Spatial prediction and ordinary kriging

Conference · Sun May 01 04:00:00 EDT 1988 · J. Int. Assoc. Math. Geol.; (United States)

OSTI ID:6288066

Cressie, N

Suppose data /Z(s/sub i/):i = 1,...,n/ are observed at spatial locations /s/sub i/:i = 1,...,n/. From these data, an unknown Z(s/sub 0/) is to be predicted at a known location s/sub 0/, or, if Z(s/sub 0/) has a component of measurement error, then a smooth version S(s/sub 0/) should be predicted. This article considers the assumptions needed to carry out the spatial prediction using ordinary kriging, and looks at how nugget effect, range, and sill of the variogram affect the predictor. It is concluded that certain commonly held interpretations of these variogram parameters should be modified.

• Research Organization: Iowa State Univ., Ames (USA)
• OSTI ID: 6288066
• Report Number(s): CONF-8704137-
• Conference Information: Journal Name: J. Int. Assoc. Math. Geol.; (United States) Journal Volume: 20:4
• Country of Publication: United States
• Language: English

Related Subjects

58 GEOSCIENCES
580203* -- Geophysics-- Geophysical Survey Methods-- (1980-1989)
DATA COVARIANCES
DIAGRAMS
DISTRIBUTION
FORECASTING
FUNCTIONS
GAUSS FUNCTION
GEOLOGIC DEPOSITS
GEOPHYSICAL SURVEYS
KRIGING
MATHEMATICAL MODELS
MATHEMATICS
MULTIVARIATE ANALYSIS
RANDOMNESS
SPATIAL DISTRIBUTION
STATISTICAL MODELS
STATISTICS
STOCHASTIC PROCESSES
SURVEYS
VARIATIONS