# Plasma State Monitoring and Disruption Characterization using Multimodal VAEs

arXiv: https://arxiv.org/abs/2504.17710 · HTML: https://mlsanity.com/paper/2504.17710/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 96 references that are in the map.
- First posted on arXiv 24 Apr 2025.

## Builds on (most cited first, 22 of 22)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [NVAE: A Deep Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2007.03898/) (2020)
- [Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders](https://mlsanity.com/paper/1611.02648/) (2016)
- [Hyperspherical Variational Auto-Encoders](https://mlsanity.com/paper/1804.00891/) (2018)
- [Training behavior of deep neural network in frequency domain](https://mlsanity.com/paper/1807.01251/) (2018)
- [The Road Less Scheduled](https://mlsanity.com/paper/2405.15682/) (2024)
- [Dynamical Variational Autoencoders: A Comprehensive Review](https://mlsanity.com/paper/2008.12595/) (2020)
- [Multivariate Confidence Calibration for Object Detection](https://mlsanity.com/paper/2004.13546/) (2020)
- [A Recurrent Variational Autoencoder for Speech Enhancement](https://mlsanity.com/paper/1910.10942/) (2019)
- [Plasma Surrogate Modelling using Fourier Neural Operators](https://mlsanity.com/paper/2311.05967/) (2023)
- [Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions](https://mlsanity.com/paper/1812.09502/) (2018)
- [Hybrid deep learning architecture for general disruption prediction across tokamaks](https://mlsanity.com/paper/2007.01401/) (2020)
- [Fast Dynamic 1D Simulation of Divertor Plasmas with Neural PDE Surrogates](https://mlsanity.com/paper/2305.18944/) (2023)
- [Calibrated Physics-Informed Uncertainty Quantification](https://mlsanity.com/paper/2502.04406/) (2025)
- [Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders](https://mlsanity.com/paper/2306.05023/) (2023)
- [Towards aerodynamic surrogate modeling based on β-variational autoencoders](https://mlsanity.com/paper/2408.04969/) (2024)
- [Integrated real-time supervisory management for off-normal-event handling and feedback control of tokamak plasmas](https://mlsanity.com/paper/2010.16145/) (2020)
- [Robust Confinement State Classification with Uncertainty Quantification through Ensembled Data-Driven Methods](https://mlsanity.com/paper/2502.17397/) (2025)
- [Towards Transparent and Accurate Plasma State Monitoring at JET](https://mlsanity.com/paper/2502.12182/) (2025)

## Built on by (most cited first, 2 of 2)

- [Learning Physical Operators using Neural Operators](https://mlsanity.com/paper/2602.23113/) (2026)
- [Hierarchical Multi-to-Single-Modal Knowledge Distillation for Disruption Prediction in EAST](https://mlsanity.com/paper/2607.04241/) (2026)

## Abstract (arXiv)

When a plasma disrupts in a tokamak, significant heat and electromagnetic loads are deposited onto the surrounding device components. These forces scale with plasma current and magnetic field strength, making disruptions one of the key challenges for future devices. Unfortunately, disruptions are not fully understood, with many different underlying causes that are difficult to anticipate. Data-driven models have shown success in predicting them, but they only provide limited interpretability. On the other hand, large-scale statistical analyses have been a great asset to understanding disruptive patterns. In this paper, we leverage data-driven methods to find an interpretable representation of the plasma state for disruption characterization. Specifically, we use a latent variable model to represent diagnostic measurements as a low-dimensional, latent representation. We build upon the Variational Autoencoder (VAE) framework, and extend it for (1) continuous projections of plasma trajectories; (2) a multimodal structure to separate operating regimes; and (3) separation with respect to disruptive regimes. Subsequently, we can identify continuous indicators for the disruption rate and the disruptivity based on statistical properties of measurement data. The proposed method is demonstrated using a dataset of approximately 1600 TCV discharges, selecting for flat-top disruptions or regular terminations. We evaluate the method with respect to (1) the identified disruption risk and its correlation with other plasma properties; (2) the ability to distinguish different types of disruptions; and (3) downstream analyses. For the latter, we conduct a demonstrative study on identifying parameters connected to disruptions using counterfactual-like analysis. Overall, the method can adequately identify distinct operating regimes characterized by varying proximity to disruptions in an interpretable manner.