Identification of site-specific management zones from combination of soil variables

Identification of site-specific management zones from combination of soil variables

Site-specific management demands the identification of homogeneous subfield regions within the field or management zones (ZM). However, due to the spatial variability of soil variables, determination of ZM from several variables, is often complex. Although the zonification or delimitation of MZ may...

Descripción completa

Detalles Bibliográficos
Autores principales: Córdoba, Mariano, Balzarini, Mónica, Bruno, Cecilia, Costa, José Luis
Formato: article
Lenguaje:Español
Publicado: ‎‎Corporación colombiana de investigación agropecuaria - AGROSAVIA 2019
Materias:
Transversal
Acceso en línea:http://revistacta.agrosavia.co/index.php/revista/article/view/239
http://hdl.handle.net/20.500.12324/35122
id RepoAGROSAVIA35122
record_format dspace
institution Corporación Colombiana de Investigación Agropecuaria
collection Repositorio AGROSAVIA
language Español
topic Transversal
spellingShingle Transversal
Córdoba, Mariano
Balzarini, Mónica
Bruno, Cecilia
Costa, José Luis
Identification of site-specific management zones from combination of soil variables
description Site-specific management demands the identification of homogeneous subfield regions within the field or management zones (ZM). However, due to the spatial variability of soil variables, determination of ZM from several variables, is often complex. Although the zonification or delimitation of MZ may be univariate, it is more appropriate to consider all variables simultaneously. Fuzzy k-means clustering (KM) and principal component analysis (PCA) are multivariate analyses that have been used for zonification. Nevertheless, PCA and KM have not been explicitly developed for georeferenced data. Novel versions of PCA, known as Multispati-PCA (PCAe), incorporate spatial autocorrelation among data of neighbor sites of regionalized variables. The objective of this study was to propose a new analytical tool to identify homogeneous zones from the combination of KM and PCAe on multiple soil variable data. The performance of proposed method was assessed through comparison of the average yields obtained in each zone delimited by combination of KM with PCA, as well as KM on the original variables and the new proposed method KM-PCAe. The results showed that KM-PCAe was the only method able to identify zones statistically different in terms of production potential. PCAe and its combination with KM are useful tools to map spatial variability and to identify ZM within fields from georeferenced data  
format article
author Córdoba, Mariano
Balzarini, Mónica
Bruno, Cecilia
Costa, José Luis
author_facet Córdoba, Mariano
Balzarini, Mónica
Bruno, Cecilia
Costa, José Luis
author_sort Córdoba, Mariano
title Identification of site-specific management zones from combination of soil variables
title_short Identification of site-specific management zones from combination of soil variables
title_full Identification of site-specific management zones from combination of soil variables
title_fullStr Identification of site-specific management zones from combination of soil variables
title_full_unstemmed Identification of site-specific management zones from combination of soil variables
title_sort identification of site-specific management zones from combination of soil variables
publisher ‎‎Corporación colombiana de investigación agropecuaria - AGROSAVIA
publishDate 2019
url http://revistacta.agrosavia.co/index.php/revista/article/view/239
http://hdl.handle.net/20.500.12324/35122
work_keys_str_mv AT cordobamariano identificationofsitespecificmanagementzonesfromcombinationofsoilvariables
AT balzarinimonica identificationofsitespecificmanagementzonesfromcombinationofsoilvariables
AT brunocecilia identificationofsitespecificmanagementzonesfromcombinationofsoilvariables
AT costajoseluis identificationofsitespecificmanagementzonesfromcombinationofsoilvariables
AT cordobamariano identificaciondezonasdemanejositioespecificoapartirdelacombinaciondevariablesdesuelo
AT balzarinimonica identificaciondezonasdemanejositioespecificoapartirdelacombinaciondevariablesdesuelo
AT brunocecilia identificaciondezonasdemanejositioespecificoapartirdelacombinaciondevariablesdesuelo
AT costajoseluis identificaciondezonasdemanejositioespecificoapartirdelacombinaciondevariablesdesuelo
