Distribución espacial de la incertidumbre en mapas de cubiertas obtenidos mediante teledetección

Translated title of the contribution: Spatial distribution of the uncertainty in land cover maps obtained from remote sensing

X. Pons, E. Sevillano, G. Moré, P. Serra, D. Cornford, M. Ninyerola

Research output: Contribution to journalArticle

Abstract

When combining remote sensing imagery with statistical classifiers to obtain categorical thematic maps it is not usual to provide data about the spatial distribution of the error and uncertainty of the resulting maps. This paper describes, in the context of GeoViQua FP7 project, feasible approaches for methods based on several steps such as hybrid classifiers. Both for “per pixel” and “per polygon” strategies, the proposal is based on the use of the available ground truth, which is used to properly model the spatial distribution of the errors. Results allow mapping the classification success with a very high level of reliability (R2>0,94), providing users a sound knowledge of the accuracy at every area of the map.

Original languageSpanish
Pages (from-to)1-10
Number of pages10
JournalRevista de teledeteccion
Issue number42
DOIs
Publication statusPublished - Dec 2014

Fingerprint

land cover
uncertainty
spatial distribution
remote sensing
polygon
pixel
imagery
method
project

Bibliographical note

Esta revista se publica bajo una Licencia Creative Commons Atribución-NoComercial-SinDerivar 4.0 Internacional

Funding: Comisión Europea “QUAlity aware VIsualisation for the Global Earth
Observation system of systems (GeoViQua)”, ref. FP7 ENV.2010,4.1,2-2 265178, y del proyecto financiado por el Ministerio de Economía y Competitividad del Gobierno de España “Análisis espaciotemporal de las cubiertas del suelo y del estrés de la vegetación en la P. Ibérica a la luz de medio Siglo (1975-2025) de dinámica climática y sus anomalías (DinaCliVe)”, ref. CGL2012-33927; y ICREA Academia Excellence in Research grant (2011-2015)

Keywords

  • hybrid classification
  • Landsat
  • multivariate linear regression
  • multivariate logistic regression
  • spatial distribution of uncertainty and error

Cite this

Pons, X. ; Sevillano, E. ; Moré, G. ; Serra, P. ; Cornford, D. ; Ninyerola, M. / Distribución espacial de la incertidumbre en mapas de cubiertas obtenidos mediante teledetección. In: Revista de teledeteccion. 2014 ; No. 42. pp. 1-10.
@article{1a038eddeda24440b6da214ed5fad1f1,
title = "Distribuci{\'o}n espacial de la incertidumbre en mapas de cubiertas obtenidos mediante teledetecci{\'o}n",
abstract = "When combining remote sensing imagery with statistical classifiers to obtain categorical thematic maps it is not usual to provide data about the spatial distribution of the error and uncertainty of the resulting maps. This paper describes, in the context of GeoViQua FP7 project, feasible approaches for methods based on several steps such as hybrid classifiers. Both for “per pixel” and “per polygon” strategies, the proposal is based on the use of the available ground truth, which is used to properly model the spatial distribution of the errors. Results allow mapping the classification success with a very high level of reliability (R2>0,94), providing users a sound knowledge of the accuracy at every area of the map.",
keywords = "hybrid classification, Landsat, multivariate linear regression, multivariate logistic regression, spatial distribution of uncertainty and error",
author = "X. Pons and E. Sevillano and G. Mor{\'e} and P. Serra and D. Cornford and M. Ninyerola",
note = "Esta revista se publica bajo una Licencia Creative Commons Atribuci{\'o}n-NoComercial-SinDerivar 4.0 Internacional Funding: Comisi{\'o}n Europea “QUAlity aware VIsualisation for the Global Earth Observation system of systems (GeoViQua)”, ref. FP7 ENV.2010,4.1,2-2 265178, y del proyecto financiado por el Ministerio de Econom{\'i}a y Competitividad del Gobierno de Espa{\~n}a “An{\'a}lisis espaciotemporal de las cubiertas del suelo y del estr{\'e}s de la vegetaci{\'o}n en la P. Ib{\'e}rica a la luz de medio Siglo (1975-2025) de din{\'a}mica clim{\'a}tica y sus anomal{\'i}as (DinaCliVe)”, ref. CGL2012-33927; y ICREA Academia Excellence in Research grant (2011-2015)",
year = "2014",
month = "12",
doi = "10.4995/raet.2014.3059",
language = "Spanish",
pages = "1--10",
journal = "Revista de teledeteccion",
issn = "1133-0953",
publisher = "Asociacion Espanola de Teledeteccion",
number = "42",

}

Distribución espacial de la incertidumbre en mapas de cubiertas obtenidos mediante teledetección. / Pons, X.; Sevillano, E.; Moré, G.; Serra, P.; Cornford, D.; Ninyerola, M.

In: Revista de teledeteccion, No. 42, 12.2014, p. 1-10.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Distribución espacial de la incertidumbre en mapas de cubiertas obtenidos mediante teledetección

AU - Pons, X.

AU - Sevillano, E.

AU - Moré, G.

AU - Serra, P.

AU - Cornford, D.

AU - Ninyerola, M.

N1 - Esta revista se publica bajo una Licencia Creative Commons Atribución-NoComercial-SinDerivar 4.0 Internacional Funding: Comisión Europea “QUAlity aware VIsualisation for the Global Earth Observation system of systems (GeoViQua)”, ref. FP7 ENV.2010,4.1,2-2 265178, y del proyecto financiado por el Ministerio de Economía y Competitividad del Gobierno de España “Análisis espaciotemporal de las cubiertas del suelo y del estrés de la vegetación en la P. Ibérica a la luz de medio Siglo (1975-2025) de dinámica climática y sus anomalías (DinaCliVe)”, ref. CGL2012-33927; y ICREA Academia Excellence in Research grant (2011-2015)

PY - 2014/12

Y1 - 2014/12

N2 - When combining remote sensing imagery with statistical classifiers to obtain categorical thematic maps it is not usual to provide data about the spatial distribution of the error and uncertainty of the resulting maps. This paper describes, in the context of GeoViQua FP7 project, feasible approaches for methods based on several steps such as hybrid classifiers. Both for “per pixel” and “per polygon” strategies, the proposal is based on the use of the available ground truth, which is used to properly model the spatial distribution of the errors. Results allow mapping the classification success with a very high level of reliability (R2>0,94), providing users a sound knowledge of the accuracy at every area of the map.

AB - When combining remote sensing imagery with statistical classifiers to obtain categorical thematic maps it is not usual to provide data about the spatial distribution of the error and uncertainty of the resulting maps. This paper describes, in the context of GeoViQua FP7 project, feasible approaches for methods based on several steps such as hybrid classifiers. Both for “per pixel” and “per polygon” strategies, the proposal is based on the use of the available ground truth, which is used to properly model the spatial distribution of the errors. Results allow mapping the classification success with a very high level of reliability (R2>0,94), providing users a sound knowledge of the accuracy at every area of the map.

KW - hybrid classification

KW - Landsat

KW - multivariate linear regression

KW - multivariate logistic regression

KW - spatial distribution of uncertainty and error

UR - http://www.scopus.com/inward/record.url?scp=84918837355&partnerID=8YFLogxK

U2 - 10.4995/raet.2014.3059

DO - 10.4995/raet.2014.3059

M3 - Article

AN - SCOPUS:84918837355

SP - 1

EP - 10

JO - Revista de teledeteccion

JF - Revista de teledeteccion

SN - 1133-0953

IS - 42

ER -