The real reason Google DeepMind is working with a fusion energy startup

Energy startup Commonwealth Fusion Systems (CFS) said Thursday that it is working with Google’s DeepMind division to use AI to fine-tune — even improve — the operation of its upcoming spark reactor.

The company’s plan would simulate the plasma that would burn inside CFS’s reactor using special DeepMind software known as Torax. They plan to add Torax to the AI ​​model to help the CFS figure out how to achieve fusion power.

Fusion power promises to deliver massive amounts of electricity with zero emissions from a nearly limitless fuel source: water. AI-related companies are bullish Fusion Startup As a power source in energy-hungry data centers. Google also seems to be eyeing them as a potential customer.

This isn’t Google’s first foray into nuclear fusion. The tech company worked with another fusion startup, TAE Technologies, to use AI to study how plasma behaves inside TAE’s fusion machine.

There’s a reason Google is back in trouble: AI may be uniquely suited to make fusion power possible.

One of the biggest challenges facing fusion startups is keeping the plasma inside the reactor hot enough for long enough. Unlike nuclear fission reactions, which are self-sustaining, fusion reactions are difficult to sustain outside of stars like the Sun. Without this kind of mass and gravity, the plasma is constantly at risk of spreading and tearing itself apart.

In CFS’s reactors, strong magnets help the plasma instead of gravity, but they are not perfect. Reactor operators need to develop control software that can enable the device to respond to constantly changing plasma conditions.

The problem is, there are almost too many knots to go around, certainly more than a human. This is the kind of problem that AI excels at. Experts cite AI One of the key technologies That has enabled significant advancements in the industry over the past few years.

CFS is currently building Spark, its demonstration reactor, in a suburb outside Boston. The instrument is About two-thirds completeAnd when completed no later than 2026, the startup predicts it will be the first fusion device capable of producing more energy than is needed to run the plant itself.

Google says Torax can be used with reinforcement learning or evolutionary search models to find “the most efficient and robust path to generate net energy.” The two companies are also exploring whether AI can be used to control reactor operations.

In August, Google participated in CFS $863 million Series B2 Round along with Nvidia. Earlier this year, Google also said it would Buy 200 MW of electricity From CFS’s first commercial power plant, Arc, which is planned to be built Outside of Richmond, Virginia. The technology company is also an investor in CFS competitor TAE Technologies.