PPPL launches STELLAR-AI platform to accelerate fusion energy research

A new computing platform that pairs artificial intelligence (AI) with high performance computing aims to end the bottleneck holding back fusion energy research by speeding the simulations needed to advance the field.

2026-01-23

(Press-News.org) A new computing platform that pairs artificial intelligence (AI) with high performance computing aims to end the bottleneck holding back fusion energy research by speeding the simulations needed to advance the field.

The project — known as the Simulation, Technology, and Experiment Leveraging Learning-Accelerated Research enabled by AI (STELLAR-AI ) — will be led by the U.S. Department of Energy’s (DOE) Princeton Plasma Physics Laboratory (PPPL). STELLAR-AI will expand far beyond the Lab’s walls, however, bringing together national laboratories, universities, technology companies and industry partners to build the computational foundation the fusion community needs.

It can take months to run a single high-fidelity computer simulation or to train an artificially intelligent (AI) system capable of designing an ideal fusion system using existing infrastructure. STELLAR-AI is designed to reduce that timeline by using artificial intelligence. The platform connects computing resources directly to experimental devices, including PPPL's National Spherical Torus Experiment-Upgrade (NSTX-U), which is scheduled to go live this year, allowing researchers to analyze data as experiments occur.

Building the Computational Foundation for Fusion

Jonathan Menard, deputy director for research at PPPL, sees STELLAR-AI as a cornerstone of the U.S. fusion ecosystem: a dedicated, AI-driven research environment built specifically for the fusion energy mission. STELLAR-AI will pair speed with precision, accelerating the path to commercially viable fusion power.

“Fusion is a complex system of systems. We need AI and high performance computing to really optimize the design for economic construction and operation,” said Menard. "We want to link simulation technology and experiments — in particular, NSTX-U — with AI and partnerships to get to accelerated fusion.”

STELLAR-AI will achieve this goal by integrating CPUs, GPUs and QPUs in an ideal configuration of hardware for tackling the challenges facing private fusion companies as they race to bring a solution to market. CPUs, or central processing units, are standard computer chips that handle everyday computing tasks. GPUs, or graphics processing units, are specialized chips that excel at the parallel calculations needed for artificial intelligence. QPUs, or quantum processing units, use the principles of quantum physics to solve certain complex problems that would take traditional computers far longer to complete.

A critical part of the Genesis Mission

STELLAR-AI is part of the Genesis Mission, a national effort launched by executive order in November 2025 to use AI to speed up scientific discovery across DOE laboratories.

"The Genesis platform is an integrated, ambitious system that will bring together the various unique DOE assets: experimental and user facilities, the supercomputers, data archives and, importantly, the AI models," said Shantenu Jha, head of PPPL's Computational Sciences Department. While Genesis provides that broad infrastructure, STELLAR-AI contributes fusion-specific computer codes, data and scientific models back into the national system. The project also aligns with the DOE's Fusion Science and Technology Roadmap, which calls for building an AI-Fusion Digital Convergence platform to accelerate commercialization of a fusion power plant, achieve U.S. energy dominance, and provide the abundant power needed to drive the next generation of AI and computing.

Researchers plan to use STELLAR-AI for projects that span simulation, design and real-time experiment support. One effort will create a digital twin of NSTX-U: a computer model that mirrors the physical machine so closely that scientists can test ideas virtually before running actual experiments. Another project, called StellFoundry, uses AI to speed the design of stellarators, a type of fusion device with a twisted, pretzel-like shape that some scientists believe could offer advantages over other designs. Stellarator design requires sifting through enormous amounts of data to find the best configurations, a process that traditionally takes months or years and will greatly benefit from the STELLAR-AI platform.

A Network of Public and Private Partners

The strength of STELLAR-AI lies in PPPL’s partnerships with DOE National Laboratories, AI and HPC companies, academic institutions, as well as fusion and engineering companies. The team includes world-leading capabilities from national laboratories, including PPPL and UKAEA as well as top universities such as Massachusetts Institute of Technology and University of Wisconsin-Madison. Princeton University, which manages the laboratory for the U.S. DOE's Office of Science, is also a key partner. Princeton will support operations, research software engineering, and user training for the STELLAR-AI infrastructure. Crucial technical support comes from tech giants like NVIDIA which is providing expertise to improve the performance of several critical fusion codes, and Microsoft, which will federate Azure’s leading cloud capabilities. We also have direct collaboration with the fusion industry, including Commonwealth Fusion Systems, General Atomics, Type One Energy and Realta Fusion. This unique combination of partners will deliver proven AI models and key tools for the U.S. fusion industry.

STELLAR-AI is just one of several initiatives that position PPPL as a hub for public-private collaboration in fusion energy. The laboratory's seven decades of plasma research, combined with experimental facilities like NSTX-U and computational expertise, have made it a destination for companies and research institutions seeking to accelerate fusion development.

PPPL is mastering the art of using plasma — the fourth state of matter — to solve some of the world’s toughest science and technology challenges. Nestled on Princeton University’s Forrestal Campus in Plainsboro, New Jersey, our research ignites innovation in a range of applications including fusion energy, nanoscale fabrication, quantum materials and devices, and sustainability science. The University manages the Laboratory for the U.S. Department of Energy’s Office of Science, which is the nation’s single largest supporter of basic research in the physical sciences. Feel the heat at https://energy.gov/science and https://www.pppl.gov.

