A multivariate spatial clustering method for partitioning tree-based orchard data into homogenous zones

A. Peeters, M. Zude, J. Kathner, M. Unlu, R. Kanber, A. Hetzroni, R. Gebbers, A. Ben-Gal

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A combined spatial-aspatial clustering approach for partitioning tree-based data in orchards was developed. The method employs the Getis-Ord Gi∗ statistic applied to the analysis of individual tree data in a grapefruit orchard located near the city of Adana, Turkey. Analyzed tree-variables included yield (total fruit weight per tree) and two possible yield-determining variables, tree size measured as tree trunk circumference (cm) and soil properties measured by the soil apparent electrical conductivity (ECa (mS/m)). Data were collected from 179 trees. The developed method was applied to the analysis of 'hot-spots' (clusters of high data values) and 'cold-spots' (clusters of low data values) in orchards and compared to the k-means clustering algorithm, an aspatial clustering method widely-used in agriculture. The combined method improved results by both discriminating among feature values as well as representing their spatial structure and therefore represents a superior technique for identifying homogenous spatial clusters in orchards. The approach can be used for delineating management zones for optimal precision management of tree crops.

Original languageEnglish
Title of host publicationPrecision Agriculture 2015 - Papers Presented at the 10th European Conference on Precision Agriculture, ECPA 2015
EditorsJohn V. Stafford
PublisherWageningen Academic Publishers
Pages233-239
Number of pages7
ISBN (Electronic)9789086862672
DOIs
StatePublished - 1 Jan 2015
Externally publishedYes
Event10th European Conference on Precision Agriculture, ECPA 2015 - Tel-Aviv, Israel
Duration: 12 Jul 201516 Jul 2015

Publication series

NamePrecision Agriculture 2015 - Papers Presented at the 10th European Conference on Precision Agriculture, ECPA 2015

Conference

Conference10th European Conference on Precision Agriculture, ECPA 2015
Country/TerritoryIsrael
CityTel-Aviv
Period12/07/1516/07/15

Keywords

  • GIS
  • Hot-spot analysis
  • K-means clustering
  • Management zones
  • Spatial clustering

ASJC Scopus subject areas

  • Agronomy and Crop Science
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'A multivariate spatial clustering method for partitioning tree-based orchard data into homogenous zones'. Together they form a unique fingerprint.

Cite this