Adriano Agnello

Ji Won Park, Simon Birrer, Madison Ueland et al. · cambridge

We present a Bayesian graph neural network (BGNN) that can estimate the weak lensing convergence ($κ$) from photometric measurements of galaxies along a given line of sight. The method is of particular interest in strong gravitational time delay cosmography (TDC), where characterizing the "external convergence" ($κ_{\rm ext}$) from the lens environment and line of sight is necessary for precise inference of the Hubble constant ($H_0$). Starting from a large-scale simulation with a $κ$ resolution of $\sim$1$'$, we introduce fluctuations on galaxy-galaxy lensing scales of $\sim$1$''$ and extract random sightlines to train our BGNN. We then evaluate the model on test sets with varying degrees of overlap with the training distribution. For each test set of 1,000 sightlines, the BGNN infers the individual $κ$ posteriors, which we combine in a hierarchical Bayesian model to yield constraints on the hyperparameters governing the population. For a test field well sampled by the training set, the BGNN recovers the population mean of $κ$ precisely and without bias, resulting in a contribution to the $H_0$ error budget well under 1\%. In the tails of the training set with sparse samples, the BGNN, which can ingest all available information about each sightline, extracts more $κ$ signal compared to a simplified version of the traditional method based on matching galaxy number counts, which is limited by sample variance. Our hierarchical inference pipeline using BGNNs promises to improve the $κ_{\rm ext}$ characterization for precision TDC. The implementation of our pipeline is available as a public Python package, Node to Joy.

Cécile Rousseau, Samuel Jackson, Rodrigo H. Ordonez-Hurtado et al.

Development and operation of commercially viable fusion energy reactors such as tokamaks require accurate predictions of plasma dynamics from sparse, noisy, and incomplete sensors readings. The complexity of the underlying physics and the heterogeneity of experimental data pose formidable challenges for conventional numerical methods, while simultaneously highlight the promise of modern data-native AI approaches. A major obstacle in realizing this potential is, however, the lack of curated, openly available datasets and standardized benchmarks. Existing fusion datasets are scarce, fragmented across institutions, facility-specific, and inconsistently annotated, which limits reproducibility and prevents a fair and scalable comparison of AI approaches. In this paper, we introduce TokaMark, a structured benchmark to evaluate AI models on real experimental data collected from the Mega Ampere Spherical Tokamak (MAST). TokaMark provides a comprehensive suite of tools designed to (i) unify access to multi-modal heterogeneous fusion data, and (ii) harmonize formats, metadata, temporal alignment and evaluation protocols to enable consistent cross-model and cross-task comparisons. The benchmark includes a curated list of 14 tasks spanning a range of physical mechanisms, exploiting a variety of diagnostics and covering multiple operational use cases. A baseline model is provided to facilitate transparent comparison and validation within a unified framework. By establishing a unified benchmark for both the fusion and AI-for-science communities, TokaMark aims to accelerate progress in data-driven AI-based plasma modeling, contributing to the broader goal of achieving sustainable and stable fusion energy. The benchmark, documentation, and tooling will be fully open sourced upon acceptance to encourage community adoption and contribution.

Tobia Boschi, Andrea Loreti, Nicola C. Amorisco et al.

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.

Adriano Agnello, Helen Brooks, Cyd Cowley et al.

There is great potential for the application of AI tools in fusion research, and substantial worldwide benefit if fusion power is realised. However, using AI comes with its own challenges, many of which can be mitigated if responsible and robust methodologies are built into existing approaches. To do that requires close, long-term collaborations between fusion domain experts and AI developers and awareness of the fact that not all problems in fusion research are best tackled with AI tools. In April 2025, experts from academia, industry, UKAEA and STFC discussed how AI can be used to advance R&D in fusion energy at the first edition of The Economist FusionFest event. This Perspective is an expanded and updated summary of the round table discussion, providing more context and examples.

Alasdair Ross, George K. Holt, Kamran Pentland et al.

