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 a Wendland compactly supported correlation function with the nodes arranged on a rectangular grid. The grid at each finer level increases by a factor of two and the basis functions are scaled to have a constant overlap. The coefficients associated with the basis functions at each level of resolution are distributed according to a Gaussian Markov random field (GMRF) and take advantage of the fact that the basis is organized as a lattice. Several numerical examples and analytical results establish that this scheme gives a good approximation to standard covariance functions such as the Matérn and also has flexibility to fit more complicated shapes. The other important feature of this model is that it can be applied to statistical inference for large spatial datasets because key matrices in the computations are sparse. The computational efficiency applies to both the evaluation of the likelihood and spatial predictions.

[1]  S. R. Searle,et al.  On Deriving the Inverse of a Sum of Matrices , 1981 .

[2]  C. Willmott,et al.  CLIMATOLOGICALLY AIDED INTERPOLATION (CAI) OF TERRESTRIAL AIR TEMPERATURE , 1995 .

[3]  Holger Wendland,et al.  Piecewise polynomial, positive definite and compactly supported radial functions of minimal degree , 1995, Adv. Comput. Math..

[4]  Holger Wendland,et al.  Error Estimates for Interpolation by Compactly Supported Radial Basis Functions of Minimal Degree , 1998 .

[5]  Sw. Banerjee,et al.  Hierarchical Modeling and Analysis for Spatial Data , 2003 .

[6]  G. Skomal,et al.  in the North Atlantic Ocean , 2003 .

[7]  P. Jones,et al.  Hemispheric and Large-Scale Surface Air Temperature Variations: An Extensive Revision and an Update to 2001. , 2003 .

[8]  Zhiyi Chi,et al.  Approximating likelihoods for large spatial data sets , 2004 .

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

[10]  Leonhard Held,et al.  Gaussian Markov Random Fields: Theory and Applications , 2005 .

[11]  Jun Yan.  Gaussian Markov Random Fields: Theory and Applications. Harvard Rue and Leonhard Held , 2006 .

[12]  Richard L. Smith,et al.  Asymptotic properties of computationally efficient alternative estimators for a class of multivariate normal models , 2007 .

[13]  Peter Congdon,et al.  Gaussian Markov Random Fields: Theory and Applications , 2007 .

[14]  Finn Lindgren,et al.  Explicit construction of GMRF approximations to generalised Matérn fields on irregular grids , 2007 .

[15]  M. Fuentes.  Approximate Likelihood for Large Irregularly Spaced Spatial Data , 2007, Journal of the American Statistical Association.

[16]  N. Cressie,et al.  Fixed rank kriging for very large spatial data sets , 2008 .

[17]  Michael L. Stein,et al.  A modeling approach for large spatial datasets , 2008 .

[18]  H. Rue,et al.  Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations , 2009 .

[19]  Stephan R. Sain,et al.  spam: A Sparse Matrix R Package with Emphasis on MCMC Methods for Gaussian Markov Random Fields , 2010 .

[20]  Matthias Katzfuss,et al.  Spatio‐temporal smoothing and EM estimation for massive remote‐sensing data sets , 2011 .

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

[22]  Noel A Cressie,et al.  Statistics for Spatio-Temporal Data , 2011 .

[23]  Jianhua Z. Huang,et al.  A full scale approximation of covariance functions for large spatial data sets , 2012 .

[24]  Dorit Hammerling,et al.  Explorer A Multi-resolution Gaussian process model for the analysis of large spatial data sets , 2012 .

[25]  Andrew O. Finley,et al.  Approximate Bayesian inference for large spatial datasets using predictive process models , 2012, Comput. Stat. Data Anal..

[26]  P. Jones,et al.  Hemispheric and large-scale land-surface air temperature variations: An extensive revision and an update to 2010: LAND-SURFACE TEMPERATURE VARIATIONS , 2012 .

[27]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[28]  Douglas W. Nychka,et al.  Multiresolution Kriging Based on Markov Random Fields , 2015 .