Getis-Ord's hot- and cold-spot statistics as a basis for multivariate spatial clustering of orchard tree data

We propose a multivariate spatial clustering approach for partitioning orchard data.Data is spatially scaled by Getis-Ord GiÂ? statistic, followed by k-means clustering.Trees are discriminated into spatially homogeneous groups.Feasibility and performance were assessed in comparison to k-means clustering.Results improved cluster discrimination and representation of spatial structure. Precision agriculture aims at sustainably optimizing the management of cultivated fields by addressing the spatial variability found in crops and their environment. Spatial variability can be evaluated using spatial cluster analysis, which partitions data into homogeneous groups, considering the geographical location of features and their spatial relationships. Spatial clustering methods evaluate the degree of spatial autocorrelation between features and quantify the statistical significance of identified clusters. Clustering of orchard data calls for an approach which is based on modeling point data, i.e. individual trees, which can be related to site-specific measurements. We present and evaluate a spatial clustering method using the Getis-Ord GiÂ? statistic to the analysis of tree-based data in an experimental orchard. We examine the robustness of this method for the analysis of "hot-spots" (clusters of high data values) and "cold-spots" (clusters of low data values) in orchards and compare it to the k-means clustering algorithm, a widely-used aspatial method. We then present a novel approach which accounts for the spatial structure of data in a multivariate cluster analysis by combining the spatial Getis-Ord GiÂ? statistic with k-means multivariate clustering. The combined method improved results by both discriminating among features values as well as representing their spatial structure and therefore represents a superior technique for identifying homogenous spatial clusters in orchards. This approach can be used as a tool for precision management of orchards by partitioning trees into management zones.

[1]  M. C. Cooper,et al.  The effect of measurement error on determining the number of clusters in clusteranalysis , 1988 .

[2]  A. Getis.  The Analysis of Spatial Association by Use of Distance Statistics , 2010 .

[3]  Brigitte Charnomordic,et al.  A segmentation algorithm for the delineation of agricultural management zones , 2010 .

[4]  Clyde W. Fraisse,et al.  Delineation of Site-Specific Management Zones by Unsupervised Classification of Topographic Attributes and Soil Electrical Conductivity , 2001 .

[5]  Victor Alchanatis,et al.  Spatial–spectral processing strategies for detection of salinity effects in cauliflower, aubergine and kohlrabi , 2013 .

[6]  L. Anselin.  Local Indicators of Spatial Association—LISA , 2010 .

[7]  A. W. Schumann,et al.  Delineating productivity zones in a citrus grove using citrus production, tree growth and temporally stable soil data , 2011, Precision Agriculture.

[8]  Ofer Levi,et al.  Combining spectral and spatial information from aerial hyperspectral images for delineating homogenous management zones , 2013 .

[9]  Kenneth A. Sudduth,et al.  Soil electrical conductivity and topography related to yield for three contrasting soil-crop systems , 2003 .

[10]  Michel Dabas,et al.  Comparison of instruments for geoelectrical soil mapping at the field scale , 2009 .

[11]  Theofanis Gemtos,et al.  Delineation of management zones in an apple orchard in Greece using a multivariate approach , 2013 .

[12]  Mónica Balzarini,et al.  Subfield management class delineation using cluster analysis from spatial principal components of soil variables , 2013 .

[13]  Arnold W. Schumann,et al.  Nutrient Management Zones for Citrus Based on Variation in Soil Properties and Tree Performance , 2006, Precision Agriculture.

[14]  A. Castrignanò,et al.  A comparison of different algorithms for the delineation of management zones , 2010, Precision Agriculture.

[15]  A. D. Gordon.  A survey of constrained classification , 1996 .

[16]  Josse De Baerdemaeker,et al.  Key soil and topographic properties to delineate potential management classes for precision agriculture in the European loess area , 2008 .

[17]  Yafit Cohen,et al.  Modified Hot-Spot analysis for spatio-temporalanalysis: a case study of the leaf-roll virus expansion in vineyards , 2011 .

