arXiv subjects

Andrea Loreti

Publications and source records attributed to Andrea Loreti.

5 recordsLinked to original sources

arXiv2026

TokaMind: A Multi-Modal Transformer Foundation Model for Tokamak Plasma Dynamics

We present TokaMind, to our knowledge the first open-source foundation model for tokamak plasma dynamics, based on a Multi-Modal Transformer (MMT) and pretrained on heterogeneous 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 lightweight fixed-basis Discrete Cosine Transform embedding (DCT3D) and provide a clean interface for alternative embeddings (e.g., Variational Autoencoders). We evaluate TokaMind on the recently introduced MAST benchmark TokaMark, which comprises 14 tasks with heterogeneous reconstruction and forecasting objectives. Our results show that fine-tuned TokaMind outperforms the strongest benchmark baseline on all but one task. Compared with training the same architecture from scratch under a matched epoch budget, warm-start adaptation is most beneficial on demanding downstream settings, including long-horizon forecasting and high-dimensional equilibrium objectives. These findings highlight the value of multi-modal pretraining for tokamak plasma dynamics and provide a practical, extensible foundation for future fusion modeling tasks. Training code and model weights are publicly available at github.com/UKAEA-IBM-STFC-Fusion-FMs/tokamind and huggingface.co/UKAEA-IBM-STFC, respectively.

physics.plasm-ph↗

arXiv2026

TokaMark: A Comprehensive Benchmark for MAST Tokamak Plasma Models

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, and highlight the promise of modern data-native 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 unify access to multi-modal fusion data and standardize evaluation protocols. 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, 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 dataset, benchmark, documentation, and tooling are open-sourced under https://github.com/UKAEA-IBM-STFC-Fusion-FMs/tokamark_baseline.

physics.plasm-ph↗

arXiv2025

Automated Construction of a Knowledge Graph of Nuclear Fusion Energy for Effective Elicitation and Retrieval of Information

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 natural language. Additionally, we develop a knowledge-graph retrieval-augmented generation system that uses multiple prompts with large language models to provide contextually relevant answers to natural-language queries, including complex multi-hop questions requiring reasoning across interconnected entities.

cs.CL↗

arXiv2024

Vertex Fitting In Low-Material Budget Pixel Detectors

This paper provides a detailed description of a vertex fitting algorithm designed for precision measurements in low-energy particle physics experiments. An accurate reconstruction of low-momentum trajectories is facilitated by reducing the material budget of the detector to a few per mill of the radiation length. This decreases the multiple scattering experienced by particles within the detector, thereby enhancing vertex fitting accuracy. However, in the case of light detection systems, the intrinsic spatial resolution of the sensors imposes further constraints on the final vertex resolution that require careful consideration. The algorithm developed in this study addresses both multiple scattering and spatial resolution aspects in the context of vertex fitting, specifically tailored for light pixel detectors. Furthermore, this works presents a detailed examination of the vertex reconstruction within the low-material budget pixel detector of the Mu3e experiment.

physics.ins-det↗

arXiv2012

Weak response of neutron matter at low momentum transfer

The Landau parameters obtained from the matrix elements of an effective interaction recently derived within the formalism of correlated basis functions have been used to carry out a study of the weak response of neutron matter in the region of low momentum transfer. The proposed approach allows for a consistent description of different interaction effects and can be extended to describe matter at non vanishing temperature. The results show that interactions lead to a sizable enhancement of the neutrino mean free path in cold neutron matter. The dependence of the mean free path on temperature and neutrino energy is also analyzed.

nucl-th↗