_version_ 1808104950531620864
spelling RepoAGROSAVIA351222023-10-18T19:10:49Z Identification of site-specific management zones from combination of soil variables Identificación de zonas de manejo sitio-específico a partir de la combinación de variables de suelo Córdoba, Mariano Balzarini, Mónica Bruno, Cecilia Costa, José Luis Transversal Site-specific management demands the identification of homogeneous subfield regions within the field or management zones (ZM). However, due to the spatial variability of soil variables, determination of ZM from several variables, is often complex. Although the zonification or delimitation of MZ may be univariate, it is more appropriate to consider all variables simultaneously. Fuzzy k-means clustering (KM) and principal component analysis (PCA) are multivariate analyses that have been used for zonification. Nevertheless, PCA and KM have not been explicitly developed for georeferenced data. Novel versions of PCA, known as Multispati-PCA (PCAe), incorporate spatial autocorrelation among data of neighbor sites of regionalized variables. The objective of this study was to propose a new analytical tool to identify homogeneous zones from the combination of KM and PCAe on multiple soil variable data. The performance of proposed method was assessed through comparison of the average yields obtained in each zone delimited by combination of KM with PCA, as well as KM on the original variables and the new proposed method KM-PCAe. The results showed that KM-PCAe was the only method able to identify zones statistically different in terms of production potential. PCAe and its combination with KM are useful tools to map spatial variability and to identify ZM within fields from georeferenced data   El manejo sitio-específico demanda la identificación de sub-regiones homogéneas, o zonas de manejo (ZM), dentro del espacio productivo. Sin embargo, definir ZM suele ser complejo debido a que la variabilidad espacial del suelo puede depender de varias variables. La zonificación o delimitación de ZM puede realizarse utilizando una variable de suelo a la vez o considerando varias variables simultáneamente. Entre los métodos de análisis multivariado, difundido para la zonificación, se encuentra el análisis de conglomerados fuzzy k-means (KM) y el análisis de componentes principales (PCA). No obstante, como otros métodos multivariados, éstos no han sido desarrollados específicamente para datos georreferenciados. Una nueva versión del PCA, conocido como MULTISPATI-PCA (PCAe), permite contemplar la autocorrelación espacial entre datos de variables regionalizadas. El objetivo de este estudio fue proponer una nueva estrategia de análisis para la identificación de ZM, combinando la aplicación KM y PCAe sobre datos de múltiples variables de suelo. La capacidad del método propuesto se evaluó en base a la comparación de los rendimientos promedios alcanzados en cada zona delimitada, tanto para la combinación de KM con PCA, la aplicación tradicional de KM sobre las variables originales y la nueva propuesta KM-PCAe. Los resultados mostraron que KM-PCAe fue el único método que permitió distinguir zonas estadísticamente diferentes en cuanto al potencial productivo. Se concluye que la combinación propuesta constituye una herramienta importante para el mapeo de la variabilidad espacial y la identificación de ZM a partir de datos georreferenciados.    2019-08-09T19:29:57Z 2019-08-09T19:29:57Z 2012 article Artículo científico http://purl.org/coar/resource_type/c_2df8fbb1 info:eu-repo/semantics/article https://purl.org/redcol/resource_type/ART http://purl.org/coar/version/c_970fb48d4fbd8a85 http://revistacta.agrosavia.co/index.php/revista/article/view/239 10.21930/rcta.vol13_num1_art:239 http://hdl.handle.net/20.500.12324/35122 reponame:Biblioteca Digital Agropecuaria de Colombia repourl:https://repository.agrosavia.co instname:Corporación colombiana de investigación agropecuaria AGROSAVIA spa http://revistacta.agrosavia.co/index.php/revista/article/view/239/244 Attribution-NonCommercial-ShareAlike 4.0 International http://creativecommons.org/licenses/by-nc-sa/4.0/ info:eu-repo/semantics/openAccess application/pdf application/pdf ‎‎Corporación colombiana de investigación agropecuaria - AGROSAVIA Revista Ciencia y Tecnología Agropecuaria; Vol 13 No 1 (2012); 47-54

Ejemplares similares