arXiv subjects

Olivier Sauter

Publications and source records attributed to Olivier Sauter.

8 recordsLinked to original sources

arXiv2026

An Inverse Grad-Shafranov Neural Network Approach to Tokamak Magnetic Control

A new approach to tokamak magnetic control enabling high-precision plasma shaping and novel real-time adaptability is experimentally demonstrated on the Tokamak a Configuration Variable (TCV). The method is motivated by the insight that, under appropriate assumptions, a real-time inverse Grad-Shafranov solver approximates an optimal control policy for plasma boundary regulation. Building on this, a control architecture is developed in which classical controllers enforce operational constraints while a fast surrogate model provides a real-time inverse mapping from the desired plasma boundary to Poloidal Field Coil currents. Experimental results on TCV demonstrate improved plasma shaping with respect to the standard discharge preparation procedure --- albeit without explicit real-time shape feedback --- while enabling flexible response to asynchronous events. It is shown that a single network provides satisfactory performance across a range of plasma magnetic configurations. Real-time adaptivity is demonstrated in simulation, and partially in experiment, through adaptive strike point motion and early termination in response to a real-time trigger. These results suggest a viable path toward magnetic control architectures that reduce reliance on dense diagnostic coverage while maintaining high-accuracy plasma shaping, with potential relevance for future fusion power plant operation.

physics.plasm-ph↗

arXiv2026

On the timescales of controlled termination of tokamak plasmas

The RAPTOR code is used to model how the time required for controlled termination of Ohmic plasmas scales from present tokamaks like TCV and JET, to reactor-grade tokamaks like ITER and DEMO. We show that ramping the plasma current $I_p$ down to 20% of the flat-top value over a time $Δt_{ramp-down}=τ_{LR}=L_i/R$, with internal inductance $L_i$ and resistance $R$ evaluated at flat-top conditions, results in an approximately self-similar peaking of the current density for these four tokamaks, indicating the adequacy of $τ_{LR}$ as a relevant timescale for cross-machine comparison, yielding $τ_{LR} =$ 0.033s (TCV), 2.87s (JET), 63.2s (ITER) and 166.9s (DEMO). Note that $τ_{LR}$ is easy to evaluate, both in systems codes and on a real-time control system. For the simulated ramp-downs with $Δt_{ramp-down}=τ_{LR}$, the end-of-ramp-down normalized internal inductance $\ell_{i3}$ is limited below 2. An $I_p$ ramp-down faster than $τ_{LR}=L_i/R$ requires a reversal of the boundary loop voltage and leads to the formation of a broad plasma layer carrying current in the direction opposite to the total plasma current, concomitant with $\ell_{i3}>2$, a central region with low magnetic shear and strongly peaked pressure profiles. Significant reduction of plasma volume and elongation, as foreseen for ITER and DEMO, is shown to counteract the reversal of current density and the $\ell_{i3}$ increase, while easing vertical stability control, potentially enabling faster $I_p$ ramp-down scenarios. Experimental and theoretical studies should be performed to test the feasibility of such fast termination scenarios, notably with respect to vertical position control, shape control and (resistive) beta limits. A simple analytical model is proposed and applied to estimate $τ_{LR}$ based on 0D engineering parameters for different tokamaks and for different operating points.

physics.plasm-ph↗

arXiv2025

FGE: A Fast Free-Boundary Grad-Shafranov Evolutive Solver

Accurate and rapid simulation of the free boundary tokamak plasma equilibrium evolution is essential for modern plasma control, stability analysis, and scenario development. This paper presents the Free-Boundary Grad-Shafranov Evolutive (FGE) code, a highly flexible and control-oriented solver designed to address the challenges posed by advanced plasma configurations across a range of devices. FGE evolved from the FBT and LIUQE codes and is part of the MEQ suite, sharing many of the low-level optimized functions. It self-consistently solves the free-boundary Grad-Shafranov equation coupled with circuit equations for external conductors and models for plasma profile evolution. The code implements a fully non-linear, Newton-based framework with multiple, highly optimized solver options, state representations, and residual formulations that enable rapid computation across different simulation setups. A key capability is the self-consistent integration of various 0D and 1D current diffusion equations (CDEs) to model the resistive evolution of the plasma current profile as well as the ability to model plasmas with multiple magnetic axes (Doublets). Furthermore, FGE allows to linearize the plasma dynamics around a given equilibrium to generate a state-space model suitable for controller design and analysis. Numerical studies are presented demonstrating the code's speed of convergence and validating its performance against experimental data. Furthermore, benchmarks against the RAPTOR and KINX codes for profile evolution and vertical growth rate estimates are presented highlighting FGE's capabilities for both prediction and analysis.

