Generating Electricity Managed by Intelligent Nuclear Assets

ARPA-E GEMINA Program Graphic

Release Date:
Project Count:

Program Description:

Generating Electricity Managed by Intelligent Nuclear Assets (GEMINA) aims to develop digital twin technology for advanced nuclear reactors and transform operations and maintenance (O&M) systems in the next generation of nuclear power plants. ARPA-E is looking for interdisciplinary teams to develop digital twins, or a similar technology, for an advanced reactor design as the foundation of their O&M strategy. Performers will design tools that introduce greater flexibility in reactor systems, increased autonomy in operations, and faster design iteration. The goal is to create a 10x reduction in O&M costs at advanced reactor power plants, thereby improving their economic competitiveness. To accomplish this, teams will apply diverse technologies that are driving efficiencies in other industries, such as artificial intelligence (AI), advanced control systems, predictive maintenance, and model-based fault detection. Projects will focus on O&M solutions for the reactor core, balance of plant (BOP), or entire reactor plant system (including both the reactor core and BOP). Because advanced reactors are still in design phase, with no physical units operating, teams working on core operations will also develop cyber-physical systems that simulate advanced reactor core operating dynamics using a combination of non-nuclear experimental facilities (e.g., test or flow loops) and software. Teams will use these systems as the “real asset,” a surrogate to test their digital twin platforms.

Innovation Need:

Many U.S. nuclear reactors are shutting down prematurely. Eight have closed in the last six years; 10 more are scheduled to be decommissioned by 2025. The reason is that although nuclear power is considered by many to be necessary to achieve a zero-carbon grid, nuclear power plants are comparatively cost-intensive in some markets. Many industries are employing AI, advanced data analytics, distributed computing, powerful physics simulation tools, and other breakthroughs to advance autonomous, efficient, and low-cost O&M in their processes. O&M is approximately 80% of a reactor’s total generating cost. So far, the nuclear energy industry has not fully explored or applied these innovations, resulting in a profound need for the design of effective and low-cost advanced reactor O&M procedures. There is tremendous opportunity for innovation in advanced reactors, since learnings gained now can provide feedback into the designs, laying the groundwork for optimal O&M. GEMINA sets the stage for a future where advanced reactors operate with a staffing plan and fixed O&M costs more akin to those of a combined cycle natural gas plant than those of the legacy light-water reactor fleet.

Potential Impact:

The program goal is to reduce fixed O&M costs from ~13 $/MWh in the current fleet to ~2 $/MWh in the advanced fleet. Benefits include:


Establishing U.S. advanced reactor technological leadership and improving U.S. energy security with safe, reliable, dispatchable power for a robust and resilient electric power system;


Reducing energy-related emissions with a competitive, carbon-free electricity source; and


Increasing productivity and creating a competitive edge for advanced reactors.


Program Director:
Dr. Jenifer Shafer;Dr. Robert Ledoux
Press and General Inquiries Email:

Project Listing

Argonne National Laboratory (ANL) - Maintenance of Advanced Reactor Sensors and Components (MARS)
Electric Power Research Institute (EPRI) - Build-to-Replace: A New Paradigm for Reducing Advanced Reactor O&M Costs
Framatome - Digital Twin-Based Asset Performance and Reliability Diagnosis for the HTGR Reactor Cavity Cooling System Using Metroscope
General Electric (GE) Global Research - AI-Enabled Predictive Maintenance Digital Twins for Advanced Nuclear Reactors
Massachusetts Institute of Technology (MIT) - High-Fidelity Digital Twins for BWRX-300 Critical Systems
Massachusetts Institute of Technology (MIT) - Generation of Critical Irradiation Data to Enable Digital Twinning of Molten-Salt Reactors
Moltex Energy - SSR APPLIED - Automated Power Plants: Intelligent, Efficient, and Digitized
University of Michigan - PROJECT "SAFARI”- Secure Automation For Advanced Reactor Innovation
X-Energy - Advanced Operation & Maintenance Techniques Implemented in the Xe-100 Plant Digital Twin to Reduce Fixed O&M Cost