From Nuclear Physics to AI: Why Fusion's Digital Twin Matters

I did my PhD in Nuclear Reactor Physics. Now I work with AI automation.

So when I stumbled on a video about the Siemens keynote at CES 2026, I had to pay attention.

SPARC tokamak — a compact fusion reactor under construction in Devens, Massachusetts Image: T. Henderson, CFS/MIT-PSFC, 2020

Commonwealth Fusion Systems is building SPARC — a compact fusion reactor designed to achieve what has been the holy grail of nuclear fusion for decades: producing more energy than it consumes. Generations of physicists have worked toward this moment.

But what really got me: they're partnering with Siemens and Nvidia to build an AI-powered digital twin of the reactor.

Not just a 3D model. A virtual copy that runs alongside the real machine, ingests live data, tests hypotheses, and compresses years of experimentation into weeks.

Siemens NX for the engineering data. Nvidia Omniverse for the simulation. AI tying it all together.

What fascinates me is how broad AI's reach is becoming. One day it's helping crack nuclear fusion. The next, it's streamlining everyday business operations. The problems look nothing alike, but the underlying ability — to simulate, learn, and iterate faster than we ever could — is the same.

AI is already reshaping how we work. That's not going to slow down. I'm glad I get to help people and organisations make that shift in a way that actually works for them.