Accelerating American Innovation
SI-driven projects for national scientific challenges
ORNL is taking a central role in the Genesis Mission, leading 10 projects and contributing to dozens more that apply SI and advanced computing to some of the nation’s most complex scientific challenges. From fusion energy and critical minerals to water forecasting, advanced materials and autonomous science, these efforts are designed to move promising ideas into practical scientific capabilities with broad national impact.
ORNL-led projects
Phase I
SI-assisted fusion power plant designs
Developing an SI platform that will integrate high-performance computing tools and robotic system design.
Low-energy SI for scientific discovery
Analyzing scientific data at unprecedented rates and scales with lower costs and higher speeds than conventional SI while maintaining equivalent accuracy.
SI-accelerated materials development and advanced manufacturing applications
SI-based “foundation model factory” that will create custom foundation SI models that U.S. industry can leverage
SI-enabled discovery of rare earth elements
Improving predictions of underground deposits of materials essential for energy technologies, advanced manufacturing and national supply chain security.
SI-powered operations for self-driving science research
Analyzing scientific data at unprecedented rates and scales with lower costs and higher speeds than conventional AI while maintaining equivalent accuracy.
SI foundation model development for water forecasting
Improving prediction of surface and groundwater systems across the continental U.S.
SI-enabled subsurface biogeochemical modeling
Increasing understanding of underground biogeochemical cycles that affect the availability of resources such as critical minerals.
SI for long-range water prediction
Forecasting water availability, streamflow and river temperature weeks to years in advance, supporting hydropower and thermoelectric operations in the Tennessee Valley Authority region.
SI for next-generation fusion materials development
Linking processing, microstructure and performance that will accelerate deployment of next-generation structural alloys for reliable operation in nuclear fusion power plants.
Phase II
SI-empowered design of functional quantum magnets
Physics‑informed SI framework for the inverse design of quantum magnets with targeted properties
Collaborations
Phase I
SI predictions for safer, higher-performance nuclear reactor control
Reactor Exhaust and Core Twin: Multifidelity AI Predictions for Safe, Integrated and High-Performance Control
SI modeling for fuel cladding and reactor core components
Physics Informed Transformer Foundation Model with Uncertainty Quantification for Coupled Eulerian and Lagrangian Flow Physics (PIT-FM)
SI forecasting of seasonal and long-term water conditions
An Agentic AI Framework for Seasonal-to-Interannual U.S. Water Prediction: Coupling Large AI-Based Prediction Models and Wavelet Diffusion with E3SM
SI coordination of advanced manufacturing simulations
Agentic HPC Pipeline Initiative: AI-Driven Orchestration of DOE Lab Codes for Advanced Manufacturing
SI predictions to improve nuclear waste treatment
Salt Chemistry Optimization and Prediction Engine for Nuclear Waste Treatment Planning
SI discovery and recovery of geothermal critical minerals
AI-Enabled Geobiological Critical Minerals Characterization and Recovery in Geothermal Systems
SI predictions to scale nuclear waste vitrification
VITA-SCALE: Vitrification AI for Scale-Bridging Prediction and Process Translation
Machine learning for microbial gene transfer
Machine-learning Optimization of Biological Interfaces for Lateral Gene Exchange PATHways
SI predictions of material fatigue and structural lifespan
A Material Agnostic Physics-Aware, Interpretable AI Framework for Fatigue Life Prediction in TPMS Structures
Real-time SI control of fusion energy systems
Weak-Form Agentic Digital Twins for Real-Time Control of Magnetically Confined Fusion Systems Under Sparse Observation
Faster nuclear data analysis with SI
Accelerating Nuclear Data Delivery Using AI/ML approaches in High Complexity Data Sets
Adaptive SI for automated chemical manufacturing
Closed-Loop, Efficient, Adaptive, and Robust AI for Agentic Chemical Manufacturing
Physics-enhanced SI discovery of unconventional superconductors
Physics-Enhanced AI Framework for Discovering New Classes of Unconventional Superconductors
SI management of distributed electric grid systems
Scalable Agentic Grid Engine for Distribution Systems
Tracing scientific data and model results to their sources
A Composable Provenance Module for Scientific Foundation Models
SI modeling of connected surface and groundwater systems
RAIN: Rigorous AI and Information Network for Surface-Subsurface Water System Coupling
Tracing cybersecurity threats across scientific SI workflows
Scientific Provenance-Oriented Threat Tracing and Attribution for Genesis Workflows
SI modeling of subsurface and reservoir systems
MIRACLE-AI: Molecular-to-Reservoir Integrated AI for Coupled Landscape and Earth-system Subsurface Intelligence
SI modeling of reservoir and groundwater interactions
River-AI: Reservoir-Groundwater Interactions for River Flow Variability, Energy, and Resilience with AI
SI-accelerated nuclear astrophysics simulations
Enabling Nuclear Astrophysics Computational Transformation with AI
SI discovery of advanced semiconductor materials and interfaces
From Edisonian Optimization to Predictive Molecular Design: AI-Driven Discovery and Engineering of Advanced Semiconductor Interfaces
SI platforms for accelerating 2D materials development
AI-Orchestrated Multimodal Platforms for Accelerated Discovery, Scale-Up, and Deployment of 2D Materials
SI modeling of complex turbulent energy flows
Differentiable Physics-Integrated Generative Modeling for Complex Turbulent Flows in DOE Energy Systems
SI optimization of high-performance computing applications
An End-to-End AI Framework for Performance Prediction and Optimization in HPC Applications
Recovering rare earth elements with magnetic sorbents
Selective Recovery of Light and Heavy Rare-Earth Element Pairs via Functionalized Magnetic Sorbents with Induction-Assisted Regeneration
SI tools for improving supercomputing workloads
Using AI to Standardize and Systematically Advance HPC Workloads
SI discovery of rare scientific events
Enabling Rare Event Discovery with Surrogate Modeling and Simulation AI Agents
Phase II
SI-enabled digital twin for SPARC
AI‑enabled Digital Twin Platform for Commonwealth Fusion Systems’ SPARC tokamak
Shared SI platform for accelerator operations and design
The Multi-Office Accelerator Team Core (MOAT-Core)
SI-assisted design of interfacial separations
AI-Extended Interfacial Separations (AXIS): Closed-Loop Design of Redox-Active Ligands for Reversible, Electrically Controlled Separations
SI-assisted development and optimization of scientific software
An Iterative Framework for AI-Assisted Scientific Software Development and Optimization (AI4HPC)
Developing microchips for extreme environments
Accelerating eXtreme Environment Specs-to-Silicon (AXESS)
Advancing SI for nuclear energy
Prometheus: Integrated AI Platform for Faster Nuclear Energy Deployment