenic temperatures, and speed," said Tran. "As a result, we've built our own custom detectors for many years, and Fermilab has established deep expertise in microelectronics for extreme environments. More recently, we've developed tools and methods used across the community to integrate AI onto chips. All of this coming together within the Genesis Mission is a great opportunity for Fermilab to team up with others and use AI to significantly accelerate chip design."

University partners include Arizona State University, Georgia Institute of Technology, Massachusetts Institute of Technology, Purdue University, the University of California San Diego, and the University of Southern California. Among the other collaborators are Lawrence Berkeley, Oak Ridge, and Sandia National Laboratories; SLAC National Accelerator Laboratory; and industry partners, including Advanced Micro Devices, Dataerai, IBM, and Siemens EDA.

"Siemens is putting industrial-grade hardware design solutions behind the Genesis Mission," said David Burnette, engineering director for catapult high-level synthesis at Siemens Digital Industries Software. "By uniting Siemens's proven technologies with the breakthrough science at Fermilab and across the DOE labs, we're accelerating a new class of chips for quantum, fusion, and high-radiation environments-at a speed and scale the nation has never had."

FRIB operations: Ayan Paul, a research associate professor at Northeastern University in Boston, Mass., is leading a Phase II project titled "Agentic Assistance for Advanced Rare Isotope Separator (ARIS) Operations at the Facility for Rare Isotope Beams (FRIB): Beam Tuning, Calibration, Monitoring, and Knowledge Harvesting." It will develop an agentic AI system to safely streamline the operation and tuning of the FRIB particle separator.

According to Paul, weekly beam development at FRIB takes 16-24 hours, about half of which goes to manual isotope calibration. This project aims to develop three sets of AI agents to assist FRIB staff and users in planning experiments, tuning the machine, and monitoring the system.

"If the project targets are met, the team projects 500 additional hours of beam time for science at FRIB each year, corresponding to several more experiments," the project abstract states.

Michigan State University, where FRIB is located, and Gravitate AI are partners on this project.

Fusion digital twin: Thomas Looby at Commonwealth Fusion Systems is leading a Phase II project titled "Accelerating the Path to Commercial Fusion Energy via an AI-Enabled Digital Twin Platform for SPARC." It aims to build a digital twin to simulate and optimize operations of a fusion demonstration device.

CFS is a participant in the DOE Milestone Program currently developing SPARC, its tokamak prototype, and this project aims to use DOE supercomputers to process fusion data, strengthen AI tools, and advance digital twin visualization work that previously was started by CFS, Nvidia, and Siemens for SPARC.

This work is expected to support and accelerate tokamak operations by creating, sustaining, and optimizing fusion plasma scenarios between experimental pulses and connect plasma behavior with lifetime performance models of plasma-facing components.

While several fusion companies were selected to lead Phase I projects in the first round of Genesis Mission selections, CFS is the only private company leading a project in this second round. Collaborators include ORNL, Lawrence Livermore National Laboratory, Princeton Plasma Physics Laboratory, SLAC, MIT, Carnegie Mellon University, Ansys, General Atomics/DIII-D, Google DeepMind, and Nvidia.

CFS cofounder and chief science officer Brandon Sorbom said that the project "will convert decades of R&D performed across the U.S. fusion community into tools that can be applied to accelerate SPARC operations. Together, our team of public and private leaders in AI and fusion will be able to unify and apply decades of U.S. research and tackle some of the fusion industry's biggest challenges."

Waste processing: Kevin Brown, a research professor at Vanderbilt University, is leading a Phase I project titled "WasteChemAI: Chemical Speciation and Partitioning AI Framework for DOE Waste Processing and Disposal Optimization," which focuses on optimizing the chemical processing of nuclear waste.

"Chemical processing for nuclear waste management and long-term demonstration of environmental safety requires detailed understanding of the behavior of chemical species and radionuclides under a range of process and environmental conditions," Brown said. "The WasteChemAI project will use machine learning and artificial intelligence to dramatically accelerate the engineering evaluation processes and provide more reliable information along with quantified uncertainty."