While ITER has been using Microsoft tools for years, the two organizations have now begun a formal collaboration that may yield benefits never thought possible. Cooperation ramped up a notch last week when the two organizations signed a Memorandum of Understanding to work together to apply artificial intelligence (AI) and other digital technologies to help engineers construct the ITER machine and accelerate research in nuclear physics.Inspired by what he learned from case studies, ITER’s Deputy Director-General and Chief Scientist Alain Bécoulet began developing a closer relationship with Microsoft in 2023. He had already been pushing to increase the use of digital technology, including facilitating document retrieval from ITER’s document management system with Microsoft Copilot (a new tool was recently released). According to Bécoulet, helping researchers manage the knowledge gained throughout the project is as precious as the end product. “We want to stabilize this knowledge into codes and standards, so that next time somebody addresses the construction of a nuclear reactor or reactor-like machine, they just build up on what has been done and not reinvent the wheel,” he says.Both organizations recognized the value in increased collaboration: scientists and engineers are deeply skilled in their own field but much less so in AI, while companies like Microsoft who are at the forefront of AI can, through collaboration, help scientists like those working in nuclear fusion to harness its power. The gains reaped from working together could exceed the sum of what each could produce alone.A collaboration with a range of expected benefitsITER is particularly interested in working with Microsoft Research, which was created in 1991 and now employs hundreds of people performing fundamental research in a range of areas, including social sciences.When generative AI came on the scene three years ago, Microsoft Research created a whole new department, called AI for Science. “We understood that with new generative AI models, AI would be transformative,” says Philippe Limantour, Chief Technology and CyberSecurity Officer at Microsoft France. “So we decided to build teams with AI specialists, data scientists, and researchers in different fields to work together, applying AI to solve the most complex problems like developing new drugs, or discovering new materials.”For ITER, the payoff could come in the form of facilitating precision construction or strengthening plasma modelling. For example, AI can serve as the underpinning for digital twins that will help assembly crews choose the best fix virtually, or it can help review the reams of data produced during vacuum vessel assembly and welding and save time in verifying the quality and precision of the work. Digital twins will also help physicists make predictions about plasma behaviour in different scenarios. They can also be used to generate synthetic data to train AI models—and test scenarios to help run experiments. “The aim is to strengthen the integrated modelling of ITER plasmas, both in terms of experimental design and real-time control, as well as the analysis and processing of gigantic quantities of data,” Bécoulet explains, adding that the cooperation could also lead to a major leap forward in ITER’s ability to optimize its operational regime based on the most fundamental calculations through simulations that call on the highest computing capacities currently available as well as solid data mining capabilities.While AI is one of the main areas of collaboration, it is not the only one. Microsoft offers high-performance computing as a service, and its engineers are experts in adapting software to the rapidly evolving architectures of the world’s fastest machines. Many of the codes used for physics simulations at ITER were written in the 1970s and do not take advantage of the massively parallel processing and GPU operations available today. Microsoft experts can help adapt that software to make it run much faster on modern hardware—and keep doing so as the machines get better.Given the evolutive nature of digital technology, and the enthusiasm on both sides, Bécoulet expects big benefits over the years.

An upending tool is designed to handle some of the largest ITER components such as vacuum vessel sectors and toroidal field coils. As a consequence, its steel frame is quite cumbersome and can only be delivered in two halves that are later bolted together. On Friday 28 March, the first half of a second upending tool, required to speed up the assembly of the sector modules, was delivered to ITER and will be followed by the second half this week. Manufactured under tight time constraints by the Korean company Yujin Mechatronics, this second upending tool, although very similar to the first one, is more versatile.As the handling of vacuum vessel sectors and toroidal field coils requires different sets of attachments, the original upending tool, in use at ITER for the past five years, needed to be reconfigured for every operation. With two units soon available, each one will be “specialized” in one type of component. Lengthy reconfiguration operations will not be needed anymore, and time in the range of weeks will be saved in the assembly process schedule.

