Precision Agriculture

, Volume 11, Issue 6, pp 600–620 | Cite as

A comparison of different algorithms for the delineation of management zones

  • F. Guastaferro
  • A. CastrignanòEmail author
  • D. De Benedetto
  • D. Sollitto
  • A. Troccoli
  • B. Cafarelli


One approach to the application of site-specific techniques and technologies in precision agriculture is to subdivide a field into a few contiguous homogenous zones, often referred to as management zones (MZs). Delineating MZs can be based on some sort of clustering, however there is no widely accepted method. The application of fuzzy set theory to clustering has enabled researchers to account better for the continuous variation in natural phenomena. Moreover, the methods based on non-parametric density estimation can detect clusters of unequal size and dispersion. The objectives of this paper were to: (1) compare different procedures for creating management zones and (2) determine the relation of the MZs delineated with potential yield. One hundred georeferenced point measurements of soil and crop properties were obtained from a 12 ha field cropped with durum wheat for two seasons. The trial was carried out at the experimental farm of CRA-CER in Foggia (Italy). All variables were interpolated on a 1 × 1 m grid using the geostatistical techniques of kriging and cokriging. The techniques compared to identify MZs were: (1) the ISODATA method, (2) the fuzzy c-means algorithm and (3) a non-parametric density algorithm. The ISODATA method, which was the simplest, subdivided the field into three distinct classes of suitable size for uniform management, whereas the other two methods created two classes. The non-parametric density algorithm characterized the edge properties between adjacent clusters more efficiently than the fuzzy method. The clusters from the non-parametric density algorithm and yield maps for three seasons (2005–2006, 2006–2007 and 2007–2008) were compared and agreement measures were computed. The kappa coefficients for the three seasons were negative or small positive values which indicate only slight agreement. These results illustrate the importance of temporal variation in spatial variation of yield in rainfed conditions, which limits the use of the MZ approach.


Management zone (MZ) Geostatistics Clustering Fuzzy c-means Density algorithm Kappa (k) statistic 



The authors wish to thank Dr. Newell R. Kitchen and Dr. Scott T. Drummond of USDA-ARS, Cropping Syst. and Water Quality Res. Unit, Columbia, MO 65211 for their valid assistance in using MZA software.


