Nonstationary modeling for multivariate spatial processes

We derive a class of matrix valued covariance functions where the direct and cross-covariance functions are Matern. The parameters of the Matern class are allowed to vary with location, yielding local variances, local ranges, local geometric anisotropies and local smoothnesses. We discuss inclusion of a nonconstant cross-correlation coefficient and a valid approximation. Estimation utilizes kernel smoothed empirical covariance matrices and a locally weighted minimum Frobenius distance that yields local parameter estimates at any location. We derive the asymptotic mean squared error of our kernel smoother and discuss the case when multiple field realizations are available. Finally, the model is illustrated on two datasets, one a synthetic bivariate one-dimensional spatial process, and the second a set of temperature and precipitation model output from a regional climate model.

[1]  J. Hart,et al.  Kernel Regression Estimation Using Repeated Measurements Data , 1986 .

[2]  G. Oehlert,et al.  Regional Trends in Sulfate Wet Deposition , 1993 .

[3]  Debashis Paul,et al.  A GENERALIZED CONVOLUTION MODEL FOR MULTIVARIATE NONSTATIONARY SPATIAL PROCESSES , 2010 .

[4]  C. F. Sirmans,et al.  Nonstationary multivariate process modeling through spatially varying coregionalization , 2004 .

[5]  Richard G. Jones,et al.  A Regional Climate Change Assessment Program for North America , 2009 .

[6]  Alan E. Gelfand,et al.  Multivariate Spatial Modeling for Geostatistical Data Using Convolved Covariance Functions , 2007 .

[7]  Donald B. Percival,et al.  Estimators of Fractal Dimension: Assessing the Roughness of Time Series and Spatial Data , 2011, 1101.1444.

[8]  Chunsheng Ma,et al.  Mittag-Leffler vector random fields with Mittag-Leffler direct and cross covariance functions , 2013 .

[9]  M. Stein.  Nonstationary spatial covariance functions , 2005 .

[10]  Christopher J Paciorek,et al.  Spatial modelling using a new class of nonstationary covariance functions , 2006, Environmetrics.

[11]  Martin Schlather,et al.  Some covariance models based on normal scale mixtures , 2011 .

[12]  Ying Sun,et al.  A Valid Matérn Class of Cross-Covariance Functions for Multivariate Random Fields With Any Number of Components , 2012 .

[13]  D. Nychka,et al.  Spatial Analysis to Quantify Numerical Model Bias and Dependence , 2008 .

[14]  M. Genton.  Separable approximations of space‐time covariance matrices , 2007 .

[15]  Jorge Mateu,et al.  Quasi-arithmetic means of covariance functions with potential applications to space-time data , 2006, J. Multivar. Anal..

[16]  Istvan Szunyogh,et al.  A Statistical Investigation of the Sensitivity of Ensemble-Based Kalman Filters to Covariance Filtering , 2011 .

[17]  N. Higham.  Computing the nearest correlation matrix—a problem from finance , 2002 .

[18]  Bo Li,et al.  An approach to modeling asymmetric multivariate spatial covariance structures , 2011, J. Multivar. Anal..

[19]  H. Rue,et al.  An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach , 2011 .

[20]  Stephen P. Boyd,et al.  Least-Squares Covariance Matrix Adjustment , 2005, SIAM J. Matrix Anal. Appl..

[21]  Jianqing Fan.  Design-adaptive Nonparametric Regression , 1992 .

[22]  Michael L. Stein,et al.  Local likelihood estimation for nonstationary random fields , 2011, J. Multivar. Anal..

[23]  P. Guttorp,et al.  Studies in the history of probability and statistics XLIX On the Matérn correlation family , 2006 .

[24]  I. S. Gradshteyn,et al.  Table of Integrals, Series, and Products , 1976 .

[25]  Stephan R. Sain,et al.  A spatial analysis of multivariate output from regional climate models , 2011, 1104.2703.

[26]  Bruno Sansó,et al.  Joint projections of temperature and precipitation change from multiple climate models: a hierarchical Bayesian approach , 2009 .

[27]  Roger Woodard,et al.  Interpolation of Spatial Data: Some Theory for Kriging , 1999, Technometrics.

[28]  David Higdon,et al.  A process-convolution approach to modelling temperatures in the North Atlantic Ocean , 1998, Environmental and Ecological Statistics.

[29]  Emilio Porcu,et al.  Characterization theorems for some classes of covariance functions associated to vector valued random fields , 2011, J. Multivar. Anal..

[30]  M. Goulard,et al.  Linear coregionalization model: Tools for estimation and choice of cross-variogram matrix , 1992 .

[31]  P. Guttorp,et al.  Nonparametric Estimation of Nonstationary Spatial Covariance Structure , 1992 .

[32]  Mikyoung Jun,et al.  Non‐stationary Cross‐Covariance Models for Multivariate Processes on a Globe , 2011 .

[33]  Ronald P. Barry,et al.  Constructing and fitting models for cokriging and multivariable spatial prediction , 1998 .

[34]  S. Cohn,et al.  Ooce Note Series on Global Modeling and Data Assimilation Construction of Correlation Functions in Two and Three Dimensions and Convolution Covariance Functions , 2022 .

[35]  Richard L. Smith,et al.  Regional probabilities of precipitation change: A Bayesian analysis of multimodel simulations , 2004 .

[36]  R. Bhatia.  Positive Definite Matrices , 2007 .

[37]  M. Fuentes.  Spectral methods for nonstationary spatial processes , 2002 .

[38]  Richard L. Smith,et al.  Bayesian Modeling of Uncertainty in Ensembles of Climate Models , 2009 .

[39]  Naomi Altman,et al.  Kernel Smoothing of Data with Correlated Errors , 1990 .

[40]  Tatiyana V. Apanasovich,et al.  Cross-covariance functions for multivariate random fields based on latent dimensions , 2010 .

[41]  T. Gneiting,et al.  Matérn Cross-Covariance Functions for Multivariate Random Fields , 2010 .

[42]  Marc G. Genton,et al.  Correlation Models for Temperature Fields , 2011 .