Operational safety at mission-critical work sites is a top priority given the complex and hazardous nature of daily tasks. This paper presents the Human-Agent Risk Navigation and Event Safety System (HARNESS), a modular AI framework designed to forecast hazardous events and analyze operational risks in U.S. Department of Energy (DOE) environments. HARNESS integrates Large Language Models (LLMs) with structured work data, historical event retrieval, and risk analysis to proactively identify potential hazards. A human-in-the-loop mechanism allows subject matter experts (SMEs) to refine predictions, creating an adaptive learning loop that enhances performance over time. By combining SME collaboration with iterative agentic reasoning, HARNESS improves the reliability and efficiency of predictive safety systems. Preliminary deployment shows promising results, with future work focusing on quantitative evaluation of accuracy, SME agreement, and decision latency reduction.

The United States has formed a $1bn partnership with Advanced Micro Devices (AMD) to construct two supercomputers that will tackle large scientific problems ranging from nuclear power to cancer treatments to national security. The Reuters news agency first reported the new partnership, citing Energy Secretary Chris Wright and AMD CEO Lisa Su. The machines can accelerate the process of making scientific discoveries in areas the US is focused on. Energy Secretary Wright said the systems would "supercharge" advances in nuclear power and fusion energy, technologies for defence and national security, and the development of drugs. Scientists and companies are trying to replicate fusion, the reaction that fuels the sun, by jamming light atoms in a plasma gas under intense heat and pressure to release massive amounts of energy.

The AI for Nuclear Energy workshop at Oak Ridge National Laboratory evaluated the potential of Large Language Models (LLMs) to accelerate fusion and fission research. Fourteen interdisciplinary teams explored diverse nuclear science challenges using ChatGPT, Gemini, Claude, and other AI models over a single day. Applications ranged from developing foundation models for fusion reactor control to automating Monte Carlo simulations, predicting material degradation, and designing experimental programs for advanced reactors. Teams employed structured workflows combining prompt engineering, deep research capabilities, and iterative refinement to generate hypotheses, prototype code, and research strategies. Key findings demonstrate that LLMs excel at early-stage exploration, literature synthesis, and workflow design, successfully identifying research gaps and generating plausible experimental frameworks. However, significant limitations emerged, including difficulties with novel materials designs, advanced code generation for modeling and simulation, and domain-specific details requiring expert validation. The successful outcomes resulted from expert-driven prompt engineering and treating AI as a complementary tool rather than a replacement for physics-based methods. The workshop validated AI's potential to accelerate nuclear energy research through rapid iteration and cross-disciplinary synthesis while highlighting the need for curated nuclear-specific datasets, workflow automation, and specialized model development. These results provide a roadmap for integrating AI tools into nuclear science workflows, potentially reducing development cycles for safer, more efficient nuclear energy systems while maintaining rigorous scientific standards.

Electron and scanning probe microscopy produce vast amounts of data in the form of images or hyperspectral data, such as EELS or 4D STEM, that contain information on a wide range of structural, physical, and chemical properties of materials. To extract valuable insights from these data, it is crucial to identify physically separate regions in the data, such as phases, ferroic variants, and boundaries between them. In order to derive an easily interpretable feature analysis, combining with well-defined boundaries in a principled and unsupervised manner, here we present a physics augmented machine learning method which combines the capability of Variational Autoencoders to disentangle factors of variability within the data and the physics driven loss function that seeks to minimize the total length of the discontinuities in images corresponding to latent representations. Our method is applied to various materials, including NiO-LSMO, BiFeO3, and graphene. The results demonstrate the effectiveness of our approach in extracting meaningful information from large volumes of imaging data. The fully notebook containing implementation of the code and analysis workflow is available at https://github.com/arpanbiswas52/PaperNotebooks

ORNL Weinberg Fellow Addis Fuhr uses quantum chemistry and machine learning methods to advance new materials. When Addis Fuhr was growing up in Bakersfield, California, he enjoyed visiting the mall to gaze at crystals and rocks in the gem store. "I was always fascinated and loved how the different crystals looked and how they would get their different colors," he said. "I now know it's from impurities." It was impossible to see at the time, but the future Alvin M. Weinberg Fellow at the Department of Energy's Oak Ridge National Laboratory had identified a potential career option.

Paul Brackman loads 3D-printed metal samples into a tower for examination using an X-ray CT scan in DOE's Manufacturing Demonstration Facility at ORNL.

HPCwire presents our interview with Bronson Messer, distinguished scientist and director of Science at the Oak Ridge Leadership Computing Facility (OLCF), ORNL, and an HPCwire 2022 Person to Watch. Messer recaps ORNL's journey to exascale and sheds light on how all the pieces line up to support the all-important science. Also covered are the role of the Exascale Computing Project, insights into architectural directions and evolving HPC-AI synergies. This interview was conducted by email earlier this year. Bronson, congratulations on being named a 2022 HPCwire Person to Watch! Can you give us a summary overview of your responsibilities at Oak Ridge Leadership Computing Facility and what your position entails?

Companies who have some success with their initial AI projects are seeking ways to accelerate adoption to deliver more value to the business. One researcher has defined an AI Adoption Maturity Model that presents a roadmap for accelerating AI adoption. The first stage of the six-step AI adoption maturity model is the digitization of work, turning work in the physical world into digital processes that can be tracked and recorded as data, suggests Dr. Michael Wu, chief AI strategist for PROS Holdings, providing AI-based software as a service for pricing optimization, with a focus on the airline industry. "This stage is all about getting the data, which is the raw material for AI," stated Wu, in an account from ZDNet. "If you are on the digital transformation bandwagon, good for you. You are already in Stage 1 of this maturity curve."

The Neutron Sciences Directorate (NScD) at Oak Ridge National Laboratory (ORNL) operates the High Flux Isotope Reactor (HFIR), the United States' highest flux reactor based neutron source, and the Spallation Neutron Source (SNS), the world's most intense pulsed accelerator based neutron source. Together these facilities operate 30 instruments for neutron scattering research, each year carrying out in excess of 1,000 experiments in the physical, chemical, materials, biological and medical sciences. HFIR also provides unique facilities for isotope production and neutron irradiation. To learn more about Neutron Sciences at ORNL go to: http://neutrons.ornl.gov. Oak Ridge National Laboratory is also a leader in computational and computer science, with unique strengths in high-performance computing and data analytics with applications to the physical and biological sciences.

Oak Ridge National Laboratory is behind the development of a new type of artificial intelligence (AI) software called Peregrine, meant to improve the quality of functional parts being produced via powder bed 3D printers. Peregrine requires no "expensive characterization equipment," yet possesses the ability to evaluate parts during manufacturing. "Capturing that information creates a digital'clone' for each part, providing a trove of data from the raw material to the operational component," said Vincent Paquit, leader of advanced manufacturing data analytics research as part of ORNL's Imaging, Signals and Machine Learning group. "We then use that data to qualify the part and to inform future builds across multiple part geometries and with multiple materials, achieving new levels of automation and manufacturing quality assurance." Oak Ridge National Laboratory researcher Chase Joslin uses Peregrine software to monitor and analyze a component being 3D printed at the Manufacturing Demonstration Facility at ORNL (Image: Luke Scime, ORNL, U.S. Dept. of Energy) The software is based on a convolutional neural network that imitates the human brain, rapidly evaluating images from cameras during printing.