Effect Of Noise In The Estimation Of Magnitudes With Spatial Dependence: A Spatial Statistics Technique Based On Kriging
Kriging is a family of linear methods for the estimation of physical quantities with spatial dependence which are optimal in the squared minima sense. To perform the interpolation, kriging considers, in addition to the value and location of the observations, the spatial correlation of the quantity b...
| Autores: | , |
|---|---|
| Tipo de recurso: | capítulo de libro |
| Fecha de publicación: | 2005 |
| País: | España |
| Institución: | Universidad Complutense de Madrid (UCM) |
| Repositorio: | Docta Complutense |
| Idioma: | inglés |
| OAI Identifier: | oai:docta.ucm.es:20.500.14352/53382 |
| Acceso en línea: | https://hdl.handle.net/20.500.14352/53382 |
| Access Level: | acceso abierto |
| Palabra clave: | 535 Images Óptica (Física) 2209.19 Óptica Física |
| Sumario: | Kriging is a family of linear methods for the estimation of physical quantities with spatial dependence which are optimal in the squared minima sense. To perform the interpolation, kriging considers, in addition to the value and location of the observations, the spatial correlation of the quantity by means of variogram, the random fluctuations of the measured magnitude and the resolution of the measuring devices. The traditional way kriging equations are solved involves the resolution of inverse of great matrices, so that it is normally quite time consuming. Comparing the uncertainty obtained with kriging (for magnitudes with spatial dependence) with standard techniques for uncertainty estimation, we have seen that for the case of regular sampling, the uncertainty estimation can be computed as a convolution. |
|---|