Modeling and emulation of nonstationary Gaussian fields

  title={Modeling and emulation of nonstationary Gaussian fields},
  author={Douglas W. Nychka and Dorit M. Hammerling and Mitchell Krock and Ashton Wiens},
  journal={Spatial Statistics},
Geophysical and other natural processes often exhibit non-stationary covariances and this feature is important to take into account for statistical models that attempt to emulate the physical process. A convolution-based model is used to represent non-stationary Gaussian processes that allows for variation in the correlation range and vari- ance of the process across space. Application of this model has two steps: windowed estimates of the covariance function under the as- sumption of local… Expand
Modeling spatial data using local likelihood estimation and a Matérn to spatial autoregressive translation
This work investigates the non-stationary spatial autoregressive (SAR) model related to Gaussian Markov random field (GMRF) methods, which is amenable to plug in local estimates and practical for large data sets. Expand
Bayesian Nonstationary and Nonparametric Covariance Estimation for Large Spatial Data
Given replicate observations of a Gaussian spatial field, this work proposes nonstationary and nonparametric Bayesian inference on the spatial dependence and proposes a near-linear number of nonzero entries in a sparse Cholesky factor of the precision matrix. Expand
Fast covariance parameter estimation of spatial Gaussian process models using neural networks
This work trains NNs to take moderate size spatial fields or variograms as input and return the range and noise-to-signal covariance parameters, which provide estimates with a similar accuracy compared to ML estimation and at a speedup by a factor of 100 or more. Expand
Flexible nonstationary spatiotemporal modeling of high‐frequency monitoring data
This work applies the framework of half-spectral covariance functions to the case of nonstationarity in space and time and demonstrates that this method provides a natural and tractable way to incorporate complex behaviors into a covariance model. Expand
Improving Bayesian Local Spatial Models in Large Datasets
A novel Bayesian three-step approach that allows for smaller regions without compromising the increase of the variance that would follow, and is able to propagate the uncertainty from one step to the next without issues caused by reusing the data. Expand
Empirical Bayesian kriging implementation and usage.
The EBK variant of empirical Bayesian kriging (EBK) is a fast and reliable solution for both automatic and interactive data interpolation and can be used for interpolation of very large datasets up to billions of points. Expand
Emulating Earth system model temperatures with MESMER: from global mean temperature trajectories to grid-point-level realizations on land
This study assesses the feasibility of geographically explicit climate model emulation and shows that to successfully mimic single-model initial-condition ensembles of yearly temperature from 1870 to 2100 on grid-point to regional scales with MESMER, it is sufficient to train on a single ESM run, but separate emulators need to be calibrated for individual ESMs given fundamental inter-model differences. Expand
Emulating Earth System Model temperatures: from global mean temperature trajectories to grid-point level realizations on land
Abstract. Earth System Models (ESMs) are invaluable tools to study the climate system's response to specific greenhouse gas emission pathways. Large single-model initial-condition and multi-modelExpand
Nonrigid Registration Using Gaussian Processes and Local Likelihood Estimation
The nonrigid registration method is applied to a pair of massive remote sensing elevation data sets exhibiting complex geological terrain, with improved accuracy and uncertainty quantification in a cross validation study versus two rigid registration methods. Expand
Exploration of PM mass, source, and component-related factors that might explain heterogeneity in daily PM2.5-mortality associations across the United States
Abstract Multi-city epidemiologic studies examining short-term (daily) differences in fine particulate matter (PM2.5) provide evidence of substantial spatial heterogeneity in city-specific mortalityExpand


A Generalized Convolution Model and Estimation for Non-stationary Random Functions
Standard geostatistical models assume second order stationarity of the underlying Random Function. In some instances, there is little reason to expect the spatial dependence structure to beExpand
Estimation and Prediction of a Class of Convolution-Based Spatial Nonstationary Models for Large Spatial Data
In this article we address two important issues common to the analysis of large spatial datasets. One is the modeling of nonstationarity, and the other is the computational challenges in doingExpand
Spatial Modelling Using a New Class of Nonstationary Covariance Functions.
A new class of nonstationary covariance functions for spatial modelling, which includes a non stationary version of the Matérn stationary covariance, in which the differentiability of the spatial surface is controlled by a parameter, freeing one from fixing the differentiable in advance. Expand
Exploring a New Class of Non-stationary Spatial Gaussian Random Fields with Varying Local Anisotropy
Gaussian random fields (GRFs) constitute an important part of spatial modelling, but can be computationally infeasible for general covariance structures. An efficient approach is to specify GRFs viaExpand
Spectral methods for nonstationary spatial processes
SUMMARY We propose a nonstationary periodogram and various parametric approaches for estimating the spectral density of a nonstationary spatial process. We also study the asymptotic properties of theExpand
A Multiresolution Gaussian Process Model for the Analysis of Large Spatial Datasets
We develop a multiresolution model to predict two-dimensional spatial fields based on irregularly spaced observations. The radial basis functions at each level of resolution are constructed using aExpand
An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach
Continuously indexed Gaussian fields (GFs) are the most important ingredient in spatial statistical modelling and geostatistics. The specification through the covariance function gives an intuitiveExpand
A process-convolution approach to modelling temperatures in the North Atlantic Ocean
  • D. Higdon
  • Computer Science
  • Environmental and Ecological Statistics
  • 2004
A Bayesian approach is taken here which relies on Markov chain Monte Carlo for exploring the posterior distribution of the convolution kernel in a process-convolution approach for space-time modelling. Expand
Kriging and automated variogram modeling within a moving window
Abstract A spatial estimation procedure based on ordinary kriging is described and evaluated which consists of using only sampling sites contained within a moving window centered at the estimateExpand
Local likelihood estimation for nonstationary random fields
A weighted local likelihood estimate for the parameters that govern the local spatial dependency of a locally stationary random field is developed that smoothly downweights the influence of faraway observations, works for irregular sampling locations, and when designed appropriately, can trade bias and variance for reducing estimation error. Expand