At Princeton University’s Andlinger Center, a cross-disciplinary team of engineers, physicists, and data scientists, collaborating with the Princeton Plasma Physics Laboratory (PPPL), have used AI to handle plasma instabilities in nuclear fusion. 

Fusion energy, which mirrors the means of powering the Sun, uses immense pressure and warmth to fuse atoms, releasing vast quantities of energy. 

Replicating this on Earth involves confining ultra-hot plasma with powerful magnetic fields inside tokamak reactors – complex devices often dubbed ‘stars in jars.’ However, in the confines of a fusion reactor, plasma is notoriously volatile, potentially destabilizing and breaching the magnetic barriers designed to contain it. 

In experiments conducted on the DIII-D National Fusion Facility in San Diego, a team of researchers showcased an AI model that, relying solely on historical experimental data, could predict the onset of ‘tearing mode instabilities’ – a selected form of plasma disruption – as much as 300 milliseconds prematurely. 

The researchers employed a deep neural network trained on past DIII-D tokamak data to predict future instabilities based on real-time plasma characteristics.

This model then informed a reinforcement learning (RL) algorithm, which iteratively refined its control strategies through simulated experiments, learning to keep up high power levels while avoiding instabilities.

The team’s findings were published in a study in Nature.

Azarakhsh Jalalvand, a co-author, likened the method to flight training, where a pilot learns in a simulator before taking control of an actual aircraft. 

“You wouldn’t teach someone by handing them a set of keys and telling them to try their best,” Jalalvand remarked, stressing the importance of a gradual, informed learning process for the AI.

a. The graph shows how the actuators behave over time, with AI control (in blue) and without it (in black). The red lines mark the thresholds beyond which plasma stability may be compromised. b. This part illustrates the anticipated likelihood of tearing instabilities as influenced by the actuators’ adjustments. c. Here, we see the anticipated effect of the actuators’ control on maintaining the plasma pressure inside normalized levels. d. This section depicts how the plasma is anticipated to evolve inside a set of parameters, guided by the strategic interventions of AI control. Source: Nature (Open Access)

Upon validating the AI controller’s simulation performance, the team proceeded to real-world tests on the DIII-D tokamak, where they observed the AI successfully manipulating reactor parameters to cut back instabilities. 

A tokamak is a tool utilized in nuclear fusion research designed to restrict a plasma using magnetic fields. It’s some of the researched forms of fusion reactor, with the final word goal of manufacturing controlled thermonuclear fusion power. The tokamak is characterised by its toroidal (doughnut-shaped) configuration, which is taken into account effective for holding the high-temperature plasma needed for fusion reactions.

The AI controller’s temporary yet critical predictive powers enable the system to regulate operational parameters in real-time, stopping the instabilities and maintaining the plasma’s equilibrium inside the reactor’s magnetic field.

Professor Egemen Kolemen, who spearheaded the research, explained the team’s approach, stating, “By learning from past experiments, quite than incorporating information from physics-based models, the AI could develop a final control policy that supported a stable, high-powered plasma regime in real time, at an actual reactor.” 

Jaemin Seo, from the Department of Mechanical and Aerospace Engineering, discussed how accurate and fast prediction is the linchpin of this study, noting, “Previous studies have generally focused on either suppressing or mitigating the results of those tearing instabilities after they occur within the plasma. But our approach allows us to predict and avoid those instabilities before they ever appear.”

“Tearing mode instabilities are one in all the main causes of plasma disruption, and they’re going to change into much more outstanding as we attempt to run fusion reactions on the high powers required to supply enough energy,” Seo explained.

Looking ahead, the researchers plan to collect more evidence of the AI controller’s performance and extend its capabilities to other tokamaks and plasma instabilities.

 “We have strong evidence that the controller works quite well at DIII-D, but we’d like more data to point out that it may well work in quite a few different situations,” Seo remarked, outlining the trail forward.

Bridging AI’s energy divide with nuclear fusion

The Princeton study demonstrates how AI can support fusion, but fusion could also support AI. 

In some ways, AI has a symbiotic yet fragile relationship with energy. Evidence strongly suggests that generative AI’s exponential growth is resulting in staggering energy consumption that already rivals the consumption of small nations. 

The essence of the dilemma lies in AI’s foundational infrastructure – data centers. These vast digital installations are notorious for his or her colossal energy and water demands. 

The International Energy Agency (IEA) recently highlighted the growing footprint of knowledge centers, which already eat greater than 1.3% of the world’s electricity.

Projections by the Boston Consulting Group and the European Union paint a grim picture, with data center energy demands potentially doubling and even tripling in the approaching years, exacerbating energy challenges. 

In response, Big Tech is strengthening its energy infrastructure by the day while considering nuclear energy, including fusion. 

Microsoft recently opened a job posting for a “Principal Program Manager Nuclear Technology” and goals to develop a world strategy centered around Small Modular Reactors (SMRs) and micro-reactors, demonstrating cognizance of the looming energy issues confronting AI.

Recently, Helion Energy, supported by Sam Altman of OpenAI, announced its intention to launch the world’s first fusion power plant inside five years. 

If Helion works, it not only is a possible way out of the climate crisis but a path towards a much higher quality of life.

Have loved being involved for the last 7 years and excited to be investing more. David and Chris are amazing.

— Sam Altman (@sama) November 5, 2021

As the Princeton study explains, fusion reactions are immensely complex to contain and unpredictable.

However, one other central challenge is achieving a “net energy gain,” meaning the fusion process produces more energy than it consumes.

Helion faces considerable technical challenges. Jessica Lovering from the Good Energy Collective highlights two major hurdles: “producing more energy than the method uses – and converting that energy right into a consistent, inexpensive type of electricity that would flow onto the grid.” 

To date, only Lawrence Livermore’s National Ignition Facility has achieved “scientific net energy gain” with fusion, but not “engineering gain,” which considers the entire energy input for the method. 

In other words, securing net energy gains from the entire fusion process, including engineering efforts, is critical to creating fusion a viable energy technology quite than an expensive experiment. 

where @Helion_Energy will soon start to put in polaris:

— Sam Altman (@sama) February 2, 2024

Helion is forging ahead, developing its seventh prototype, Polaris, which is anticipated to reveal electricity production from fusion reactions in 2024. 

Based in Everett, Washington, Helion has already secured Microsoft as its first customer through an influence purchase agreement. They’re aiming for his or her first plan to supply no less than 50 megawatts (mW) capability. 

microsoft becomes helion’s first customer, in the primary industrial deal for fusion power:

— Sam Altman (@sama) May 10, 2023

This is minuscule when it comes to raw capability, with the common wind turbine producing around 3mW – so it’d be such as a small wind farm. However, once operational, Helion will create clean energy like other types of renewable energy. It’s safer than fission plants and can eventually change into cheaper to supply en-masse. 

As the digital and physical realms change into intertwined, the energy demands of AI and cloud computing will proceed to escalate.

Pursuing nuclear fusion offers a glimpse right into a future where clean, abundant energy could power inexorable AI development. 

And seeing that Microsoft, Altman, and other tech firms are already lining themselves up as investors and buyers, it is going to definitely be tech firms that get their hands on fusion power first.

The post Nuclear fusion and AI: an evolving, symbiotic relationship appeared first on DailyAI.

This article was originally published at