[18]  T. A. Gemtos,et al.  Spatial variation in yield and quality in a small apple orchard , 2010, Precision Agriculture.

[19]  Zhou Shi,et al.  Delineation of site-specific management zones using fuzzy clustering analysis in a coastal saline land , 2007 .

[20]  Robert Haining,et al.  Spatial Data Analysis: Theory and Practice , 2003 .

[21]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[22]  Slobodan Ribarić,et al.  Introduction to Pattern Recognition , 1988 .

[23]  R. M. Lark,et al.  Forming Spatially Coherent Regions by Classification of Multi-Variate Data: An Example from the Analysis of Maps of Crop Yield , 1998, Int. J. Geogr. Inf. Sci..

[24]  A. Mitchell.  The ESRI guide to GIS analysis , 1999 .

[25]  Qiang Fu,et al.  Delineating soil nutrient management zones based on fuzzy clustering optimized by PSO , 2010, Math. Comput. Model..

[26]  Alan R. Orpin,et al.  Towards a statistically valid method of textural sea floor characterization of benthic habitats , 2006 .

[27]  D. Westfall,et al.  Evaluating Farmer Defined Management Zone Maps for Variable Rate Fertilizer Application , 2000, Precision Agriculture.

[28]  Kenneth A. Sudduth,et al.  Soil Electrical Conductivity as a Crop Productivity Measure for Claypan Soils , 1999 .

[29]  M. R. Neishabouri,et al.  Delineation of site specific nutrient management zones for a paddy cultivated area based on soil fertility using fuzzy clustering , 2012 .

[30]  Uri Yermiyahu,et al.  Spatial distribution of water status in irrigated olive orchards by thermal imaging , 2013, Precision Agriculture.

[31]  G. W. Milligan,et al.  An examination of procedures for determining the number of clusters in a data set , 1985 .

[32]  Noel A Cressie,et al.  Statistics for Spatio-Temporal Data , 2011 .

[33]  J. Ord,et al.  Local Spatial Autocorrelation Statistics: Distributional Issues and an Application , 2010 .

[34]  Pierre Chopin,et al.  Assessment of regional variability in crop yields with spatial autocorrelation: Banana farms and policy implications in Martinique , 2013 .

[35]  T. Caliński,et al.  A dendrite method for cluster analysis , 1974 .

[36]  R. Gebbers,et al.  Electrical conductivity mapping for precision farming , 2009 .

[37]  Geoffrey H. Ball,et al.  ISODATA, A NOVEL METHOD OF DATA ANALYSIS AND PATTERN CLASSIFICATION , 1965 .

[38]  Yafit Cohen,et al.  Effect of elevation on spatio‐temporal patterns of olive fly (Bactrocera oleae) populations in northern Greece , 2008 .

[39]  Clyde W. Fraisse,et al.  Management Zone Analyst (MZA) , 2004, Agronomy Journal.

[40]  A. Castrignanò,et al.  Spatio-temporal population dynamics and area-wide delineation of Bactrocera oleae monitoring zones using multi-variate geostatistics , 2012, Precision Agriculture.

[41]  Achim Dobermann,et al.  Creating Spatially Contiguous Yield Classes for Site‐Specific Management , 2003 .

[42]  Rodrigo Ortega,et al.  Determination of management zones in corn (Zea mays L.) based on soil fertility , 2007 .

[43]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2010, Pattern Recognit. Lett..

[44]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[45]  Robert Haining,et al.  Spatial data analysis , 2003 .

[46]  Panos M. Pardalos,et al.  Data Mining in Agriculture , 2008 .

[47]  Sergios Theodoridis,et al.  Introduction to Pattern Recognition: A Matlab Approach , 2010 .

[48]  F. J. Pierce,et al.  Spatial variation in tree characteristics and yield in a pear orchard , 2010, Precision Agriculture.

[49]  Dennis L. Corwin,et al.  Editorial: Applications of apparent soil electrical conductivity in precision agriculture , 2005 .

[50]  Kenneth A. Sudduth,et al.  Delineating productivity zones on claypan soil fields using apparent soil electrical conductivity , 2005 .