In December 2023, ITER celebrated the completion of the main construction work on the Tritium Building—a "formidable adventure" initiated 14 years earlier under Europe's responsibility. Once fully equipped, the facility will handle the rare, expensive and slightly radioactive element tritium which, along with the other hydrogen isotope deuterium, composes the gaseous mix forming the fusion plasma. On Wednesday 26 March, a Procurement Agreement was signed with the Korean Domestic Agency to deliver what can be considered the very heart of the tritium plant: the storage and delivery system (SDS) that will occupy an entire level of the Tritium Building. For the Korean Domestic Agency and its director Kijung Jung, the signature was highly symbolic: the Procurement Agreement represents the ninth and last “package” to be signed by Korea in the context of the original division of tasks among the Members. For the ITER Organization, it marked a decisive step in the completion of a facility that needs to be ready for commissioning by 2030. “The storage and delivery system is at the crossroads of the tritium plant,” explains Ian Bonnett, who leads the Tritium Plant Project. “It will act as a fuel distribution centre not only for tritium but for non-radioactive gases such as deuterium, nitrogen, neon or argon required by different systems within the installation. When ITER is ready for deuterium-tritium operation, it will receive the tritium from suppliers and ensure that it is properly stored and available when required.”  ITER will be by and far the largest tritium consumer ever, using up the better part of the tritium inventory worldwide, estimated at a few dozen kilograms. Tritium will be transported and stored in IAEA-certified containers equipped with “hydride beds” that passively lock hydrogen in a solid matrix at room temperature. Tritium, an isotope of hydrogen, will be stored in “hydride beds” that passively lock hydrogen in a solid matrix at room temperature. The storage and delivery system will accommodate 52 such beds, with the possibility of extension to meet ITER needs. As a side benefit helium-3, the highly valuable decay product of tritium, will be harvested from the hydride beds and collected for use in ITER or in other scientific experiments.ITER will be by and far the largest tritium consumer ever. It is expected that the project’s scientific program will use the better part of the tritium inventory worldwide, estimated at a few dozen kilograms¹. Once industrialized, fusion will rely on tritium breeding, whose tools and techniques will be developed and tested in ITER’s Test Blanket Module program.¹The only source of readily available tritium is a type of fission reactor called CANDU where tritium is created by neutron capture in the heavy water coolant. CANDU reactors were initially developed by Canada and are presently operated in Canada, China, Korea, Romania and Argentina.

In the framework of a deepened collaboration between the Southwestern Institute of Physics (SWIP), China and the ITER Organization, the HL-3 tokamak has become a satellite device of ITER. A campaign dedicated to deuterium-tritium plasma experiments in support of ITER's physics research and operation is planned.  In December 2023, the ITER Organization signed an agreement for academic, scientific and technical cooperation with the Southwestern Institute of Physics (SWIP) in Chengdu, China. SWIP has built more than 20 experimental devices for controlled nuclear fusion research, including medium-sized tokamaks HL-1 (1984) and HL-1M (1994), divertor-based tokamak HL-2A (2002), and the advanced-divertor tokamak HL-3 (formerly called HL-2M) that achieved first plasma in 2020 and high-confinement operation (H-mode) in August 2023. Collaboration is now intensifying in areas such as integrated operation scenarios simulation, disruption physics, and plasma control. The spring 2025 experimental campaign has attracted international research teams from the United States, France, Japan, South Korea, Portugal, and Thailand for joint investigations that will target key challenges for high-fusion-power-production deuterium-tritium (DT) plasmas in ITER such as high-beta plasma sustainment, disruption mitigation techniques, isotope mixing effects, and advanced heat exhaust solutions.A prototype tri-band spectrometer system for ITER's charge-exchange recombination spectroscopy diagnostics has completed its initial technical validation on HL-3, demonstrating the capabilities for simultaneous ion temperature measurements and impurity monitoring which will improve ITER measurement capabilities. The HL-3 team has also successfully commissioned two self-developed plasma heating systems—a high-power electron cyclotron heating system and a 7 MW neutral beam injection system—during recent facility upgrades.  HL-3 is a research device located at the Center of Fusion Science/Southwestern Institute of Physics (SWIP) in Chengdu, China. Its construction was a decade-long project that cumulated with the completion of first plasma in December 2020. Photo courtesy of SWIP. Recent experiments have achieved stable 1.6 MA plasmas in diverted configuration and developed a novel tripod divertor magnetic configuration demonstrating enhanced heat flux handling. Operation scenarios with electron or ion internal transport barriers have achieved HL-3 record electron temperatures exceeding 160 million degrees and ion temperatures above 117 million degrees in a reproducible way. The operational strategies and the control algorithms required to access and sustain these high-temperature plasmas have been successfully developed. This progress in the development of high-performance scenarios is essential for successful deuterium-tritium operation in HL-3 and for burning plasma research.Future HL-3 research priorities include increasing heating power capacity to pursue scenarios with higher fusion triple product and operation with a higher temperature wall to decrease recycling levels and, eventually, in-vessel tritium retention. Machine-learning applications are also being integrated for real-time plasma shaping control, instability suppression, and disruption prediction—critical developments supporting the facility's transition to high-performance plasma operations to be followed by deuterium-tritium plasmas.

