Search results for "kriging"
showing 3 items of 93 documents
Magnetic susceptibility spatial distribution as an indicator of soil pollution in the area of Opole city = Rozkład przestrzenny podatności magnetyczn…
2018
Magnetometria glebowa, polegająca na pomiarze podatności magnetycznej wierzchniej warstwy gleby, jest bardzo przydatną i coraz powszechniej stosowaną techniką monitorowania stanu gleb objętych wpływem antropopresji. Jak wynika z danych literaturowych, metoda ta wymaga dalszego udoskonalania, szczególnie w zakresie technik obrazowania danych magnetometrycznych. Celem badań była ocena przekształceń magnetycznych gleb na terenie miasta Opola (woj. opolskie) z zastosowaniem magnetometrii glebowej oraz trzech technik interpolacji danych magnetometrycznych (naturalnego sąsiedztwa NN, ważonych odwrotnych odległości IDW oraz krigingu zwykłego OK). Dane zostały zgromadzone podczas pomiarów terenowyc…
Spatial data fusion and analysis for soil characterization: a case study in a coastal basin of south-western Sicily (southern Italy)
2012
Salinization is one of the most serious problems confronting sustainable agriculture in semi-arid and arid regions. Accurate mapping of soil salinization and the associated risk represent a fundamental step in planning agricultural and remediation activities. Geostatistical analysis is very useful for soil quality assessment because it makes it possible to determine the spatial relationships between selected variables and to produce synthetic maps of spatial variation. The main objective of this paper was to map the soil salinization risk in the Delia-Nivolelli alluvial basin (south-western Sicily, southern Italy), using multivariate geostatistical techniques and a set of topographical, phy…
Sensitivity analysis of Gaussian processes for oceanic chlorophyll prediction
2015
Gaussian Process Regression (GPR) for machine learning has lately been successfully introduced for chlorophyll content mapping from remotely sensed data. The method provides a fast, stable and accurate prediction of biophysical parameters. However, since GPR is a non-linear kernel regression method, the relevance of the features are not accessible. In this paper, we introduce a probabilistic approach for feature sensitivity analysis (SA) of the GPR in order to reveal the relative importance of the features (bands) being used in the regression process. We evaluated the SA on GPR ocean chlorophyll content prediction. The method revealed the importance of the spectral bands, thus allowing the …