Vignesh Gopakumar

Vignesh Gopakumar

Auto-generated profile, based on publicly available information

Vignesh Gopakumar

Centre for Artificial Intelligence, Department of Computer Science, University College London, London WC1V 6LJ, United Kingdom

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 April 2024 in Nuclear Fusion
Verified
Journal Article
Open access
PDF file
VGVignesh Gopakumar
Vignesh Gopakumar
SPStanislas Pamela
Stanislas Pamela
LZLorenzo Zanisi
Lorenzo Zanisi
ZLZongyi Li
Zongyi Li
AGAnder Gray
Ander Gray
AAAnima Anandkumar
Anima Anandkumar
Predicting plasma evolution within a Tokamak reactor is crucial to realizing the goal of sustainable fusion. Capabilities in forecasting the spatio-temporal evolution of plasma rapidly and accurately allow us to quickly iterate over design and control strategies on current Tokamak devices and future reactors. Modelling plasma evolution using numerical solvers is often expensive, consuming many hours on supercomputers, and hence, we need alternative inexpensive surrogate models. We demonstrate accurate predictions of plasma evolution both in simulation and experimental domains using deep learning-based surrogate modelling tools, viz., Fourier neural operators (FNO). We show that FNO has a speedup of six orders of magnitude over traditional solvers in predicting the plasma dynamics simulated from magnetohydrodynamic models, while maintaining a high accuracy (Mean Squared Error in the normalised domain ≈ 10 − 5 ). Our modified version of the FNO is capable of solving multi-variable Partial Differential Equations, and can capture the dependence among the different variables in a single model. FNOs can also predict plasma evolution on real-world experimental data observed by the cameras positioned within the MAST Tokamak, i.e. cameras looking across the central solenoid and the divertor in the Tokamak. We show that FNOs are able to accurately forecast the evolution of plasma and have the potential to be deployed for real-time monitoring. We also illustrate their capability in forecasting the plasma shape, the locations of interactions of the plasma with the central solenoid and the divertor for the full (available) duration of the plasma shot within MAST. The FNO offers a viable alternative for surrogate modelling as it is quick to train and infer, and requires fewer data points, while being able to do zero-shot super-resolution and getting high-fidelity solutions.

13 February 2024 in Nuclear Fusion
Verified
Journal Article
Open access
LZL. Zanisi
L. Zanisi
AHA. Ho
A. Ho
JBJ. Barr
J. Barr
TMT. Madula
T. Madula
JCJ. Citrin
J. Citrin
VGV. Gopakumar
V. Gopakumar
Model-based plasma scenario development lies at the heart of the design and operation of future fusion powerplants. Including turbulent transport in integrated models is essential for delivering a successful roadmap towards operation of ITER and the design of DEMO-class devices. Given the highly iterative nature of integrated models, fast machine-learning-based surrogates of turbulent transport are fundamental to fulfil the pressing need for faster simulations opening up pulse design, optimization, and flight simulator applications. A significant bottleneck is the generation of suitably large training datasets covering a large volume in parameter space, which can be prohibitively expensive to obtain for higher fidelity codes. In this work, we propose ADEPT (Active Deep Ensembles for Plasma Turbulence), a physics-informed, two-stage Active Learning strategy to ease this challenge. Active Learning queries a given model by means of an acquisition function that identifies regions where additional data would improve the surrogate model. We provide a benchmark study using available data from the literature for the QuaLiKiz quasilinear transport model. We demonstrate quantitatively that the physics-informed nature of the proposed workflow reduces the need to perform simulations in stable regions of the parameter space, resulting in significantly improved data efficiency compared to non-physics informed approaches which consider a regression problem over the whole domain. We show an up to a factor of 20 reduction in training dataset size needed to achieve the same performance as random sampling. We then validate the surrogates on multichannel integrated modelling of ITG-dominated JET scenarios and demonstrate that they recover the performance of QuaLiKiz to better than 10%. This matches the performance obtained in previous work, but with two orders of magnitude fewer training data points.

31 March 2023 in Machine Learning with Applications
Verified
Journal Article
Open access
VGVignesh Gopakumar
Vignesh Gopakumar
SPStanislas Pamela
Stanislas Pamela
DSDebasmita Samaddar
Debasmita Samaddar

4 February 2020 in Machine Learning: Science and Technology
Verified
Journal Article
Open access
PDF file
VGVignesh Gopakumar
Vignesh Gopakumar
DSD Samaddar
D Samaddar
We propose a method for data-driven modelling of the temporal evolution of the plasma and neutral characteristics at the edge of a tokamak using neural networks. Our method proposes a novel fully convolutional network to serve as function approximators in modelling complex nonlinear phenomenon observed in the multi-physics representations of high energy physics. More specifically, we target the evolution of the temperatures, densities and parallel velocities of the electrons, ions and neutral particles at the edge. The central challenge in this context is in modelling together the different physics principles encapsulated in the evolution of plasma and the neutrals. We demonstrate that the inherent differences in nonlinear behaviour can be addressed by forking the network to process the plasma and neutral information individually before integrating as a holistic system. Our approach takes into account the spatial dependencies of the physics parameters across the grid while performing the temporal mappings, ensuring that the underlying physics is factored in and not lost to the black-box. Having used the conventional edge plasma-neutral solver code SOLPS to build the synthetic dataset, our method demonstrates a computational gain of over 5 orders of magnitude over it without a considerable compromise on accuracy.

17 December 2025 in Machine Learning: Science and Technology
Verified
Journal Article
Open access
VGVignesh Gopakumar
Vignesh Gopakumar
AGAnder Gray
Ander Gray
JOJoel Oskarsson
Joel Oskarsson
DGDaniel Giles
Daniel Giles
LZLorenzo Zanisi
Lorenzo Zanisi
MDMarc Deisenroth
Marc Deisenroth
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.

23 April 2024 in IEEE Transactions on Plasma Science
Verified
Journal Article
Open access
TBTheodore Brown
Theodore Brown
SMStephen Marsden
Stephen Marsden
VGVignesh Gopakumar
Vignesh Gopakumar
ATAlexander Terenin
Alexander Terenin
HGHong Ge
Hong Ge
FCFrancis Casson
Francis Casson
The safety factor profile is a key property in determining the stability of tokamak plasmas. To design the safety factor profile in the United Kingdom’s proposed Spherical Tokamak for Energy Production (STEP), we apply multi-objective Bayesian optimization (MOBO) to design electron-cyclotron heating profiles. Bayesian optimization (BO) is an iterative machine learning technique that uses an uncertainty-aware predictive model to choose the next designs to evaluate based on the data gathered during optimization. By taking a multi-objective approach, the optimizer generates sets of solutions that represent optimal tradeoffs between objectives, enabling decision makers to understand the compromises made in each design. The solutions from our method score higher than those generated in previous work by a genetic algorithm (GA); however, the key result is that our method returns a purposefully diverse range of optimal solutions, providing more information to tokamak designers without incurring additional computational cost.