Six months and ten days: that’s what it took to assemble the massive elements of sector module #7, one of the nine sectors that will form the torus-shaped vacuum vessel that will house the fusion reactions. Lessons learned from the assembly of sector module #6¹ plus a streamlined work organization, improved methods and procedures, and the dependability and performance of upgraded tools have divided by three the time required to finalize this strategic “building block” of the ITER machine. A “sector module” is built from three important components—a vacuum vessel sector (440 tonnes), its thermal shield, and two vertical toroidal field coils (330 tonnes each).On Friday 28 March, the teams that contributed to this remarkable achievement gathered at the foot of the tool suspending the completed module to celebrate. Soberly, ITER Machine Assembly Program Manager Jens Reich declared that the milestone had been achieved “in the assigned time frame” … and even a bit earlier than anticipated. In a more emotional address, Sergio Orlandi, the head of ITER Construction Project recalled the difficulties encountered, expressed his pride in the teams and confessed feeling “like in a dream”—a feeling that was shared by Tai Jiang, the president of CNPE-Europe and head of the CNPE team on the ITER site. (The CNPE consortium is the principal contractor for tokamak assembly on site.) From left to right: Tai Jiang, president of CNPE-Europe and head of the CNPE team on the ITER site; Sergio Orlandi, head of ITER Construction Project; Jens Reich, Machine Assembly Program Manager; Nicolas Sapet, ITER Sector Modules Assembly Project Leader; and Nicolas Vendeuvre, the contract responsible officer. Sergio pledged that today’s achievement will be tomorrow routine, with one module being installed in the tokamak pit “every two to three months.” Nicolas Sapet, leader of the Sector Modules Assembly Project, was certain that the teams would do “even better for the next one.” As for Kijung Jung, the director of ITER Korea which had procured the vacuum vessel sector at the centre of the module as well as the thermal shield, he stressed the importance of continuing to work in the same spirit of commitment and dedication—all the way to the end of machine assembly, through commissioning and into machine operation. Â¹The assembly of sector module #6 lasted 18 months. The module was installed in the tokamak pit in May 2022. Affected by dimensional non-conformities that required significant repair, the module was extracted from the pit in July 2023. Repairs are being finalized and sector module #6 will be second installed inside the pit.

Ever wonder how scientists are trying to recreate the power of the sun on Earth? In our latest ITER podcast episode, we dive into the fascinating world of tokamaks—donut-shaped magnetic cages that could be the key to unlimited clean energy. Join us in Season 3 of the ITER podcast as we unravel the mysteries of fusion with expert insights from ITER scientists, exploring how decades of research are bringing us closer to harnessing the same energy that powers stars. From tiny experimental devices to massive reactors, discover the incredible journey of fusion science and why tokamaks might just be humanity's most promising path to sustainable power.Episode 2 of Behind the Science of Fusion is available now.Look up "Tokamaks" on the podcast page of the ITER website or open it directly here. You can also find the ITER podcast at Podbean, Spotify, Amazon Music, Apple Podcasts, and Deezer.

The prestigious Women in Nuclear (WiN) Global Excellence Award is a chance to celebrate an individual who has communicated consistently, effectively and positively the key messages for the nuclear industry and nuclear applications.The successful candidate will be offered free registration at the WiN Global 32nd Annual Conference in London (14-18 July 2025) and the opportunity to speak at the Annual Conference.For application criteria see the WiN website. Apply by 13 April 2025.