END

ELSE PRESS RELEASES FROM THIS DATE:

Breakthrough in development of reliable satellite-based positioning for dense urban areas

2026-01-23

Global navigation satellite systems (GNSS) are vital for positioning autonomous vehicles, buses, drones, and outdoor robots. Yet its accuracy often degrades in dense urban areas due to signal blockage and reflections. Now, researchers have developed a GNSS-only method that delivers stable, accurate positioning without relying on fragile carrier-phase ambiguity resolution. Tested across six challenging urban scenarios, the approach consistently outperformed existing methods, enabling safer and more reliable autonomous navigation. Accurately determining position is critical for the safety and reliability of autonomous vehicles and outdoor ...

DNA-templated method opens new frontiers in synthesizing amorphous silver nanostructures

2026-01-23

A research team from the Institute of Physics, Chinese Academy of Sciences has developed a novel DNA origami-based technique to synthesize stable, monolithic amorphous silver nanostructures under ambient conditions. By using DNA scaffold with fivefold rotational symmetry, the method introduces geometric frustration that effectively suppresses crystallization in metallic silver, a traditionally challenging feat due to the natural tendency of silver to form crystalline structures. Detailed characterization and molecular ...

Stress-testing AI vision systems: Rethinking how adversarial images are generated

2026-01-23

Deep neural networks (DNNs) have become a cornerstone of modern AI technology, driving a thriving field of research in image-related tasks. These systems have found applications in medical diagnosis, automated data processing, computer vision, and various forms of industrial automation, to name a few. As our reliance on AI models grows, so does our need to test them thoroughly using adversarial examples. Simply put, adversarial examples are images that have been strategically modified with noise to trick an AI into making a mistake. Understanding adversarial image generation techniques is essential for identifying vulnerabilities in DNNs and for developing more secure, reliable systems. Despite ...

Why a crowded office can be the loneliest place on earth

2026-01-23

A comprehensive new review published in the Journal of Management synthesizes decades of research to understand the epidemic of workplace loneliness. By analyzing 233 empirical studies, researchers from Portland State University have identified how workplace conditions contribute to isolation and offer evidence-based paths to reconnection. The research emphasizes that loneliness is distinct from social isolation. While isolation is about being alone, loneliness is the subjective feeling that one’s social relationships are deficient—meaning ...

Choosing the right biochar can lock toxic cadmium in soil, study finds

2026-01-23

Cadmium contamination in agricultural soils is a growing global concern, threatening food safety, crop productivity, and human health. New research shows that not all biochars work the same way and that choosing the right type of biochar can make the difference between trapping toxic metals in soil or unintentionally making them more mobile. In a study published online on January 15, 2026, researchers report that biochar produced at high temperatures can work together with soil microbes to effectively immobilize cadmium, one of the most hazardous heavy metals found in farmland ...

Desperate race to resurrect newly-named zombie tree

2026-01-23

A recently identified tree species in Australia has been given the name ‘zombie’ by scientists who say ambitious assistance is needed to reverse its ‘living dead’ status. University of Queensland botanist Professor Rod Fensham said it was a race against time to save Rhodamnia zombi from the fungal disease myrtle rust. “This species did not have a name when it was first assessed in 2020, and since then 10 per cent of the trees have died and none of those remaining are producing flowers or fruit because of myrtle rust,” ...

New study links combination of hormone therapy and tirzepatide to greater weight loss after menopause

2026-01-23

JACKSONVILLE, Fla. — A new study led by Mayo Clinic found that postmenopausal women receiving menopausal hormone therapy lost 35% more weight while taking tirzepatide, a Food and Drug Administration-approved drug for the treatment of overweight and obesity. The findings, published in The Lancet Obstetrics, Gynaecology, & Women's Health, could expand treatment possibilities for millions of women struggling with obesity and obesity-related diseases after menopause. Menopause can accelerate age-related weight gain and increase the likelihood of developing overweight and obesity, which are major risk factors for cardiovascular ...

How molecules move in extreme water environments depends on their shape

2026-01-23

Water behaves in remarkable ways when heated and pressurized beyond its critical point. Under these extreme conditions, known as supercritical water, it no longer acts like an ordinary liquid. Instead, it takes on properties similar to organic solvents, dissolving hydrocarbons efficiently and transporting molecules rapidly. These unique features make supercritical water a promising green medium for energy conversion technologies such as biomass gasification, plastic recycling, and in situ fuel extraction. Yet many of these reactions occur inside extremely ...

Early-life exposure to a common pollutant harms fish development across generations

2026-01-23

A widely distributed environmental pollutant can leave lasting biological scars that persist long after direct exposure has ended, according to a new study that tracked its effects across multiple generations of fish. Researchers found that brief exposure to benzo[a]pyrene, a toxic compound produced by fossil fuel combustion and industrial activity, disrupted normal development and skeletal health not only in directly exposed fish but also in their unexposed descendants. The study reveals that these long-term effects are driven by persistent changes in metabolism, shedding new light on how ...

How is your corn growing? Aerial surveillance provides answers

2026-01-22

With already thin profit margins and increasingly uncertain farm labor and other input costs, precision agriculture technology could improve New England’s small and medium-sized farms’ efficiency, productivity, and resilience. Unfortunately, factors such as up-front costs and validation of the technology’s accuracy in the region remain a barrier to adoption. A research team at UNH led by Benjamin Fraser, visiting assistant professor and director of the Basic and Applied Spatial Analysis ...

LAST 30 PRESS RELEASES:

Why wetland restoration needs citizens on the ground

Sharktober: Study links October shark bite spike to tiger shark reproduction