https://github.com/plasmacontrol/tearingavoidance
The Python scripts for training the ML models for tearing prediction & avoidance
https://github.com/plasmacontrol/tearingavoidance
Last synced: about 1 year ago
JSON representation
The Python scripts for training the ML models for tearing prediction & avoidance
- Host: GitHub
- URL: https://github.com/plasmacontrol/tearingavoidance
- Owner: PlasmaControl
- Created: 2024-03-01T15:19:20.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-03-14T15:56:05.000Z (about 2 years ago)
- Last Synced: 2025-01-16T10:32:34.704Z (about 1 year ago)
- Language: PureBasic
- Size: 1.28 MB
- Stars: 3
- Watchers: 7
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Tearing Avoidance Control
- Tearing mode instability is the leading cause of plasma disruption in a tokamak.
- This repository provides the Python scripts for training the ML models:\
(1) Tearing mode prediction model using deep learning\
(2) Tearing mode avoidance model using deep reinforcement learning
# Note
- Some scripts need experimental data from DIII-D, which are not available from this repository. To access DIII-D data, you should become a DIII-D user, per the instructions at https://d3dfusion.org/become-a-user/ .
# References
- J. Seo et al., "Avoiding fusion plasma tearing instability with deep reinforcement learning." Nature [626 (2024): 746.](https://www.nature.com/articles/s41586-024-07024-9)