Open Access
March 2011 Spatial models generated by nested stochastic partial differential equations, with an application to global ozone mapping
David Bolin, Finn Lindgren
Ann. Appl. Stat. 5(1): 523-550 (March 2011). DOI: 10.1214/10-AOAS383
Abstract

A new class of stochastic field models is constructed using nested stochastic partial differential equations (SPDEs). The model class is computationally efficient, applicable to data on general smooth manifolds, and includes both the Gaussian Matérn fields and a wide family of fields with oscillating covariance functions. Nonstationary covariance models are obtained by spatially varying the parameters in the SPDEs, and the model parameters are estimated using direct numerical optimization, which is more efficient than standard Markov Chain Monte Carlo procedures. The model class is used to estimate daily ozone maps using a large data set of spatially irregular global total column ozone data.

References

1.

Adler, R. J. (1981). The Geometry of Random Fields. Wiley, New York. MR611857Adler, R. J. (1981). The Geometry of Random Fields. Wiley, New York. MR611857

2.

Bolin, D. and Lindgren, F. (2009). Wavelet Markov approximations as efficient alternatives to tapering and convolution fields (submitted). Preprints in Math. Sci. 2009:13, Lund Univ.Bolin, D. and Lindgren, F. (2009). Wavelet Markov approximations as efficient alternatives to tapering and convolution fields (submitted). Preprints in Math. Sci. 2009:13, Lund Univ.

3.

Cressie, N. and Johannesson, G. (2008). Fixed rank kriging for very large spatial data sets. J. R. Stat. Soc. Ser. B Stat. Methodol. 70 209–226. MR2412639 10.1111/j.1467-9868.2007.00633.xCressie, N. and Johannesson, G. (2008). Fixed rank kriging for very large spatial data sets. J. R. Stat. Soc. Ser. B Stat. Methodol. 70 209–226. MR2412639 10.1111/j.1467-9868.2007.00633.x

4.

Gelman, A., Roberts, G. O. and Gilks, W. R. (1996). Efficient Metropolis jumping rules. Bayesian Stat. 5 599–607. MR1425429Gelman, A., Roberts, G. O. and Gilks, W. R. (1996). Efficient Metropolis jumping rules. Bayesian Stat. 5 599–607. MR1425429

5.

Gneiting, T. (1998). Simple tests for the validity of correlation function models on the circle. Statist. Probab. Lett. 39 119–122. MR1652540Gneiting, T. (1998). Simple tests for the validity of correlation function models on the circle. Statist. Probab. Lett. 39 119–122. MR1652540

6.

Hastie, T., Tibshirani, R. and Friedman, J. H. (2001). The Elements of Statistical Learning. Springer, New York. MR1851606Hastie, T., Tibshirani, R. and Friedman, J. H. (2001). The Elements of Statistical Learning. Springer, New York. MR1851606

7.

Hill, E. L. (1954). The theory of vector spherical harmonics. Amer. J. Phys. 22 211–214. MR61226 10.1119/1.1933682Hill, E. L. (1954). The theory of vector spherical harmonics. Amer. J. Phys. 22 211–214. MR61226 10.1119/1.1933682

8.

Jun, M. and Stein, M. L. (2007). An approach to producing space–time covariance functions on spheres. Technometrics 49 468–479. MR2394558 10.1198/004017007000000155Jun, M. and Stein, M. L. (2007). An approach to producing space–time covariance functions on spheres. Technometrics 49 468–479. MR2394558 10.1198/004017007000000155

9.

Jun, M. and Stein, M. L. (2008). Nonstationary covariance models for global data. Ann. Appl. Statist. 2 1271–1289. MR2655659 10.1214/08-AOAS183 euclid.aoas/1231424210 Jun, M. and Stein, M. L. (2008). Nonstationary covariance models for global data. Ann. Appl. Statist. 2 1271–1289. MR2655659 10.1214/08-AOAS183 euclid.aoas/1231424210

10.

Lindgren, F., Rue, H. and Lindström, J. (2010). An explicit link between Gaussian fields and Gaussian Markov random fields, The SPDE approach (submitted). Preprints in Math. Sci. 2010:3, Lund Univ.Lindgren, F., Rue, H. and Lindström, J. (2010). An explicit link between Gaussian fields and Gaussian Markov random fields, The SPDE approach (submitted). Preprints in Math. Sci. 2010:3, Lund Univ.

