A Kalman filter method for estimation and prediction of space–time data with an autoregressive structure

Abstract We propose a new Kalman filter algorithm to provide a formal statistical analysis of space–time data with an autoregressive structure. The Kalman filter technique allows to capture the temporal dependence as well as the spatial correlation structure through state-space equations, and it is aimed to perform statistical inference in terms of both parameter estimation and prediction at unobserved locations. We put in relevance the nugget effect at the observation equation. We test our procedure and compare it with classical kriging prediction via an intensive simulation study. We show that the Kalman filter is superior in both the estimation, without using a plug-in approach, and prediction for spatio-temporal data, providing a suitable formal procedure for the statistical analysis of space–time data. Finally, an application to the prediction of daily air temperature data in some regions of southern Chile is presented.

[1]  P. Guttorp,et al.  A non‐homogeneous hidden Markov model for precipitation occurrence , 1999 .

[2]  Michela Cameletti,et al.  A Unified Statistical Approach for Simulation, Modeling, Analysis and Mapping of Environmental Data , 2010, Simul..

[3]  Mike Rees,et al.  5. Statistics for Spatial Data , 1993 .

[4]  N. Cressie,et al.  Spatio-temporal prediction of snow water equivalent using the Kalman filter , 1996 .

[5]  Jean Thioulouse,et al.  Evaluation of the precision of systematic sampling: Nugget effect and covariogram modelling , 1993 .

[6]  Jonathan R. Stroud,et al.  An Ensemble Kalman Filter and Smoother for Satellite Data Assimilation , 2010 .

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

[8]  N. C. Van de Giesen,et al.  Using a spatio-temporal dynamic state-space model with the EM algorithm to patch gaps in daily riverflow series , 2005 .

[9]  Han-Xiong Li,et al.  Spatio-Temporal Modeling of Nonlinear Distributed Parameter Systems , 2011 .

[10]  K. Mardia,et al.  Maximum likelihood estimation of models for residual covariance in spatial regression , 1984 .

[11]  M. Bevilacqua,et al.  Estimation and prediction using generalized Wendland covariance functions under fixed domain asymptotics , 2016, The Annals of Statistics.

[12]  Guillermo Ferreira,et al.  Kalman filter estimation for a regression model with locally stationary errors , 2013, Comput. Stat. Data Anal..

[13]  Stefano Grassi,et al.  When Long Memory Meets the Kalman Filter: A Comparative Study , 2011, Comput. Stat. Data Anal..

[14]  Mohinder S. Grewal,et al.  Global Positioning Systems, Inertial Navigation, and Integration , 2000 .

[15]  N. Cressie,et al.  A dimension-reduced approach to space-time Kalman filtering , 1999 .

[16]  Christopher K. Wikle,et al.  Estimation of Parameterized Spatio-Temporal Dynamic Models , 2007 .

[17]  Jeffrey L. Anderson.  An Ensemble Adjustment Kalman Filter for Data Assimilation , 2001 .

[18]  Richard A. Davis,et al.  Time Series: Theory and Methods , 2013 .

[19]  Mevin B Hooten,et al.  The basis function approach for modeling autocorrelation in ecological data. , 2016, Ecology.

[20]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[21]  Han-Xiong Li,et al.  Spatio-Temporal Modeling of Nonlinear Distributed Parameter Systems: A Time/Space Separation Based Approach , 2011 .

[22]  H. Rue,et al.  Spatio-temporal modeling of particulate matter concentration through the SPDE approach , 2012, AStA Advances in Statistical Analysis.

[23]  Christopher K. Wikle,et al.  Space-time Kalman filter , 2014 .

[24]  P. Guttorp,et al.  Geostatistical Space-Time Models, Stationarity, Separability, and Full Symmetry , 2007 .

[25]  Wilfredo Palma,et al.  State space modeling of long-memory processes , 1998 .

[26]  C. Wikle.  Hierarchical Models in Environmental Science , 2003 .

[27]  Moreno Bevilacqua,et al.  Analysis of Random Fields Using CompRandFld , 2015 .

[28]  Anthony N. Pettitt,et al.  Comment on the paper: ‘Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations’ by Rue, H. Martino, S. and Chopin, N. , 2009 .

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

[30]  Javad Rezaie,et al.  Kalman filter variants in the closed skew normal setting , 2014, Comput. Stat. Data Anal..

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

[32]  Michela Cameletti,et al.  The EM algorithm in a distributed computing environment for modelling environmental space-time data , 2009, Environ. Model. Softw..

[33]  Sujit K. Sahu,et al.  Hierarchical Bayesian models for space-time air pollution data , 2012 .

[34]  N. Cressie,et al.  Fixed Rank Filtering for Spatio-Temporal Data , 2010 .

[35]  Hugh F. Durrant-Whyte,et al.  Evaluating the Performance of Kalman-Filter-Based EEG Source Localization , 2009, IEEE Transactions on Biomedical Engineering.

[36]  J. Mateu,et al.  Spatio-temporal analysis with short- and long-memory dependence: a state-space approach , 2018 .

[37]  D. Bernstein,et al.  What is the ensemble Kalman filter and how well does it work? , 2006, 2006 American Control Conference.

[38]  Dale L. Zimmerman,et al.  A comparison of spatial semivariogram estimators and corresponding ordinary Kriging predictors , 1991 .

[39]  M. Genton,et al.  A skewed Kalman filter , 2005 .

[40]  Michael A. West,et al.  Time Series: Modeling, Computation, and Inference , 2010 .

[41]  Melvin J. Hinich,et al.  Time Series Analysis by State Space Methods , 2001 .

[42]  F. J. Alonso,et al.  The Kriged Kalman filter , 1998 .

[43]  Nozer D. Singpurwalla,et al.  Understanding the Kalman Filter , 1983 .

[44]  S. Dass,et al.  Nonlinear dynamical system identification using unscented Kalman filter , 2016 .

[45]  J. Angus.  Forecasting, Structural Time Series and the Kalman Filter , 1992 .