Stanislas Pamela

We present the FreeGSNKE pulse design tool (FPDT), an open-source, Python-based computational framework that enables in silico testing and predictive design of tokamak plasma scenarios and control strategies. The FPDT couples the FreeGSNKE evolutive equilibrium solver with a virtual plasma control system (PCS) containing modular and customisable controllers. Given a set of user-defined waveforms and control parameters, the virtual PCS uses feedback and feedforward control to modulate plasma current, position, and shape, while adhering to machine safety limits on poloidal field (PF) coil currents and voltages. The resulting framework allows simulation of the controlled dynamic evolution of plasma equilibria, along with the currents in both active PF coils and passive conducting structures, under the assumption of axisymmetry. The FPDT can be used to develop plasma scenarios, test control schemes, calibrate control parameters, and perform uncertainty quantification studies, thereby reducing iterative and expensive experimental testing on a physical tokamak. The FPDT is machine-agnostic and can be customised to implement different control algorithms tailored to the specific tokamak of interest. Here, we outline the overall framework and validate its performance on plasma discharges on the MAST Upgrade tokamak in the ‘flat-top’ phase. We demonstrate excellent quantitative agreement between the FPDT simulations, the desired control waveforms, and the experimental shot data. With this extension to the FreeGSNKE open-source suite of codes we aim to encourage more reproducible and collaborative research in plasma modeling and control.

Transient phenomena and their control are of high relevance in magnetic confinement fusion plasmas to guarantee a stable and safe plasma operation. Interpretative simulations can maximize the insights gained from experiments on present machines and predictive simulations can help in the preparation of design, mitigation techniques and operational scenarios for future devices. In this article, we provide an overview of recent advances and novel scientific results obtained with the 3D non-linear hybrid fluid-kinetic code JOREK, covering physics of plasma transients from the core to the scrape-off layer (SOL) both for tokamak and stellarator devices. Substantial progress was made in the physics understanding, model validation with experiments and experiment interpretation, thus, giving confidence for predictions to devices like DTT, ITER and DEMO. The topics addressed comprise a wide range: the edge physics of new operation scenarios and edge localized mode suppression; major disruptions with a focus on runaway electrons and vertical displacement events as well as disruption mitigation by shattered pellet injection; the physics mechanisms and operational limits of the flux pumping regime for sawtooth control; MHD limits of stellarators and work towards incorporating advanced edge/SOL/exhaust dynamics; continuing improvements of the code for more efficient hybrid simulations on conventional and accelerated high performance computing architectures.

We present TokaMind, an open-source foundation model framework for fusion plasma modeling, based on a Multi-Modal Transformer (MMT) and trained on heterogeneous tokamak diagnostics from the publicly available MAST dataset. TokaMind supports multiple data modalities (time-series, 2D profiles, and videos) with different sampling rates, robust missing-signal handling, and efficient task adaptation via selectively loading and freezing four model components. To represent multi-modal signals, we use a training-free Discrete Cosine Transform embedding (DCT3D) and provide a clean interface for alternative embeddings (e.g., Variational Autoencoders - VAEs). We evaluate TokaMind on the recently introduced MAST benchmark TokaMark, comparing training and embedding strategies. Our results show that fine-tuned TokaMind outperforms the benchmark baseline on all but one task, and that, for several tasks, lightweight fine-tuning yields better performance than training the same architecture from scratch under a matched epoch budget. These findings highlight the benefits of multi-modal pretraining for tokamak plasma dynamics and provide a practical, extensible foundation for future fusion modeling tasks. Training code and model weights will be made publicly available.

