Spectral representation of spatially correlated data

Authors

  • Edilenia Queiroz Pereira Departamento de Estatística – Universidade Estadual de Maringá – UEM
  • Diogo Francisco Rossoni Departamento de Estatística - Universidade Estadual de Maringá https://orcid.org/0000-0001-6337-6628
  • Carla Eloize Carducci Universidade Federal de Santa Catarina – Campus de Curitibanos – UFSC

Keywords:

Spectral density, Spatial Statistics, Geostatistics, Big Data

Abstract

Geostatistics seeks to detect and explain the dependence associated with a continuous spatial random field.
Both the spatial and spectral approaches can be valid instruments to detect this spatial dependence. The study of Geostatistics through the spectral approach seeks ways to solve problems that the Geostatistical theory faces, such as manipulation of large databases. For this purpose, spectral techniques are used, being these powerful tools to study the spatial structure, besides offering significant computational benefits in data manipulation. It was found that from the spectral density it is possible to obtain estimates to calculate the covariance; With covariance directly related to semivariance, the estimated semivariance can be obtained. In addition, it has been shown that the computational time spent when working with the spectral density remains constant for all n sizes of simulated samples. In the classical method, the computational time spent increased exponentially as n increased.

References

CARDUCCI, C. E. et al. Scaling of pores in 3D images of Latosols (Oxisols) with contrasting mineralogy under a conservation management systemSoil Research, 2014a. Disponível em: <http://dx.doi.org/10.1071/SR13238>

CARDUCCI, C. E. et al. Distribuição espacial das raízes de cafeeiro e dos poros de dois Latossolos sob manejo conservacionista. Revista Brasileira de Engenharia Agrícola e Ambiental, v. 18, n. 3, p. 270–278, mar. 2014b.

CARDUCCI, C. E. et al. Spatial variability of pores in oxidic latosol under a conservation management system with different gypsium doses. Ciência e Agrotecnologia, v. 38, n. 5, p. 445–460, out. 2014c.

CARDUCCI, C. E. et al. Gypsum effects on the spatial distribution of coffee roots and the pores system in oxidic Brazilian Latosol. Soil and Tillage Research, v. 145, p. 171–180, jan. 2015.

CASAIS, R. M. C. CONTRIBUTIONS TO SPECTRAL SPATIAL STATISTICS. Santiago de Compostela: Universidade de Santiago de Compostela, 2006.

CHERRY, S. Nonparametric estimation of the sill in geostatistics. [s.l.] Environmetric, 1997.

CRESSIE, N. A. C. Fitting variogram models by weighted least squares. [s.l: s.n.].

CRESSIE, N. A. C.; HAWKINS, D. M. Robust estimation of the variogram: Mathematical Geology. [s.l: s.n.]. v. 12

FUENTES, M. Spectral methods for nonstationary spatial processes. Biometrika, v. 89, n. 1, p. 197–210, 2002.

GELFAND, A. et al. Handbook os Spatial Statistics. London: CRC Press, 2010.

GRINGARTEN, E.; DEUTSCH, C. V. Teacher’s Aide Variogram Interpretation and Modeling. Mathematical Geology, v. 33, n. 4, p. 507–534, 2001.

MATEU, J; JUAN, P; PORCU, E. Geostatistical Analysis Through Spectral Techniques: Some Words of Caution. Communications in Statistics - Simulation and Computation, v. 36, n. 5, p. 1035–1051, 2007.

R CORE TEAM. R: A language and environment for statistical computingVienna, AustriaR Foundation for Statistical Computing, 2015.

SCHLATHER, M. et al. Analysis, Simulation and Prediction of Multivariate Random Fields with Package RandomFields. Journal of Statistical Software, v. 63, n. 1, p. 1–25, 2015.

SEVCIKOVA, H.; PERCIVAL, D.; GNEITING, T. fractaldim: Estimation of fractal dimensions, 2014. Disponível em: <http://cran.r-project.org/package=fractaldim>

ZIMMERMAN, D. L.; ZIMMERMAN, M. B. A Monte Carlo comparison of spatial semivariogram estimators and corresponding ordinary kriging predictors. 33. ed. [s.l.] Technometrics, 1991.

Published

08-01-2017

How to Cite

Pereira, E. Q., Rossoni, D. F., & Carducci, C. E. (2017). Spectral representation of spatially correlated data. Sigmae, 5(1), 27–36. Retrieved from https://publicacoes.unifal-mg.edu.br/revistas/index.php/sigmae/article/view/425

Issue

Section

Applied Statistics