physics.plasm-ph↗

arXiv2025

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

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 à 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.

physics.plasm-ph↗

arXiv2025

Plasma State Monitoring and Disruption Characterization using Multimodal VAEs

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.

physics.plasm-ph↗

arXiv2025

Robust Confinement State Classification with Uncertainty Quantification through Ensembled Data-Driven Methods

Maximizing fusion performance in tokamaks relies on high energy confinement, often achieved through distinct operating regimes. The automated labeling of these confinement states is crucial to enable large-scale analyses or for real-time control applications. While this task becomes difficult to automate near state transitions or in marginal scenarios, much success has been achieved with data-driven models. However, these methods generally provide predictions as point estimates, and cannot adequately deal with missing and/or broken input signals. To enable wide-range applicability, we develop methods for confinement state classification with uncertainty quantification and model robustness. We focus on off-line analysis for TCV discharges, distinguishing L-mode, H-mode, and an in-between dithering phase (D). We propose ensembling data-driven methods on two axes: model formulations and feature sets. The former considers a dynamic formulation based on a recurrent Fourier Neural Operator-architecture and a static formulation based on gradient-boosted decision trees. These models are trained using multiple feature groupings categorized by diagnostic system or physical quantity. A dataset of 302 TCV discharges is fully labeled, and will be publicly released. We evaluate our method quantitatively using Cohen's kappa coefficient for predictive performance and the Expected Calibration Error for the uncertainty calibration. Furthermore, we discuss performance using a variety of common and alternative scenarios, the performance of individual components, out-of-distribution performance, cases of broken or missing signals, and evaluate conditionally-averaged behavior around different state transitions. Overall, the proposed method can distinguish L, D and H-mode with high performance, can cope with missing or broken signals, and provides meaningful uncertainty estimates.

physics.plasm-ph↗

arXiv2025

Towards Transparent and Accurate Plasma State Monitoring at JET

Controlling and monitoring plasma within a tokamak device is complex and challenging. Plasma off-normal events, such as disruptions, are hindering steady-state operation. For large devices, they can even endanger the machine's integrity and it represents in general one of the most serious concerns for the exploitation of the tokamak concept for future power plants. Effective plasma state monitoring carries the potential to enable an understanding of such phenomena and their evolution which is crucial for the successful operation of tokamaks. This paper presents the application of a transparent and data-driven methodology to monitor the plasma state in a tokamak. Compared to previous studies in the field, supervised and unsupervised learning techniques are combined. The dataset consisted of 520 expert-validated discharges from JET. The goal was to provide an interpretable plasma state representation for the JET operational space by leveraging multi-task learning for the first time in the context of plasma state monitoring. When evaluated as disruption predictors, a sequence-based approach showed significant improvements compared to the state-based models. The best resulting network achieved a promising cross-validated success rate when combined with a physical indicator and accounting for nearby instabilities. Qualitative evaluations of the learned latent space uncovered operational and disruptive regions as well as patterns related to learned dynamics and global feature importance. The applied methodology provides novel possibilities for the definition of triggers to switch between different control scenarios, data analysis, and learning as well as exploring latent dynamics for plasma state monitoring. It also showed promising quantitative and qualitative results with warning times suitable for avoidance purposes and distributions that are consistent with known physical mechanisms.

physics.plasm-ph↗

arXiv2012

Understanding the core density profile in TCV H-mode plasmas

Results from a database analysis of H-mode electron density profiles on the Tokamak à Configuration Variable (TCV) in stationary conditions show that the logarithmic electron density gradient increases with collisionality. By contrast, usual observations of H-modes showed that the electron density profiles tend to flatten with increasing collisionality. In this work it is reinforced that the role of collisionality alone, depending on the parameter regime, can be rather weak and in these, dominantly electron heated TCV cases, the electron density gradient is tailored by the underlying turbulence regime, which is mostly determined by the ratio of the electron to ion temperature and that of their gradients. Additionally, mostly in ohmic plasmas, the Ware-pinch can significantly contribute to the density peaking. Qualitative agreement between the predicted density peaking by quasi-linear gyrokinetic simulations and the experimental results is found. Quantitative comparison would necessitate ion temperature measurements, which are lacking in the considered experimental dataset. However, the simulation results show that it is the combination of several effects that influences the density peaking in TCV H-mode plasmas.

physics.plasm-ph↗