Reliable fault diagnosis of induction motors from current signals is critical for preventing failures in industrial systems. However, deep learning models often exhibit performance degradation when the torque load and other operating conditions change. Although a lot of research has been completed on supervised fault classification using current signals, the investigation of the behaviour of these datasets for unsupervised learning has not been done. This study quantifies and analyses the “shadowing effect” of operational variability, demonstrating that a baseline 1D-CNN achieving 100% accuracy under static 0 Nm loads drops to 53.19% accuracy when subjected to 4 Nm load in the KAIST dataset using a stator current. Similar trends were validated using the Paderborn University (PU) bearing dataset. Using 1D-CNN feature extraction followed by Principal Component Analysis (PCA), t-SNE, and hierarchical clustering, we show that standard linear mitigation strategies, such as removing high-variance principal components, are ineffective because fault and load features are deeply entangled. Hierarchical clustering analysis confirms that the feature space is organised by load dominance, with the primary tree split consistently occurring by torque load rather than fault type. Crucially, we identify that internal geometric metrics, such as “spread” and “diameter”, correlate with external purity metrics like the proposed “Dominance Score”. The findings establish a quantitative basis for developing unsupervised, load-invariant diagnostic models that utilise geometric stopping criteria to isolate fault clusters without using ground-truth labels.

Data-driven surrogate models offer fast, inexpensive approximations to complex numerical and experimental systems but typically lack uncertainty quantification, limiting their reliability in safety-critical applications. While Bayesian methods provide uncertainty estimates, they offer no statistical guarantees and struggle with high-dimensional spatio-temporal problems due to computational costs and dependence on prior specification. We present a conformal prediction (CP) framework that provides statistically guaranteed marginal coverage for surrogate models in a model-agnostic manner with near-zero computational cost. Our approach handles high-dimensional spatio-temporal outputs by performing cell-wise calibration while preserving the tensorial structure of predictions. Through extensive empirical evaluation across diverse applications—including partial differential equations, magnetohydrodynamics, weather forecasting, and fusion diagnostics—we demonstrate that CP achieves empirical coverage with valid error bars regardless of model architecture (MLP, U-Net, FNO, ViT, GNN), training regime, or output dimensionality (spanning 32 to over 20 million dimensions). We evaluate three nonconformity scores (conformalised quantile regression, absolute error residual, and standard deviation) for both deterministic and probabilistic models, showing that guaranteed coverage holds even for out-of-distribution predictions where models are deployed on physics regimes different from their training data. Calibration requires only seconds to minutes on standard hardware, with prediction set construction incurring negligible computational overhead. The framework enables rigorous validation of pre-trained surrogate models for downstream applications without retraining, providing actionable uncertainty quantification for decision-making in scientific domains. While CP provides marginal rather than conditional coverage and assumes exchangeability between calibration and test data—limitations we demonstrate empirically through sensitivity analyses—our method circumvents the curse of dimensionality inherent in traditional uncertainty quantification approaches, offering a practical tool for the trustworthy deployment of machine learning in the physical sciences.

Simulation-based plasma scenario development plays a crucial role in designing next-generation tokamaks and fusion power plants. However, the inclusion of high-fidelity simulations of Scrape-Off Layer (SOL) turbulence and transient MHD events such as Edge Localized Modes (ELMs) in highly iterative applications remains computationally prohibitive, limiting their use in design and control workflows. Understanding these phenomena is vital, as they govern heat flux on plasma-facing components, influencing reactor performance and material lifetime. This study explored Fourier Neural Operators (FNOs) as surrogate models to accelerate plasma simulations from the JOREK MHD and STORM turbulence codes. FNOs were trained on single-step rollouts and evaluated in terms of long-term predictive accuracy in an auto-regressive manner. To mitigate the computational burden of dataset generation, a transfer learning strategy was explored, leveraging low-fidelity simulations to improve performance on high-fidelity datasets. These results showed that FNOs effectively captured initial plasma evolution, including blob movement and density source localization for JOREK and STORM, respectively. However, long rollouts accumulated errors and exhibited sensitivity to certain physical phenomena, leading to non-monotonic error spikes. Transfer learning significantly reduced errors for small dataset sizes and short rollouts, achieving an order-of-magnitude reduction when transfering from low- to high-fidelity datasets. However, its effectiveness diminished with longer rollouts and larger dataset sizes, especially when applied to datasets with significantly different dynamics. Attempts to transfer models to previously unseen variables in simulations were unsuccessful, underscoring the limitations of transfer learning in this context. These findings demonstrate the promise of neural operators for accelerating fusion-relevant PDE simulations. However, they also highlight key challenges: improving long-term accuracy to mitigate error accumulation, capturing critical physical behaviors, and developing robust surrogates that effectively leverage multi-fidelity, multi-physics datasets.

