https://github.com/vijaideen/VICTOR-GSC2026
VICTOR (Variational Inference for Confined Tokamak Output Reconstruction) — A Physics-Informed Neural Network that reconstructs plasma emissivity on the WEST Tokamak in ~0.5ms, trained entirely without ground-truth labels. Enabling real-time fusion reactor diagnostics and disruption prevention.
https://github.com/vijaideen/VICTOR-GSC2026
deep-learning-scientific-computing flax google-cloud-run gsc2026 jax nuclear-fusion open-innovation physics-informed-neural-network plasma-diagnostics sdg7 soft-xray-tomography streamlit tokamak unbiased-ai vertex-ai
Last synced: 5 days ago
JSON representation
VICTOR (Variational Inference for Confined Tokamak Output Reconstruction) — A Physics-Informed Neural Network that reconstructs plasma emissivity on the WEST Tokamak in ~0.5ms, trained entirely without ground-truth labels. Enabling real-time fusion reactor diagnostics and disruption prevention.
- Host: GitHub
- URL: https://github.com/vijaideen/VICTOR-GSC2026
- Owner: vijaideen
- License: apache-2.0
- Created: 2026-04-11T14:26:59.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2026-04-18T21:02:37.000Z (about 2 months ago)
- Last Synced: 2026-04-18T22:32:48.172Z (about 2 months ago)
- Topics: deep-learning-scientific-computing, flax, google-cloud-run, gsc2026, jax, nuclear-fusion, open-innovation, physics-informed-neural-network, plasma-diagnostics, sdg7, soft-xray-tomography, streamlit, tokamak, unbiased-ai, vertex-ai
- Language: Jupyter Notebook
- Homepage: https://spectra-west-3105564668.us-central1.run.app/
- Size: 162 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
Awesome Lists containing this project
- awesome-ml-in-plasma-physics - VICTOR-GSC2026 - Physics-informed neural network notebook for WEST tokamak soft X-ray tomography reconstruction using JAX/Flax (Tools / Machine Learning Frameworks for Plasma Physics)