Reliable position and shape control in tokamak plasmas requires accurate real-time regulation of several strongly coupled shape parameters. The control vectors that disentangle these couplings, referred to as \textit{virtual circuits} (VCs), enable independent shape parameter control for a specific Grad--Shafranov (GS) equilibrium. Numerical calculation of VCs is not currently feasible in real time, therefore VCs are usually computed prior to each experiment, using a small number of reference GS equilibria sampled along the desired scenario trajectory, with each VC used to control the plasma within a preset time interval. While effective near the reference equilibrium, this approach can lead to degraded performance as the plasma departs from the reference equilibrium and/or from the desired trajectory, and it complicates the design of robust control strategies for rapidly evolving plasma configurations. In this paper, we construct neural-network-based emulators of plasma shape parameters from which VCs can be derived, to provide the MAST Upgrade (MAST-U) plasma control system with state-aware VCs in real-time. To do this, we develop an extensive library of over a million simulated GS equilibria, covering a substantial portion of the MAST-U operational space. These emulators provide differentiable functions whose gradients can be rapidly computed, enabling the derivation of accurate VCs for real-time shape control. We perform extensive verification of the emulated VCs by testing whether they disentangle the control problem. The neural-network-based approach delivers high accuracy and orthogonality across a diverse range of equilibria. This work establishes the physical validity of emulated VCs as a scalable and general alternative to schedules of precomputed VCs.

Pedro Cavestany, Alasdair Ross, Adriano Agnello et al.

Machine learning has recently been adopted to emulate sensitivity matrices for real-time magnetic control of tokamak plasmas. However, these approaches would benefit from a quantification of possible inaccuracies. We report on two aspects of real-time applicability of emulators. First, we quantify the agreement of target displacement from VCs computed via Jacobians of the shape emulators with those from finite differences Jacobians on exact Grad-Shafranov solutions. Good agreement ($\approx$5-10%) can be achieved on a selection of geometric targets using combinations of neural network emulators with $\approx10^5$ parameters. A sample of $\approx10^{5}-10^{6}$ synthetic equilibria is essential to train emulators that are not over-regularised or overfitting. Smaller models trained on the shape targets may be further fine-tuned to better fit the Jacobians. Second, we address the effect of vessel currents that are not directly measured in real-time and are typically subsumed into effective "shaping currents" when designing virtual circuits. We demonstrate that shaping currents can be inferred via simple linear regression on a trailing window of active coil current measurements with residuals of only a few Ampères, enabling a choice for the most appropriate shaping currents at any point in a shot. While these results are based on historic shot data and simulations tailored to MAST-U, they indicate that emulators with few-millisecond latency can be developed for robust real-time plasma shape control in existing and upcoming tokamaks.

Andrea Loreti, Kesi Chen, Ruby George et al.

In this document, we discuss a multi-step approach to automated construction of a knowledge graph, for structuring and representing domain-specific knowledge from large document corpora. We apply our method to build the first knowledge graph of nuclear fusion energy, a highly specialized field characterized by vast scope and heterogeneity. This is an ideal benchmark to test the key features of our pipeline, including automatic named entity recognition and entity resolution. We show how pre-trained large language models can be used to address these challenges and we evaluate their performance against Zipf's law, which characterizes human-generated natural language. Additionally, we develop a knowledge-graph retrieval-augmented generation system that combines large language models with a multi-prompt approach. This system provides contextually relevant answers to natural-language queries, including complex multi-hop questions that require reasoning across interconnected entities.

Marin Mlinarević, George K. Holt, Adriano Agnello

A surrogate model for particle-in-cell plasma simulations based on a graph neural network is presented. The graph is constructed in such a way as to enable the representation of electromagnetic fields on a fixed spatial grid. The model is applied to simulate beams of electrons in one dimension over a wide range of temperatures, drift momenta and densities, and is shown to reproduce two-stream instabilities - a common and fundamental plasma instability. Qualitatively, the characteristic phase-space mixing of counterpropagating electron beams is observed. Quantitatively, the model's performance is evaluated in terms of the accuracy of its predictions of number density distributions, the electric field, and their Fourier decompositions, particularly the growth rate of the fastest-growing unstable mode, as well as particle position, momentum distributions, energy conservation and run time. The model achieves high accuracy with a time step longer than conventional simulation by two orders of magnitude. This work demonstrates that complex plasma dynamics can be learned and shows promise for the development of fast differentiable simulators suitable for solving forward and inverse problems in plasma physics.