The increasing complexity and volume of plasma fusion experimental data, coupled with the growing adoption of machine learning in fusion research, necessitate advanced and efficient data management solutions. We propose an open data service for fusion experiments operated by the UKAEA, designed to address the evolving needs of machine-learning-driven fusion research. Our system provides a framework to organize MAST, MAST upgrade (MAST-U), and Joint European Torus (JET) experimental data in accordance with findability, accessibility, interoperability, and reuse (FAIR) principles, using distributed object storage for scalability and a relational database for efficient metadata indexing. In addition, it offers simplified abstractions through an application programming interface (API), facilitating seamless data access and integration with data analysis and machine learning workflows. Performance evaluation of metrics such as data load time and throughput, across varying numbers of parallel workers, demonstrates the data pipeline’s optimization for efficient machine learning application development. Our solution significantly enhances support for data-driven research and machine learning applications in fusion by laying the groundwork for open, FAIR-compliant fusion data, which enables cross-machine analysis, prompts international collaboration, and potentially accelerates advancements in fusion energy research.

This paper discusses the NVIDIA Omniverse platform for visualizing and integrating digital twins of fusion power plants, focusing on enhancing the design, simulation, and operational workflows of complex fusion systems. As global fusion projects such as ITER, STEP, and CFETR move toward realizing practical fusion energy, sophisticated tools to model, simulate, and optimize such systems become increasingly critical. Digital twins are virtual replicas of physical systems that act as a “single source of truth” by integrating scientific analysis, engineering design, and real-time data integration. This paper outlines the workflow for creating and visualizing a digital twin of a tokamak, demonstrating the integration of computer-aided design models, simulation data, and material properties into Omniverse. It also provides a view of extending Omniverse with real-time data visualization, Python scripting, and generative AI in applications that make the digital twin even more functional and interactive, allowing seamless collaboration across teams and stakeholders. The interoperability challenges that limit the adoption of Omniverse in fusion research are also discussed. In conclusion, the paper outlines how Omniverse can create a comprehensive, immersive, and interactive environment that optimizes the design and operation of a fusion power plant. In the future, this approach may extend to developing more efficient and reliable fusion energy systems.

A key aspect in the modelling of magnetohydrodynamic (MHD) equilibria in tokamak devices is having access to fast, accurate, and stable numerical simulation methods. There is an increasing demand for reliable methods that can be used to develop traditional or machine learning-based shape control feedback systems, optimise scenario designs, and integrate with other plasma edge or transport modelling codes. To handle such applications, these codes need to be flexible and, more importantly, they need to have been validated against both analytically known and real-world tokamak equilibria to ensure they are consistent and credible. In this paper, we are interested in solving the static forward Grad–Shafranov (GS) problem for free–boundary MHD equilibria. Our focus is on the validation of the static forward solver in the Python-based equilibrium code FreeGSNKE by solving equilibria from magnetics-only EFIT ++ reconstructions of MAST-U shots. In addition, we also validate FreeGSNKE against equilibria simulated using the well-established MATLAB-based equilibrium code Fiesta. To do this, we develop a computational pipeline that allows one to load the same (a)symmetric MAST-U machine description into each solver, specify the required inputs (active/passive conductor currents, plasma profiles and coefficients, etc.) from EFIT++, and solve the GS equation for all available time slices across a shot. For a number of different MAST-U shots, we demonstrate that both FreeGSNKE and Fiesta can successfully reproduce various poloidal flux quantities and shape targets (e.g. midplane radii, magnetic axes, separatrices, X-points, and strikepoints) in agreement with EFIT++ calculations to a very high degree of accuracy. We also provide public access to the code/data required to load the MAST-U machine description in FreeGSNKE/Fiesta and reproduce the equilibria in the shots shown.