Transformational AI Models Consortium (ModCon)
Argonne is helping shape the Genesis Mission’s direction by leading the Transformational AI Models Consortium (ModCon). The cornerstone of the Genesis Mission’s AI models and data efforts, ModCon will build and deploy self-improving AI models that advance science, engineering and energy missions by harnessing DOE’s unique data, facilities and expertise. ModCon identified a set of initial “seed” teams with researchers from across DOE’s national labs, academia and industry. Below are the model teams with Argonne involvement.
Accelerating Scientific Discovery through AI-Driven Code Development
This Model Team will create an AI-driven co-development ecosystem to adapt and optimize flagship DOE applications, shortening the time from scientific concept to validated simulation.
AI Driven Co-Design for Microelectronics
This Model Team will transform the way microelectronics research is conducted to unlock new pathways for materials research and computer systems design, significantly reducing the time to develop tools for DOE science applications such as AI-driven data analysis and system control.
AI for Efficient Quantum Algorithms
This Model Team will create an integrated suite of AI-enabled tools and methodologies that advance the frontiers of quantum computer science to accelerate the discovery of new quantum algorithms.
AI for Planning and Operation of the U.S. Power Grid
This Model Team will use vast amounts of grid data to develop a foundational AI model that will help incorporate AI, including autonomous systems, into power system planning and operations. The effort will accelerate the secure and reliable modernization of the U.S. power grid.
AI Foundational Model Transforming Combustion Science and Technology for Energy and National Security
This Model Team will use AI to enable key breakthroughs in next-generation fuel combustion technologies such as predicting and understanding rare safety-critical events, real-time forecasting and control, and rapid co-design of fuels and engines. This effort will reduce dependence on foreign energy sources, ensure the operational readiness of defense systems, slash fuel and engine design cycles, reduce maintenance costs, and create AI-driven workflows for combustion science.
America’s AI Revolution Transforms Scientific Discovery at the Speed of Light
This Model Team will speed breakthroughs in microelectronics, medicine, advanced manufacturing, and energy security by transforming the world’s top scientific facilities into intelligent, self-driving engines of discovery. The team will use Synergistic Neutron and Photon Autonomous Science – Imaging (SYNAPS-I), a data analysis platform that fundamentally changes how experiments are conducted, empowering U.S. scientists to make progress at highly accelerated speeds.
CM2US: Critical Minerals and Materials to Unlock Supply
This Model Team will help secure the domestic supply chain of critical minerals and materials by revolutionizing their discovery, extraction, and processing using an AI-driven engine that acts as a strategic guide for the entire supply chain. The effort will produce a dynamic digital map of the process from mining to market.
FAMOUS: Foundational AI Models for Optimizing and Understanding Biological Systems
This Model Team will use AI to enable synthetic biology approaches that could reinvent manufacturing, agriculture and resource management. The team will leverage advanced AI to decipher protein and pathway function, automate data generation and collection, and integrate DOE’s experimental and supercomputing systems with biotech and AI companies.
From Quarks to Cosmos Through the Lens of AI
This Model Team will pioneer a new AI frontier, physics-informed AI, that synthesizes knowledge from the most advanced experiments ever built and combines it with sophisticated simulations, modeling and theory. The effort could facilitate a new understanding of the universe while providing industry with a framework for deploying and refining AI on massive datasets.
Fusion-FM: A Foundational Model for Magnetic Confinement Fusion
This Model Team will build a single pre-trained foundation model that reduces the amount of time to develop design and engineering studies involving magnetic confinement fusion.
MAIQMag: Multimodal AI for 2D Quantum Magnets
This Model Team will use multimodal data and an AI-driven workflow to accelerate the discovery and design of functional quantum magnetic materials. The effort will position the U.S. to lead in applying AI to quantum materials by uniting world-class experimental capabilities with advanced computation.
MOAT: Multi-Office Particle Accelerator Team
This Model Team will transform how particle accelerators and light sources are operated, optimized and designed by connecting data, expertise and innovation across the DOE complex. The team will establish the technical foundation and collaborative framework for continuous advancement while creating AI methodologies applicable to other complex facilities and industrial systems.
PROMETHEUS: A Revolution in Design and Operation of Nuclear Power Plants
This Model Team will revolutionize nuclear fission energy by using AI to design, manufacture and operate reactors with minimal human intervention in a first-of-its-kind public-private partnership. The effort will deliver a digital platform for quickly deploying advanced nuclear systems at scale, saving billions per gigawatt, providing reliable power, and establishing U.S. leadership in next-generation energy.