Comparer des méthodes

	Krigage universel spatio-temporel	Krigage spatio-temporel
Domaine	Analyse spatiale	Analyse spatiale
Famille	Regression model	Regression model
Année d'origine	1999	1999
Auteur d'origine	Kyriakidis & Journel (1999); foundations in Matheron's geostatistics	Cressie & Huang; Kyriakidis & Journel
Type	Spatiotemporal geostatistical interpolation	Geostatistical interpolation
Source fondatrice	Kyriakidis, P. C., & Journel, A. G. (1999). Geostatistical space-time models: A review. Mathematical Geology, 31(6), 651-684.	Cressie, N., & Huang, H.-C. (1999). Classes of nonseparable, spatio-temporal stationary covariance functions. Journal of the American Statistical Association, 94(448), 1330-1340.
Alias	STUK, spatiotemporal universal kriging, space-time kriging with trend, universal kriging in space-time	spatiotemporal kriging, ST-kriging, space-time geostatistical interpolation, kriging in space-time
Apparentées	5	4
Résumé	Space-Time Universal Kriging (STUK) is a geostatistical method that interpolates a continuously varying phenomenon across both space and time while explicitly modelling a deterministic trend component. It generalises Universal Kriging to the joint space-time domain, producing unbiased optimal predictions and associated uncertainty estimates at unobserved space-time locations.	Space-Time Kriging is a geostatistical interpolation method that predicts an unknown variable at any location and time by borrowing strength from nearby observations in both space and time simultaneously. It models the joint spatial-temporal covariance structure through a space-time variogram, then uses optimal linear weights to produce predictions with quantified uncertainty.