AI controller predicts and avoids tearing instabilities in the DIII-D fusion reactor
Princeton and PPPL researchers (Nature, Feb 2024) trained an RL controller on past DIII-D data. It forecast tearing-mode instabilities up to 300 ms ahead and adjusted operating parameters in real time to avoid them during experiments while keeping high performance.
Key facts
- Nature 626 (22 Feb 2024)
- Forecasts tearing instabilities up to 300 ms in advance
- Demonstrated in live DIII-D shots
Science result
- Field
- physics / nuclear fusion / plasma stability
- Problem
- Avoiding disruptive tearing-mode instabilities in high-performance tokamak plasmas
- Result
- Real-time AI avoidance of tearing instabilities on a working tokamak.
- AI system
- deep RL controller with learned dynamics model
- Human role
- Human-designed; operated under human supervision
- Verification
- Peer-reviewed in Nature; demonstrated on hardware
- Status
- confirmed
What happened
The controller learned the precursors of tearing modes from archived experiments and steered the plasma away from them.
Why it matters
Instabilities that can damage reactors are a key obstacle to fusion power. Predictive AI control is a candidate solution for ITER-class devices.
Changelog
- 2026-09-29: created
Related events
- Deep reinforcement learning controls fusion plasma in the TCV tokamak ★★★★
- Google DeepMind partners with Commonwealth Fusion Systems to optimise and control the SPARC tokamak with AI ★★★
- PPPL's PACMAN framework lets multiple AI models control a tokamak in ~20 ms, preventing a tearing mode ★★
Sources (2)
- paperAvoiding fusion plasma tearing instability with deep reinforcement learning (Nature)
- pressPrinceton Engineering: Engineers use AI to wrangle fusion power
id: 2024-02-21-ai-avoids-tokamak-tearing-instabilities · updated 2026-09-29 · open in the interactive timeline