DeepMind AI: Accelerating Fusion Science Through Learned Plasma Control

DeepMind has been working with the Swiss Plasma Center to control a nuclear fusion reaction 

DeepMind worked with scientists at the Swiss Federal Institute of Technology in Lausanne (EPFL), Switzerland, to create a neural network capable of controlling the magnetic fields within EPFL's Variable Configuration Tokamak (TCV) fusion reactor.

In a paper published in Nature, DeepMind describes how it can successfully control nuclear fusion plasma by building and running controllers on the Variable Configuration Tokamak (TCV) in Lausanne, Switzerland. Using a learning architecture that combines deep RL and a simulated environment, DeepMind produces controllers that can both keep the plasma steady and be used to accurately sculpt it into different shapes. This "plasma sculpting" shows the RL system has successfully controlled the superheated matter and – importantly – allows scientists to investigate how the plasma reacts under different conditions, improving the understanding of fusion reactors.

This work is another powerful example of how machine learning and expert communities can come together to tackle grand challenges and accelerate scientific discovery. The team of DeepMind is hard at work applying this approach to fields as diverse as quantum chemistry, pure mathematics, material design, weather forecasting, and more, to solve fundamental problems and ensure AI benefits humanity.

DeepMind's successful demonstration of tokamak control shows the power of AI to accelerate and assist fusion science, and it is expected to increase sophistication in the use of AI going forward. This capability of autonomously creating controllers could be used to design new kinds of tokamaks while simultaneously designing their controllers. Its work also points to a bright future for reinforcement learning in the control of complex machines. It's especially exciting to consider fields where AI could augment human expertise, serving as a tool to discover new and creative approaches for hard real-world problems. It is predicted by the company that reinforcement learning will be a transformative technology for industrial and scientific control applications in the years to come, with applications ranging from energy efficiency to personalized medicine.