Ander Gray

UncertaintyQuantification.jl

Jasper Behrensdorf, Ander Gray, Andrea Perin, Jan Grashorn et autres

UncertaintyQuantification v0.15.1 Diff since v0.15.0 This patch release restores the isimprecise method dispatching on a vector of UQInput. Closed issues: Limit maximum number of steps in Subset Simulation (#224) isimprecise not working on vector of UQInput (#330)

UncertaintyQuantification.jl

Jasper Behrensdorf, Ander Gray, Andrea Perin, Jan Grashorn et autres

UncertaintyQuantification v0.15.0 Diff since v0.14.0 This release contains a few notable new features: Full integration with Copulas.jl for the JointDistribution Transport maps Redesigned interface for linear basis function models like the response surface Interval predictor models There are no breaking changes. An …

Learning Physical Operators using Neural Operators

Vignesh Gopakumar, Ander Gray, Dan Giles, Lorenzo Zanisi et autres

Neural operators have emerged as promising surrogate models for solving partial differential equations (PDEs), but struggle to generalise beyond training distributions and are often constrained to a fixed temporal discretisation. This work introduces a physics-informed training framework that addresses these limitations by …

Learning Physical Operators using Neural Operators

Vignesh Gopakumar, Ander Gray, Dan Giles, Lorenzo Zanisi et autres

Neural operators have emerged as promising surrogate models for solving partial differential equations (PDEs), but struggle to generalise beyond training distributions and are often constrained to a fixed temporal discretisation. This work introduces a physics-informed training framework that addresses these limitations by …

JuliaUQ/UncertaintyQuantification.jl: v0.14.0

Jasper Behrensdorf, Ander Gray, Andrea Perin, Jan Grashorn et autres

UncertaintyQuantification v0.14.0 Diff since v0.13.0 This version fixes a serious bug in TransitionalMarkovChainMonteCarlo and introduces optional binning to the kernel density estimation among other things. There are no breaking changes. Merged pull requests: Add optional binning for EmpiricalDistribution (#269) (@FriesischScott) Test on …

de, fr (code pays fourni par la source)

Uncertainty quantification of surrogate models using conformal prediction

Vignesh Gopakumar, Ander Gray, Joel Oskarsson, Lorenzo Zanisi et autres

Abstract 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 …

gb, fr, se (code pays fourni par la source)

Calibrated Physics-Informed Uncertainty Quantification

Vignesh Gopakumar, Ander Gray, Lorenzo Zanisi, Timothy Nunn et autres

Simulating complex physical systems is crucial for understanding and predicting phenomena across diverse fields, such as fluid dynamics and heat transfer, as well as plasma physics and structural mechanics. Traditional approaches rely on solving partial differential equations (PDEs) using numerical methods, which …

Guaranteed prediction sets for functional surrogate models

Ander Gray, Vignesh Gopakumar, Sylvain Rousseau, Sébastien Destercke

We propose a method for obtaining statistically guaranteed prediction sets for functional machine learning methods: surrogate models which map between function spaces, motivated by the need to build reliable PDE emulators. The method constructs nested prediction sets on a low-dimensional representation (an …

fr, gb (code pays fourni par la source)

UncertaintyQuantification.jl: Efficient Reliability Analysis Powered by Julia

Jasper Behrensdorf, Ander Gray, Matteo Broggi, M Beer

Uncertainty Quantification of Surrogate Models using Conformal Prediction

Vignesh Gopakumar, Ander Gray, Joel Oskarsson, Lorenzo Zanisi et autres

Data-driven surrogate models offer quick 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 …

Valid Error Bars for Neural Weather Models using Conformal Prediction

Vignesh Gopakumar, Joel Oskarrson, Ander Gray, Lorenzo Zanisi et autres

Neural weather models have shown immense potential as inexpensive and accurate alternatives to physics-based models. However, most models trained to perform weather forecasting do not quantify the uncertainty associated with their forecasts. This limits the trust in the model and the usefulness …

Gaussian process surrogate models for the properties of micro-tearing modes in spherical tokamaks

W. A. Hornsby, Ander Gray, J. Buchanan, Daniel Kenndy et autres

Spherical tokamaks (STs) have many desirable features that make them a suitable choice for fusion power plants. To understand their confinement properties, accurate calculation of turbulent micro-instabilities is necessary for tokamak design. Presented is a novel surrogate model for Micro-tearing modes (MTMs), …