arXiv subjects

Alessandro Pau

Publications and source records attributed to Alessandro Pau.

10 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↗

arXiv2025

Technical Aspects of Plasma Operational Simulation (POPSIM): A Framework for Data-Driven Simulation and Control

This paper reports on technical aspects of Plasma Operational Simulation (POPSIM), a research framework for data-driven simulation and control built in the machine learning framework JAX. The objective of the project is to address the extremely challenging simulation and modeling requirements of tokamak operations and control by combining simple principles-based models with data-driven models, spanning everything from power laws to new neural network architectures. This paper reports on key software and operations problems that the framework addresses, with examples from ongoing modeling activities for illustration.

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

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 \`a 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

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↗

arXiv2024

Correlation of the L-mode density limit with edge collisionality

The "density limit" is one of the fundamental bounds on tokamak operating space, and is commonly estimated via the empirical Greenwald scaling. This limit has garnered renewed interest in recent years as it has become clear that ITER and many tokamak pilot plant concepts must operate near or above the Greenwald limit to achieve their objectives. Evidence has also grown that the Greenwald scaling - in its remarkable simplicity - may not capture the full complexity of the density limit. In this study, we assemble a multi-machine database to quantify the effectiveness of the Greenwald limit as a predictor of the L-mode density limit and compare it with data-driven approaches. We find that a boundary in the plasma edge involving dimensionless collisionality and pressure, $\nu_{*\rm, edge}^{\rm limit} = 3.5 \beta_{T,{\rm edge}}^{-0.40}$, achieves significantly higher accuracy (false positive rate of 2.3% at a true positive rate of 95%) of predicting density limit disruptions than the Greenwald limit (false positive rate of 13.4% at a true positive rate of 95%) across a multi-machine dataset including metal- and carbon-wall tokamaks (AUG, C-Mod, DIII-D, and TCV). This two-parameter boundary succeeds at predicting L-mode density limits by robustly identifying the radiative state preceding the terminal MHD instability. This boundary can be applied for density limit avoidance in current devices and in ITER, where it can be measured and responded to in real time.

physics.plasm-ph↗

arXiv2022

A machine-learning-based tool for last closed-flux surface reconstruction on tokamaks

Nuclear fusion represents one of the best alternatives for a sustainable source of clean energy. Tokamaks allow to confine fusion plasma with magnetic fields and one of the main challenges in the control of the magnetic configuration is the prediction/reconstruction of the Last Closed-Flux Surface (LCFS). The evolution in time of the LCFS is determined by the interaction of the actuator coils and the internal tokamak plasma. This task requires real-time capable tools able to deal with high-dimensional data as well as with high resolution in time, where the interaction between a wide range of input actuator coils with internal plasma state responses add additional layer of complexity. In this work, we present the application of a novel state of the art machine learning model to the LCFS reconstruction in the Experimental Advanced Superconducting Tokamak (EAST) that learns automatically from the experimental data of EAST. This architecture allows not only offline simulation and testing of a particular control strategy, but can also be embedded in the real-time control system for online magnetic equilibrium reconstruction and prediction. In the real-time modeling test, our approach achieves very high accuracies, with over 99% average similarity in LCFS reconstruction of the entire discharge process.

physics.plasm-ph↗

arXiv2021

EAST discharge prediction without integrating simulation results

In this work, a purely data-driven discharge prediction model was developed and tested without integrating any data or results from simulations. The model was developed based on the experimental data from the Experimental Advanced Superconducting Tokamak (EAST) campaign 2010-2020 discharges and can predict the actual plasma current $I_{p}$, normalized beta $\beta_{n}$, toroidal beta $\beta_{t}$, beta poloidal $\beta_{p}$, electron density $n_{e}$, store energy $W_{mhd}$, loop voltage $V_{loop}$, elongation at plasma boundary $\kappa$, internal inductance $l_{i}$, q at magnetic axis $q_{0}$, and q at 95% flux surface $q_{95}$. The average similarities of all the selected key diagnostic signals between prediction results and the experimental data are greater than 90%, except for the $V_{loop}$ and $q_{0}$. Before a tokamak experiment, the values of actuator signals are set in the discharge proposal stage, with the model allowing to check the consistency of expected diagnostic signals. The model can give the estimated values of the diagnostic signals to check the reasonableness of the tokamak experimental proposal.

physics.plasm-ph↗

arXiv2020

Plasma Confinement Mode Classification Using a Sequence-to-Sequence Neural Network With Attention

In a typical fusion experiment, the plasma can have several possible confinement modes. At the TCV tokamak, aside from the Low (L) and High (H) confinement modes, an additional mode, dithering (D), is frequently observed. Developing methods that automatically detect these modes is considered to be important for future tokamak operation. Previous work with deep learning methods, particularly convolutional recurrent neural networks (Conv-RNNs), indicates that they are a suitable approach. Nevertheless, those models are sensitive to noise in the temporal alignment of labels, and that model in particular is limited to making individual decisions taking into account only its own hidden state and its input at each time step. In this work, we propose an architecture for a sequence-to-sequence neural network model with attention which solves both of those issues. Using a carefully calibrated dataset, we compare the performance of a Conv-RNN with that of our proposed sequence-to-sequence model, and show two results: one, that the Conv-RNN can be improved upon with new data; two, that the sequence-to-sequence model can improve the results even further, achieving excellent scores on both train and test data.

physics.plasm-ph↗