Neural Network Model for Land Cover Classification from Satellite Images

Land cover data represent environmental information for a variety of scientific and policy applications, so its classification from satellite images is important. Since neural networks (NN) do not require a hypothesis about data distribution, they are valuable tools to classify satellite images. The...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bocco,Mónica, Ovando,Gustavo, Sayago,Silvina, Willington,Enrique
Lenguaje:	English
Publicado:	Instituto de Investigaciones Agropecuarias, INIA 2007
Materias:	modeling back-propagation neural networks remote sensing crops-bare soil
Acceso en línea:	http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0365-28072007000400009
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:scielo:S0365-28072007000400009
record_format	dspace
spelling	oai:scielo:S0365-280720070004000092009-01-06Neural Network Model for Land Cover Classification from Satellite ImagesBocco,MónicaOvando,GustavoSayago,SilvinaWillington,Enrique modeling back-propagation neural networks remote sensing crops-bare soil Land cover data represent environmental information for a variety of scientific and policy applications, so its classification from satellite images is important. Since neural networks (NN) do not require a hypothesis about data distribution, they are valuable tools to classify satellite images. The objectives of this work were to develop NN models to classify land cover data from information from satellite images and to evaluate them when different input variables are used. MODIS-MYD13Q1 satellite images and data of 85 plots in Córdoba, Argentina, were used. Five NN models of multi-layer feed-forward perceptron were designed. Four of these received NDVI (Normalized Difference Vegetation Index), EVI (Enhanced Vegetation Index), red (RED) and near infrared (NIR) reflectance values as input patterns, respectively. The fifth NN had RED and NIR reflectances as input values. By comparing the information taken in the field and the classification made during the validation phase, it can be concluded that all models presented good performance in the classification. The model that shows better behavior is the one that jointly considers RED and NIR reflectance as input; this model shows an overall classification accuracy of 93% and an excellent Kappa statistic. The networks constructed with NDVI and EVI values have a similar behavior (86 and 83% accuracy, respectively). The Kappa statistics correspond to the categories of very good and good, respectively. The networks including only RED or NIR reflectance values get the lowest accuracy results (76 and 81%, respectively) and Kappa values within fair and good ranks, respectively.info:eu-repo/semantics/openAccessInstituto de Investigaciones Agropecuarias, INIAAgricultura Técnica v.67 n.4 20072007-12-01text/htmlhttp://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0365-28072007000400009en10.4067/S0365-28072007000400009
institution	Scielo Chile
collection	Scielo Chile
language	English
topic	modeling back-propagation neural networks remote sensing crops-bare soil
spellingShingle	modeling back-propagation neural networks remote sensing crops-bare soil Bocco,Mónica Ovando,Gustavo Sayago,Silvina Willington,Enrique Neural Network Model for Land Cover Classification from Satellite Images
description	Land cover data represent environmental information for a variety of scientific and policy applications, so its classification from satellite images is important. Since neural networks (NN) do not require a hypothesis about data distribution, they are valuable tools to classify satellite images. The objectives of this work were to develop NN models to classify land cover data from information from satellite images and to evaluate them when different input variables are used. MODIS-MYD13Q1 satellite images and data of 85 plots in Córdoba, Argentina, were used. Five NN models of multi-layer feed-forward perceptron were designed. Four of these received NDVI (Normalized Difference Vegetation Index), EVI (Enhanced Vegetation Index), red (RED) and near infrared (NIR) reflectance values as input patterns, respectively. The fifth NN had RED and NIR reflectances as input values. By comparing the information taken in the field and the classification made during the validation phase, it can be concluded that all models presented good performance in the classification. The model that shows better behavior is the one that jointly considers RED and NIR reflectance as input; this model shows an overall classification accuracy of 93% and an excellent Kappa statistic. The networks constructed with NDVI and EVI values have a similar behavior (86 and 83% accuracy, respectively). The Kappa statistics correspond to the categories of very good and good, respectively. The networks including only RED or NIR reflectance values get the lowest accuracy results (76 and 81%, respectively) and Kappa values within fair and good ranks, respectively.
author	Bocco,Mónica Ovando,Gustavo Sayago,Silvina Willington,Enrique
author_facet	Bocco,Mónica Ovando,Gustavo Sayago,Silvina Willington,Enrique
author_sort	Bocco,Mónica
title	Neural Network Model for Land Cover Classification from Satellite Images
title_short	Neural Network Model for Land Cover Classification from Satellite Images
title_full	Neural Network Model for Land Cover Classification from Satellite Images
title_fullStr	Neural Network Model for Land Cover Classification from Satellite Images
title_full_unstemmed	Neural Network Model for Land Cover Classification from Satellite Images
title_sort	neural network model for land cover classification from satellite images
publisher	Instituto de Investigaciones Agropecuarias, INIA
publishDate	2007
url	http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0365-28072007000400009
work_keys_str_mv	AT boccomonica neuralnetworkmodelforlandcoverclassificationfromsatelliteimages AT ovandogustavo neuralnetworkmodelforlandcoverclassificationfromsatelliteimages AT sayagosilvina neuralnetworkmodelforlandcoverclassificationfromsatelliteimages AT willingtonenrique neuralnetworkmodelforlandcoverclassificationfromsatelliteimages
_version_	1718438074490290176

Neural Network Model for Land Cover Classification from Satellite Images

Ejemplares similares