# Learning Plasma Dynamics and Robust Rampdown Trajectories with Predict-First Experiments at TCV

arXiv: https://arxiv.org/abs/2502.12327 · HTML: https://mlsanity.com/paper/2502.12327/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 77 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 11 of 11)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Neural Operator: Graph Kernel Network for Partial Differential Equations](https://mlsanity.com/paper/2003.03485/) (2020)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Universal Differential Equations for Scientific Machine Learning](https://mlsanity.com/paper/2001.04385/) (2020)
- [On Neural Differential Equations](https://mlsanity.com/paper/2202.02435/) (2022)
- [Hybrid deep learning architecture for general disruption prediction across tokamaks](https://mlsanity.com/paper/2007.01401/) (2020)
- [Full Shot Predictions for the DIII-D Tokamak via Deep Recurrent Networks](https://mlsanity.com/paper/2404.12416/) (2024)
- [Active Disruption Avoidance and Trajectory Design for Tokamak Ramp-downs with Neural Differential Equations and Reinforcement Learning](https://mlsanity.com/paper/2402.09387/) (2024)
- [Integrated real-time supervisory management for off-normal-event handling and feedback control of tokamak plasmas](https://mlsanity.com/paper/2010.16145/) (2020)

## Built on by (most cited first, 4 of 4)

- [TokaMark: A Comprehensive Benchmark for MAST Tokamak Plasma Models](https://mlsanity.com/paper/2602.10132/) (2026)
- [Application of parametric Shallow Recurrent Decoder Network to magnetohydrodynamic flows in liquid metal blankets of fusion reactors](https://mlsanity.com/paper/2604.02139/) (2026)
- [Offline Reinforcement Learning for Rotation Profile Control in Tokamaks](https://mlsanity.com/paper/2605.05857/) (2026)
- [IGNITE Tokamak World Model Architecture](https://mlsanity.com/paper/2610.02515/) (2026)

## Abstract (arXiv)

The rampdown phase of a tokamak pulse is difficult to simulate and often exacerbates multiple plasma instabilities. To reduce the risk of disrupting operations, we leverage advances in Scientific Machine Learning (SciML) to combine physics with data-driven models, developing a neural state-space model (NSSM) that predicts plasma dynamics during Tokamak `a Configuration Variable (TCV) rampdowns. The NSSM efficiently learns dynamics from a modest dataset of 311 pulses with only five pulses in a reactor-relevant high-performance regime. The NSSM is parallelized across uncertainties, and reinforcement learning (RL) is applied to design trajectories that avoid instability limits. High-performance experiments at TCV show statistically significant improvements in relevant metrics. A predict-first experiment, increasing plasma current by 20% from baseline, demonstrates the NSSM's ability to make small extrapolations. The developed approach paves the way for designing tokamak controls with robustness to considerable uncertainty and demonstrates the relevance of SciML for fusion experiments.