AI | Lawrence Livermore National Laboratory

Artificial intelligence (AI) is a core capability at Lawrence Livermore National Laboratory (LLNL), supporting the Laboratory’s National Nuclear Security Administration (NNSA) mission through science, engineering and high-performance computing. LLNL applies advanced AI methods alongside experimental data and physics-based modeling to accelerate discovery, improve predictive understanding and strengthen mission execution. Researchers use AI to advance strategic deterrence, stockpile modernization, materials discovery, fusion research, advanced manufacturing and energy resilience, while emphasizing trust, validation and responsible use. LLNL contributes to the U.S. Department of Energy’s Genesis Mission by helping build AI-enabled capabilities for secure data access, models, infrastructure and partnerships, while demonstrating mission-focused workflows that accelerate simulation, manufacturing and materials discovery.

Lawrence Livermore National Laboratory is increasingly looking to AI, robotics and automation to help speed the process of advanced manufacturing. Pictured are (from left) Robotics and Automation scientists and engineers Tony Qin, Karly Knox, Abhik Sarkar, Aldair Gongora and Michael Troksa.

How LLNL is using AI, robotics and automation to accelerate advanced manufacturing

Lawrence Livermore National Laboratory (LLNL) scientists and engineers, in conjunction with the Department of Energy (DOE) and National Nuclear Security Administration (NNSA), are increasingly looking to AI, robotics and automation to help accelerate advanced manufacturing, materials discovery and experimental science. The work is part of a broader push to move faster from concept to deployment in mission-relevant technologies.

LLNL selected to lead 10 projects under DOE’s Genesis Mission

Lawrence Livermore National Laboratory (LLNL) scientists and engineers have been selected to lead 10 Phase I projects under the U.S. Department of Energy’s (DOE’s) Genesis Mission, applying AI to challenges spanning high-performance computing (HPC), fusion energy, Earth systems science, materials discovery, biology, quantum technologies and fundamental physics. LLNL researchers also will contribute to 19 additional Genesis Mission projects led by partner institutions across the national laboratories, academia and industry.

A collaboration of Lawrence Livermore National Laboratory, Sandia National Laboratories, Los Alamos National Laboratory and the Kansas City National Security Campus, Aires Tide brings together expertise across design, manufacturing and flight testing in a single cross-enterprise effort.

LLNL helps advance AI-driven design and simulation for NNSA Aires Tide collaboration

Lawrence Livermore National Laboratory (LLNL) is contributing AI-enabled payload optimization and advanced modeling and simulation expertise to Aires Tide, a collaborative National Nuclear Security Administration (NNSA) demonstration exploring new ways to design flight test vehicles. Developed in collaboration with Sandia National Laboratories, Los Alamos National Laboratory (LANL) and the Kansas City National Security Campus, Aires Tide brings together expertise across design, manufacturing and flight testing in a single cross-enterprise effort. The project is also an early example of the Department of Energy’s (DOE) Genesis Mission in practice.

Lawrence Livermore National Laboratory (LLNL) Director Kim Budil, fourth from left, joined a public-private panel on AI for science, where she highlighted LLNL capabilities and AI focus areas, including the National Ignition Facility, El Capitan, high-fidelity modeling and simulation and advanced materials and manufacturing.

LLNL showcases AI-enabled science, national security and energy innovation at AI+ Expo

LLNL leaders, scientists and engineers joined national voices at the Special Competitive Studies Project’s (SCSP) AI+ Expo May 7-9 in Washington, D.C., highlighting how AI is reshaping science, security and energy innovation. The public Expo brought together government, industry, academic and Department of Energy (DOE) national laboratories for three days of sessions, demonstrations and exhibits focused on AI, national security and U.S. technological competitiveness.

With recently awarded funding, LLNL will develop quantum and machine learning-accelerated software tools and apply them to discovering ultra-strong, lightweight magnets that are crucial for electronic motors, generators and high-performance information technology.

LLNL to harness quantum computing for next-generation magnets

Lawrence Livermore National Laboratory (LLNL) has been selected to lead a project that will receive $4.1 million in funding from the U.S. Department of Energy Advanced Research Projects Agency-Energy (ARPA-E) as part of the Quantum Computing for Computational Chemistry (QC³) program. QC³ seeks to develop and apply quantum algorithms to accelerate simulations of chemistry and materials science to advance commercial energy applications.

The Genesis Mission is a national effort to accelerate discovery by uniting AI, supercomputing, experiments and the infrastructure of the national laboratories. This episode explores the problem Genesis is trying to solve, the growing gap between the pace of scientific discovery and the scale of the challenges facing the nation. At Lawrence Livermore National Laboratory, this vision is turning into a reality through infrastructure, workforce training and governance.

Top row: Scanning electron microscopy images of two different steels: Bottom row: Characteristic texture patterns generated from a convolution neural network.

Materials science: Explainable machine learning for mission-critical materials

This highly cited review shows how to explain materials machine learning (ML) predictions. For LLNL’s national security work, it is critical to understand why a model predicts what it does, when it may fail and how uncertainty changes decisions. Explainable ML strengthens verification, auditability and risk‑informed decisions across stockpile management, energy security and advanced manufacturing.

Random simulations overlaid on predictions from a MaCC surrogate.

Fusion science: Reliable surrogates to design and interpret fusion shots

LLNL researchers developed fast surrogate models for inertial confinement fusion that remain consistent between high-fidelity simulations and experimental measurements. These surrogates significantly reduce design‑cycle time and help interpret shot outcomes without rerunning expensive codes for every scenario. At LLNL, this capability strengthens National Ignition Facility (NIF) shot planning, advances high‑energy‑density (HED) science and supports stockpile management and modernization.

A limited-angle computed tomography image showing the items inside a piece of luggage.

High-energy-density science: Limited-angle CT to see more with less data

This work reconstructs computed tomography (CT) images from limited‑angle data by combining a physics forward model with probabilistic diffusion. At LLNL, this method supports nondestructive evaluation and HED diagnostics by enabling confident conclusions when full-view scans are infeasible due to geometry, time, dose or access limits. Through this approach, researchers can extract actionable information from fewer measurements and provide uncertainty estimates to support high‑consequence decisions.