Vignesh Gopakumar
  • Home
  • Research
  • Talks
  • Blog

Research


2024

Uncertainty Quantification of Surrogate Models using Conformal Prediction

Vignesh Gopakumar, Ander Gray, Joel Oskarsson, Lorenzo Zanisi, Stanislas Pamela,
Daniel Giles, Matt J. Kusner, Marc Peter Deisenroth
arXiv preprint arXiv:2408.09881, 2024

TLDR: Guaranteed and valid error bars across spatio-temporal domains using conformal prediction.

Paper Code

Valid Error Bars for Neural Weather Models using Conformal Prediction

Vignesh Gopakumar, Ander Gray, Joel Oskarsson, Lorenzo Zanisi, Stanislas Pamela, 
Daniel Giles, Matt J. Kusner, Marc Peter Deisenroth
arXiv preprint arXiv:2406.14483, 2024

TLDR: Marginal conformal prediction as a method of guaranteed error bars across neural weather models.  

Paper Code

Plasma Surrogate Modelling using Fourier Neural Operators

Vignesh Gopakumar, Stanislas Pamela, Lorenzo Zanisi, Zongyi Li, Ander Gray, 
Daniel Brennand, Nitesh Bhatia, Gregory Stathopoulos, Matt Kusner, 
Marc Peter Deisenroth, Anima Anandkumar, JOREK Team, MAST Team
Nuclear Fusion, Volume 64, Number 5, 2024

TLDR: Multi-variable FNO designed to model the plasma evolution within a Tokamak across both simulations and experiment on the MAST Tokamak.

Paper Code


2023

Fourier-RNNs for Modelling Noisy Physics data

Vignesh Gopakumar, Lorenzo Zanisi, Stanislas Pamela
arXiv preprint arXiv:2302.06534, 2023

TLDR: Recurrent Fourier neural operators with hidden state representations for non-markovian physcial modelling.

Paper

Loss Landscape Engineering via Data Regulation on PINNs

Vignesh Gopakumar, Stanislas Pamela, Debasmita Samaddar
Machine Learning with Applications, Volume 12, 2023

TLDR: Impact Data-Regulation has on smoothening the loss landscape of physics-informed neural networks for better convergence.

Paper Code


2022

Image Mapping the Temporal Evolution of Edge Characteristics in Tokamaks using Neural Networks

Vignesh Gopakumar, Debasmita Samaddar
Machine Learning: Science and Technology, Volume 1, Number 1, 2020

TLDR: Branched fully convolutional network designed to emulate the plasma at the scrape-off layer with coupled plasma and neutral behaviour.

Paper



You can find the latest list of publications in my google scholar page.

© Copyright 2025 Vignesh Gopakumar