Clustering of grape yield maps to delineate site-specific management zones

Abstract

Zonal management in vineyards requires the prior delineation of stable yield zones within the parcel. Among the different methodologies used for zone delineation, cluster analysis of yield data from several years is one of the possibilities cited in scientific literature. However, there exist reasonable doubts concerning the cluster algorithm to be used and the number of zones that have to be delineated within a field. In this paper two different cluster algorithms have been compared (k-means and fuzzy c-means) using the grape yield data corresponding to three successive years (2002, 2003 and 2004), for a 'Pinot Noir' vineyard parcel. Final choice of the most recommendable algorithm has been linked to obtaining a stable pattern of spatial yield distribution and to allowing for the delineation of compact and average sized areas. The general recommendation is to use reclassified maps of two clusters or yield classes (low yield zone and high yield zone) and, consequently, the site-specific vineyard management should be based on the prior delineation of just two different zones or sub-parcels. The two tested algorithms are good options for this purpose. However, the fuzzy c-means algorithm allows for a better zoning of the parcel, forming more compact areas and with more equilibrated zonal differences over time.Additional key words: cluster analysis; fuzzy c-means algorithm; grape yield maps; k-means algorithm; precision viticulture; zonal management. ResumenAnálisis cluster de mapas de vendimia para la delimitación de zonas de manejo diferencial El manejo zonal en viña requiere la delimitación previa de zonas estables de cosecha dentro de la parcela. Entre los diferentes métodos de zonificación existentes, el análisis cluster de los datos de cosecha de diferentes años es una de las posibilidades que han sido citadas en la literatura científica. Sin embargo, existen dudas razonables en relación al algoritmo que debe ser utilizado y al número de zonas que deben delimitarse dentro de la parcela. En este artículo se comparan dos algoritmos diferentes de clasificación (algoritmo de k-medias y algoritmo difuso de c-medias), a partir de los datos de cosecha (mapas de cosecha) correspondientes a tres años sucesivos de vendimia (2002, 2003 y 2004) en una parcela de uva 'Pinot Noir'. La elección final del método (algoritmo) ha estado vinculada a la obtención de un patrón de cosecha estable en el tiempo y a la delimitación dentro de la parcela de zonas compactas y de cierto tamaño. La recomendación general es la utilización de mapas reclasificados en dos clases de cosecha (zona de cosecha baja y zona de cosecha alta) y, en consecuencia, el manejo sitio-específico en viña debería estar basado en la delimitación previa de únicamente dos zonas diferentes o subparcelas. Los dos algoritmos evaluados son una buena opción para este propósito. Con todo, el algoritmo difuso de c-medias permite una mejor zonificación de la parcela, formando áreas que, siendo más compactas en superficie, mantienen asimismo mejor equilibradas l...

Vine vigor, yield and grape quality assessment by airborne remote sensing over three years: Analysis of unexpected relationships in cv. Tempranillo

“…In order to avoid the influence of the light intensity reflected by objects (whether they are shadowed or fully exposed), other normalised indexes have been developed, such as the Normalized Difference Vegetation Index (NDVI). Since this ratio diminishes atmospheric and luminous variations, it is very convenient in multi-temporal studies (Fischer, 1994) Several studies demonstrate that NDVI can provide information not only about vine vegetative status, but about yield and grape composition, pH, acidity, sugar content or phenolic compounds (Lamb et al, 2004;Arnó et al, 2011;Fiorillo et al, 2012;Martínez-Casasnovas et al, 2012). Nevertheless, latest technology developments have improved the spectral resolu-3 Vine vigor, yield and grape quality by airborne remote sensing of lens light fall-off and variable pixel response.…”

Use of Farmer Knowledge in the Delineation of Potential Management Zones in Precision Agriculture: A Case Study in Maize (Zea mays L.)

“…To identify and delineate PMZs, information about the yield variation pattern is a good starting point [11]. When yield maps are not available, this delineation is usually performed on the basis of other related (proxy) parameters such as remote sensing multispectral indices, soil mapping units, apparent soil electrical conductivity (ECa), or topography, among others [12,13].…”

Redundant variables and the quality of management zones

“…The MZs that belonged to different classes were 01-CuSiAlCl, 02-CuSiAl, 03-CuSi, 04-Cu, 05-CuSiCl, 06-CuAlCl, 07-SiAlCl, 08-CuAl, 09-CuCl and 12-ClAl. ARNO et al (2011) also determined by ANOVA that differences in yield were evident only when the field was subdivided into two MZs. As shown in Figure 8, none of the MZs exhibited RE values less than one.…”

“…These indices have been applied in studies related to PA (MOLIN & CASTRO, 2008;FU et al, 2010;GUASTAFERRO et al, 2010;ARNO et al, 2011). The cluster class (MZ) with the greatest differentiation was the one in which these two indices reached approximately the minimum in each design.…”