Spatial variability in classification accuracy of agricultural crops in the Dutch national land-cover database

Research output: Contribution to journalArticleAcademicpeer-review

35 Citations (Scopus)

Abstract

Variability in per cell classification accuracy is predominantly modelled with land-cover class as the explanatory variable, i.e. with users' accuracies from the error matrix. Logistic regression models were developed to include other explanatory variables: heterogeneity in the 3x3 window around a cell, the size of the patch and the complexity of the landscape in which a cell is located. It was found that per cell, the probability of correct classification was significantly (alpha = 0.05) higher for cells with a less heterogeneous neighbourhood, for cells part of larger patches and for cells in regions with a less heterogeneous landscape. To validate the models, a leave-one-out procedure was applied in which the absolute difference between the actual and the model-estimated number of cells correctly classified was summarized over 55 regions in the Netherlands. The sum of differences reduced from 60.9 to 48.1 after adding the variables 'patch size' and 'landscape dominance' to the land-cover class model. Spatial variability thus modelled therefore led to a substantial improvement in the estimation of the per cell classification accuracy.
Original languageEnglish
Pages (from-to)611-626
JournalInternational Journal of Geographical Information Science
Volume18
Issue number6
DOIs
Publication statusPublished - 2004

Fingerprint

Crops
land cover
crop
patch size
Logistics
logistics
Netherlands
regression
matrix

Keywords

  • crops
  • land use
  • spatial variation

Cite this

@article{d179363c06454f5385a7ab58b0c0991a,
title = "Spatial variability in classification accuracy of agricultural crops in the Dutch national land-cover database",
abstract = "Variability in per cell classification accuracy is predominantly modelled with land-cover class as the explanatory variable, i.e. with users' accuracies from the error matrix. Logistic regression models were developed to include other explanatory variables: heterogeneity in the 3x3 window around a cell, the size of the patch and the complexity of the landscape in which a cell is located. It was found that per cell, the probability of correct classification was significantly (alpha = 0.05) higher for cells with a less heterogeneous neighbourhood, for cells part of larger patches and for cells in regions with a less heterogeneous landscape. To validate the models, a leave-one-out procedure was applied in which the absolute difference between the actual and the model-estimated number of cells correctly classified was summarized over 55 regions in the Netherlands. The sum of differences reduced from 60.9 to 48.1 after adding the variables 'patch size' and 'landscape dominance' to the land-cover class model. Spatial variability thus modelled therefore led to a substantial improvement in the estimation of the per cell classification accuracy.",
keywords = "gewassen, landgebruik, ruimtelijke variatie, crops, land use, spatial variation",
author = "{van Oort}, P.A.J. and A.K. Bregt and {de Bruin}, S. and {de Wit}, A.J.W. and A. Stein",
year = "2004",
doi = "10.1080/13658810410001701969",
language = "English",
volume = "18",
pages = "611--626",
journal = "International Journal of Geographical Information Science",
issn = "1365-8816",
publisher = "Taylor & Francis",
number = "6",

}

TY - JOUR

T1 - Spatial variability in classification accuracy of agricultural crops in the Dutch national land-cover database

AU - van Oort, P.A.J.

AU - Bregt, A.K.

AU - de Bruin, S.

AU - de Wit, A.J.W.

AU - Stein, A.

PY - 2004

Y1 - 2004

N2 - Variability in per cell classification accuracy is predominantly modelled with land-cover class as the explanatory variable, i.e. with users' accuracies from the error matrix. Logistic regression models were developed to include other explanatory variables: heterogeneity in the 3x3 window around a cell, the size of the patch and the complexity of the landscape in which a cell is located. It was found that per cell, the probability of correct classification was significantly (alpha = 0.05) higher for cells with a less heterogeneous neighbourhood, for cells part of larger patches and for cells in regions with a less heterogeneous landscape. To validate the models, a leave-one-out procedure was applied in which the absolute difference between the actual and the model-estimated number of cells correctly classified was summarized over 55 regions in the Netherlands. The sum of differences reduced from 60.9 to 48.1 after adding the variables 'patch size' and 'landscape dominance' to the land-cover class model. Spatial variability thus modelled therefore led to a substantial improvement in the estimation of the per cell classification accuracy.

AB - Variability in per cell classification accuracy is predominantly modelled with land-cover class as the explanatory variable, i.e. with users' accuracies from the error matrix. Logistic regression models were developed to include other explanatory variables: heterogeneity in the 3x3 window around a cell, the size of the patch and the complexity of the landscape in which a cell is located. It was found that per cell, the probability of correct classification was significantly (alpha = 0.05) higher for cells with a less heterogeneous neighbourhood, for cells part of larger patches and for cells in regions with a less heterogeneous landscape. To validate the models, a leave-one-out procedure was applied in which the absolute difference between the actual and the model-estimated number of cells correctly classified was summarized over 55 regions in the Netherlands. The sum of differences reduced from 60.9 to 48.1 after adding the variables 'patch size' and 'landscape dominance' to the land-cover class model. Spatial variability thus modelled therefore led to a substantial improvement in the estimation of the per cell classification accuracy.

KW - gewassen

KW - landgebruik

KW - ruimtelijke variatie

KW - crops

KW - land use

KW - spatial variation

U2 - 10.1080/13658810410001701969

DO - 10.1080/13658810410001701969

M3 - Article

VL - 18

SP - 611

EP - 626

JO - International Journal of Geographical Information Science

JF - International Journal of Geographical Information Science

SN - 1365-8816

IS - 6

ER -