On the condition number of covariance matrices in kriging, estimation, and simulation of random fields

DOI10.1007/BF02065878zbMath0970.86543OpenAlexW1965761461WikidataQ58404631 ScholiaQ58404631MaRDI QIDQ5935068

Eric F. Wood, Amvrossios C. Bagtzoglou, Rachid Ababou

Publication date: 20 June 2001

Published in: Mathematical Geology (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf02065878

Mathematics Subject Classification ID

Geostatistics (86A32)

Related Items (19)

The effect of the nugget on Gaussian process emulators of computer models ⋮ On the variational data assimilation problem solving and sensitivity analysis ⋮ A non-intrusive solution to the ill-conditioning problem of the gradient-enhanced Gaussian covariance matrix for Gaussian processes ⋮ Asymptotic behavior of the likelihood function of covariance matrices of spatial Gaussian processes ⋮ Composite Gaussian process models for emulating expensive functions ⋮ Assessing the estimation of nearly singular covariance matrices for modeling spatial variables ⋮ Probabilistic physics-guided transfer learning for material property prediction in extrusion deposition additive manufacturing ⋮ Polynomial genetic programming for response surface modeling. II: Adaptive approximate models with probabilistic optimization problems ⋮ On the condition number anomaly of Gaussian correlation matrices ⋮ Including a Nugget Effect in Lifted Brownian Covariance Models ⋮ Mathematical Challenges in Measuring Variability Patterns for Precipitation Analysis ⋮ Parallel Bayesian Global Optimization of Expensive Functions ⋮ Sequential Design of Computer Experiments for the Solution of Bayesian Inverse Problems ⋮ Model-data-driven constitutive responses: application to a multiscale computational framework ⋮ Cases for the nugget in modeling computer experiments ⋮ Fixed-domain asymptotics of the maximum likelihood estimator and the Gaussian process approach for deterministic models ⋮ Construction and efficient implementation of adaptive objective-based designs of experiments ⋮ An efficient methodology for modeling complex computer codes with Gaussian processes ⋮ Application of FFT-based algorithms for large-scale universal kriging problems

Uses Software

• Matlab

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Conditioning of the stationary Kriging matrices for some well-known covariance models
• Conditioning of coefficient matrices of ordinary kriging

This page was built for publication: On the condition number of covariance matrices in kriging, estimation, and simulation of random fields