11.

Lindström, J. and Lindgren, F. (2008). A Gaussian Markov random field model for total yearly precipitation over the African Sahel. Preprints in Math. Sci. 2008:8, Lund Univ.Lindström, J. and Lindgren, F. (2008). A Gaussian Markov random field model for total yearly precipitation over the African Sahel. Preprints in Math. Sci. 2008:8, Lund Univ.

12.

Matérn, B. (1960). Spatial Variation. Meddelanden från statens skogsforskningsinstitut, Stockholm.Matérn, B. (1960). Spatial Variation. Meddelanden från statens skogsforskningsinstitut, Stockholm.

13.

McPeters, R. D., Bhartia, P. K., Krueger, A. J., Herman, J. R., Schlesinger, B., Wellemeyer, C. G., Seftor, C. J., Jaross, G., Taylor, S. L., Swissler, T., Torres, O., Labow, G., Byerly, W. and Cebula, R. P. (1996). Nimbus-7 Total Ozone Mapping Spectrometer (TOMS) data products user’s guide. NASA Reference Publication 1384.McPeters, R. D., Bhartia, P. K., Krueger, A. J., Herman, J. R., Schlesinger, B., Wellemeyer, C. G., Seftor, C. J., Jaross, G., Taylor, S. L., Swissler, T., Torres, O., Labow, G., Byerly, W. and Cebula, R. P. (1996). Nimbus-7 Total Ozone Mapping Spectrometer (TOMS) data products user’s guide. NASA Reference Publication 1384.

14.

Rue, H. and Held, L. (2005). Gaussian Markov Random Fields. Chapman & Hall/CRC, Boca Raton, FL. MR2130347Rue, H. and Held, L. (2005). Gaussian Markov Random Fields. Chapman & Hall/CRC, Boca Raton, FL. MR2130347

15.

Rue, H., Martino, S. and Chopin, N. (2009). Approximate Bayesian inference for latent Gaussian models using integrated nested laplace approximations (with discussion). J. R. Stat. Soc. Ser. B Stat. Methodol. 71 319–392. MR2649602 10.1111/j.1467-9868.2008.00700.xRue, H., Martino, S. and Chopin, N. (2009). Approximate Bayesian inference for latent Gaussian models using integrated nested laplace approximations (with discussion). J. R. Stat. Soc. Ser. B Stat. Methodol. 71 319–392. MR2649602 10.1111/j.1467-9868.2008.00700.x

16.

Stein, M. L. (2007). Spatial variation of total column ozone on a global scale. Ann. Appl. Statist. 1 191–210. MR2393847 10.1214/07-AOAS106 euclid.aoas/1183143735 Stein, M. L. (2007). Spatial variation of total column ozone on a global scale. Ann. Appl. Statist. 1 191–210. MR2393847 10.1214/07-AOAS106 euclid.aoas/1183143735

17.

Thomas, G. B. and Finney, R. L. (1995). Calculus and Analytic Geometry, 9 ed. Addison Wesley, New York.Thomas, G. B. and Finney, R. L. (1995). Calculus and Analytic Geometry, 9 ed. Addison Wesley, New York.

18.

Whittle, P. (1963). Stochastic processes in several dimensions. Bull. Inst. Internat. Statist. 40 974–994. MR173287Whittle, P. (1963). Stochastic processes in several dimensions. Bull. Inst. Internat. Statist. 40 974–994. MR173287

19.

Yaglom, A. M. (1987). Correlation Theory of Stationary and Related Random Functions 1. Springer, New York.Yaglom, A. M. (1987). Correlation Theory of Stationary and Related Random Functions 1. Springer, New York.
Copyright © 2011 Institute of Mathematical Statistics
David Bolin and Finn Lindgren "Spatial models generated by nested stochastic partial differential equations, with an application to global ozone mapping," The Annals of Applied Statistics 5(1), 523-550, (March 2011). https://doi.org/10.1214/10-AOAS383
Published: March 2011
Vol.5 • No. 1 • March 2011
Back to Top