The DOE has selected Sandia to lead six projects and partner on 17 additional teams through the Genesis Mission, a national effort to accelerate scientific discovery by combining artificial intelligence, high-performance computing and advanced research capabilities.

The Genesis Mission is a historic national initiative led by the DOE, which is building the world’s most powerful integrated science discovery platform. By uniting government, industry, academia and philanthropy, it is accelerating breakthroughs in energy, scientific discovery and national security through a new platform that combines AI, supercomputing, quantum systems and advanced scientific instruments.

“Sandia’s selections reflect the breadth of our mission and our researchers’ ability to connect advanced computing, artificial intelligence and engineering expertise to national challenges,” said Labs Director Laura McGill. “Through the Genesis Mission, Sandia researchers will work with partners across the national laboratory system, industry and academia to leverage AI in new approaches that will accelerate discovery and develop new capabilities in service to the nation.”

The goal of the Phase I awards under DOE’s request for applications is to identify promising pathways toward transformative scientific capabilities and establish a foundation for future investment and scale. Project teams will design and demonstrate research workflows that integrate AI with scientific investigation, while rigorously evaluating whether those approaches can accelerate discovery, improve predictive capabilities, enhance experimentation or generate new scientific insights. Phase II awards support large-scale, multi-institutional efforts to advance AI solutions for more than two dozen national science and technology challenges.

Sandia will lead six projects selected for Genesis Mission support:

• Agent Bayes: A Foundation Model for Bayesian Scientific Reasoning — Led by Sandia researcher Tommie Catanach, the project will develop an AI reasoning framework to help scientists design experiments, compare models and test scientific theories against evidence using Bayesian methods.
• AI-Augmented Digital Twins for “Born-Digital” Fusion Material Interfaces — Led by Sandia researcher Mary Alice Cusentino, the project will use AI-assisted digital twins to accelerate development of fusion material interfaces designed to withstand extreme heat, radiation and mechanical stress.
• AI Framework for Real-Time Critical Mineral Resources Mapping and Characterization While Drilling — Led by Sandia researcher Guangping Xu, the project will develop an AI framework to integrate drilling, geophysical and geochemical data to support real-time mapping and characterization of critical mineral resources.
• Physics-Informed Transformer Foundation Model with Uncertainty Quantification for Coupled Eulerian and Lagrangian Flow Physics — Led by Sandia researcher Jackie Chen, the project will deliver a reusable, physics-constrained AI foundation model workflow to improve modeling of complex flows important to energy systems, including atmospheric wind flows, combustion and aerosols.
• Upscaling Particle-Resolved Aerosol-Cloud Microphysics with Generative Modeling — Led by Sandia researcher Lekha Patel, the project will use generative AI to improve how aerosol-cloud interactions are represented in models that support understanding of clouds, precipitation and water systems.
• MIRACLE-AI: Molecular-to-Reservoir Integrated AI for Coupled Landscape and Earth-System Subsurface Intelligence — Led by Sandia researcher Umakant Mishra, the project will develop an AI-guided framework to improve predictive understanding of coupled biological, chemical and hydrologic processes that affect geothermal and other subsurface energy systems.

Sandia researchers will contribute to 16 selected Phase I projects led by partner institutions, spanning AI-enabled research in materials discovery, water and energy systems, synthetic biology, critical minerals, quantum science, advanced nuclear technologies and electric grid analysis. Sandia is collaborating with several partners on a Phase II project focused on using AI to accelerate nuclear power plant design and licensing workflows.

“When we pair world-class AI tools with Sandia’s renowned experimental, computational and mission-relevant expertise, we build research workflows that are more powerful, efficient and reliable for complex national security and energy challenges,” said Jen Gaudioso, director of the Center for Computing Research and Sandia’s Genesis Mission program manager.

The selections were announced in conjunction with the Genesis Mission Summit in Washington, D.C., where leaders from DOE, the national laboratories, industry and academia convened to discuss collaborative approaches for advancing AI-enabled scientific infrastructure.

More information about DOE’s Genesis Mission announcement is available on the DOE website.