RefDoc
Haut

Faire une nouvelle recherche
Make a new search
Lancer la recherche


Titre du document / Document title

Optimizing inverse distance weighted interpolation with cross-validation

Auteur(s) / Author(s)

MUELLER T. G. (1) ; DHANIKONDA S. R. K. (2) ; PUSULURI N. B. (2) ; KARATHANASIS A. D. (1) ; MATHIAS K. K. (2) ; MIJATOVIC B. (1) ; SEARS B. G. (1) ;

Affiliation(s) du ou des auteurs / Author(s) Affiliation(s)

(1) Department of Agronomy, University of Kentucky, N-122 Ag. Science North, Lexington, KY 40546-0091, ETATS-UNIS
(2) Department of Computer Science, 773 Anderson Hall, University of Kentucky, Lexington, KY 40506-0046, ETATS-UNIS

Résumé / Abstract

Inverse distance weighted interpolation can be easily optimized with commercially available software by selecting distance exponent values that minimize cross-validation (VCROSS) errors of prediction. The effectiveness of this approach has not been critically evaluated but is of concern because of known limitations of the VCROSS procedure. To evaluate this optimization procedure, it should be validated with an independent data set (VIDS). The objectives of this study were (1) to develop and test an optimization procedure based on VCROSS and VIDS analyses, (2) to test the accuracy of optimization of the VCROSS procedure, and (3) to evaluate the quality of maps created with VCROSS. Soil fertility and bulk soil electrical conductivity data from two previously published studies were used for the analyses. These included prediction and validation data sets for multiple locations. Our optimization procedure compared well with those obtained with a commercially available software program. The use of VCROSS resulted in overprediction of optimal distance exponent values and a substantial reduction in map quality. In many cases, the maps produced with VCROSS optimization were blocky and unrealistic. The VCROSS procedure should not be used to optimize distance exponent values for data collected on regular grids or along transects. Instead, distance exponent values between 1.5 and 2.0 should be used. Software developers should consider creating a VIDS optimizing procedure.

Revue / Journal Title

Soil science    ISSN  0038-075X   CODEN SOSCAK 

Source / Source

2005, vol. 170, no7, pp. 504-515 [12 page(s) (article)] (15 ref.)

Langue / Language

Anglais

Editeur / Publisher

Lippincott Williams & Wilkins, Hagerstown, MD, ETATS-UNIS  (1916) (Revue)

Mots-clés anglais / English Keywords

geostatistics

;

Spatial analysis

;

Optimum

;

programs

;

electrical conductivity

;

Property of soil

;

Bulk

;

Soil fertility

;

maps

;

accuracy

;

Procedure

;

Limitation

;

Prediction

;

prediction

;

errors

;

software

;

Cross validation

;

interpolation

;

Weight

;

optimization

;

Mots-clés français / French Keywords

Géostatistique

;

Analyse spatiale

;

Optimum

;

Programme

;

Conductivité électrique

;

Caractéristique sol

;

En vrac

;

Fertilité sol

;

Carte

;

Précision

;

Procédure

;

Limitation

;

Prédiction

;

Prévision

;

Erreur

;

Logiciel

;

Validation croisée

;

Interpolation

;

Poids

;

Optimisation

;

Mots-clés espagnols / Spanish Keywords

Geoestadística

;

Análisis espacial

;

Optimo

;

Programa

;

Conductividad eléctrica

;

Característica suelo

;

A granel

;

Fertilidad suelo

;

Mapa

;

Precisión

;

Procedimiento

;

Limitación

;

Predicción

;

Previsión

;

Error

;

Validación cruzada

;

Peso

;

Optimización

;

Mots-clés d'auteur / Author Keywords

Spatial analysis

;

interpolation

;

geostatistics

;

Localisation / Location

INIST-CNRS, Cote INIST : 589, 35400013212858.0030

Nº notice refdoc (ud4) : 17090338



Faire une nouvelle recherche
Make a new search
Lancer la recherche
Bas