paper-with-me

홈 › Papers

Gradient-enhanced deep Gaussian processes for multifidelity modelling

2024-02-25 · Viv Bone, Chris van der Heide, Kieran Mackle, Ingo H. J. Jahn, Peter M. Dower, Chris Manzie

Multifidelity models integrate data from multiple sources to produce a single approximator for the underlying process. Dense low-fidelity samples are used to reduce interpolation error, while sparse high-fidelity samples are used to compensate for bias or noise in the low-fidelity samples. Deep Gaussian processes (GPs) are attractive for multifidelity modelling as they are non-parametric, robust to overfitting, perform well for small datasets, and, critically, can capture nonlinear and input-dependent relationships between data of different fidelities. Many datasets naturally contain gradient data, especially when they are generated by computational models that are compatible with automatic differentiation or have adjoint solutions. Principally, this work extends deep GPs to incorporate gradient data. We demonstrate this method on an analytical test problem and a realistic partial differential equation problem, where we predict the aerodynamic coefficients of a hypersonic flight vehicle over a range of flight conditions and geometries. In both examples, the gradient-enhanced deep GP outperforms a gradient-enhanced linear GP model and their non-gradient-enhanced counterparts.

📄 PDF Abstract BibTeX arXiv:2402.16059

Code (0)

등록된 구현이 없습니다.

Tasks

Gaussian Processes

Methods 이 논문이 사용한 방법론

GPS Greedy Policy Search (GPS) is a simple algorithm that learns a policy for test-time data augmentation based on the predictive performance on a validation set. GPS starts with…

Similar Papers 제목 키워드 기반

Gradient-enhanced multifidelity neural networks for high-dimensional function approximation

2021-03-23 · Jethro Nagawkar, Leifur Leifsson

In this work, a novel multifidelity machine learning (ML) model, the gradient-enhanced multifidelity neural networks (GEMFNNs), is proposed. This model is a multifidelity version of gradient-enhanced neural networks (GEN…

Vocal Bursts Intensity Prediction

Multifidelity Surrogate Models: A New Data Fusion Perspective

2024-04-21 · Daniel N Wilke

Multifidelity surrogate modelling combines data of varying accuracy and cost from different sources. It strategically uses low-fidelity models for rapid evaluations, saving computational resources, and high-fidelity mode…

Decision Makingregression

Multifidelity Data Fusion via Gradient-Enhanced Gaussian Process Regression

2020-08-03 · Yixiang Deng, Guang Lin, Xiu Yang

We propose a data fusion method based on multi-fidelity Gaussian process regression (GPR) framework. This method combines available data of the quantity of interest (QoI) and its gradients with different fidelity levels,…

GPRregression

Physics-Informed CoKriging: A Gaussian-Process-Regression-Based Multifidelity Method for Data-Model Convergence

2018-11-24 · Xiu Yang, David Barajas-Solano, Guzel Tartakovsky, Alexandre Tartakovsky

In this work, we propose a new Gaussian process regression (GPR)-based multifidelity method: physics-informed CoKriging (CoPhIK). In CoKriging-based multifidelity methods, the quantities of interest are modeled as linear…

Active LearningGaussian ProcessesGPRregression

Multifidelity Ensemble Kalman Filtering Using Surrogate Models Defined by Physics-Informed Autoencoders

2021-02-25 · Andrey A Popov, Adrian Sandu

Data assimilation is a Bayesian inference process that obtains an enhanced understanding of a physical system of interest by fusing information from an inexact physics-based model, and from noisy sparse observations of r…

Bayesian InferenceComputational Efficiency