  1. Basso, B., Bertocco, M., Sartori, L., & Martin, E. C. (2007). Analyzing the effects of climate variability on spatial of yield in a maize-wheat-soybean rotation. European Journal of Agronomy, 6, 82–91.CrossRefGoogle Scholar
  2. Basso, B., Ritchie, J. T., Pierce, F. J., Braga, R. P., & Jones, J. W. (2001). Spatial validation of crop models for precision agriculture. Agricultural Systems, 68, 97–112.CrossRefGoogle Scholar
  3. Bhatti, A. U., Mulla, D. J., Koehler, F. E., & Gurmani, A. H. (1991). Identifying and removing spatial correlation from yield experiments. Soil Science Society of America Journal, 55, 1523–1528.CrossRefGoogle Scholar
  4. Blackmore, B. S. (2000). The interpretation of trends from multiple yield maps. Computers and Electronics in Agriculture, 26, 37–51.CrossRefGoogle Scholar
  5. Boydell, B., & McBratney, A. B. (2002). Identifying potential within-field management zones from cotton-yield estimates. Precision Agriculture, 3, 9–23.CrossRefGoogle Scholar
  6. Burrough, P. A. (1989). Fuzzy mathematical methods for soil survey and land evaluation. Journal of Soil Science, 40, 477–492.CrossRefGoogle Scholar
  7. Carr, P. M., Carlson, G. R., Jacobsen, J. S., Nielsen, G. A., & Skogley, E. O. (1991). Farming soils, not fields: a strategy for increasing fertilizer profitability. Journal of Production Agriculture, 4, 57–61.Google Scholar
  8. Castrignanò, A., Basso, B., Pisante, M., Buttafuoco, G., Troccoli, A., Cucci, G., & Fiorentino, C. (2008). Delineating management zones using crop and soil variables with a multivariate geostatistic approach. In [CD-ROM] Proceedings of the 9th international conference on precision agriculture, Denver.Google Scholar
  9. Castrignanò, A., Buttafuoco, G., Pisante, M., & Lopez, N. (2006a). Estimating within-field variation using a nonparametric density algorithm. Environmetrics, 17, 465–481.CrossRefGoogle Scholar
  10. Castrignanò, A., Giugliarini, L., Risaliti, R., & Martinelli, N. (2000). Study of spatial relationships among some soil physico-chemical properties of a field in central Italy using multivariate geostatistics. Geoderma, 97, 39–60.CrossRefGoogle Scholar
  11. Castrignanò, A., Morari, F., & Morelli, G. (2006b). Assessment of spatial relationship between some soil properties and electromagnetic induction scans. In [CD-ROM] Agricultural engineering for a better world. XVI CGR world congress, Bonn (pp. 1–6). Dusseldorf, Germany: VDI Verlag GmbH. ISBN/ISSN: 3180919582.Google Scholar
  12. Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20, 37–46.CrossRefGoogle Scholar
  13. De Benedetto, D., Sollitto, D., Guastaferro, F., Castrignanò, A., & Colecchia, S. (2009). Delineation of management zones using topographical data and geophysical ECa measurements. In G. Giametta & G. Zimbaletti (Eds.), Proceedings of XXXIII CIOSTACIGR V conference 2009, technology and management to ensure sustainable agriculture, agro-systems, forestry and safety (pp. 831–835). Reggio Calabria, Italy. DISTAFA, Artemis (Italy).Google Scholar
  14. Diker, K., Heermann, D. F., & Brodahl, M. K. (2004). Frequency analysis of yield for delineating yield response zones. Precision Agriculture, 5, 435–444.CrossRefGoogle Scholar
  15. ESRI Environmental Systems Research Institute. (1994). Grid commands. Redlands, CA: ESRI.Google Scholar
  16. Fleiss, J. L. (1981). Statistical methods for rates and proportions. New York: Wiley.Google Scholar
  17. Fleming, K. L., Westfall, D. G., Wiens, D. W., & Brodah, M. C. (2000). Evaluating farmer developed management zone maps for variable rate fertilizer application. Precision Agriculture, 2, 201–215.CrossRefGoogle Scholar
  18. Fraisse, C. W., Sudduth, K. A., & Kitchen, N. R. (2001). Delineation of site-specific management zones by unsupervised classification of topographic attributes and soil electrical conductivity. Transactions of the American Society of Agricultural and Biological Engineers, 44, 155–166.Google Scholar
  19. Fridgen, J. J., Kitchen, N. R., Sudduth, K. A., Drummond, S. T., Wiebold, W. J., & Fraisse, C. W. (2004). Management Zone Analyst (MZA): Software for subfield management zone delineation. Agronomy Journal, 96, 100–108.CrossRefGoogle Scholar
  20. Gessler, P. E., Chadwick, O. A., Chamran, F., Althouse, L., & Holmes, K. (2000). Modeling soil-landscape and ecosystem properties using terrain attributes. Soil Science Society of America Journal, 64, 2046–2056.CrossRefGoogle Scholar
  21. Géovariances. (2009). Isatis Technical Ref., ver. 9.06. Geovariances & Ecole Des Mines De Paris: Avon Cedex, France.Google Scholar
  22. Gitman, I. (1973). An algorithm for nonsupervised pattern classification. IEE Transactions on Systems, Man and Cybernetics, SMC-, 3, 66–74.Google Scholar
  23. Goovaerts, P. (1997). Geostatistics for natural resources evaluation. New York: Oxford University Press.Google Scholar
  24. Hartigan, J. A., & Hartigan, M. (1985). The dip test of unimodality. Annals of Statistics, 13, 70–84.CrossRefGoogle Scholar
  25. Huizinga, D. H. (1978). A natural or mode seeking cluster analysis algorithm. Technical report 78-1. Boulder, Colorado: Behavioral Research Institute.Google Scholar
  26. Irvin, B. J., Ventura, S. J., & Slater, B. K. (1997). Fuzzy and isodata classification of landform elements from digital terrain data in Pleasant Valley, Wisconsin. Geoderma, 77, 137–154.CrossRefGoogle Scholar
  27. Johnson, R. M., & Richard, E. P. (2003). Evaluation of crop and soil spatial variability in Louisiana sugarcane production systems. In Precision agriculture [CD-ROM]. Proceedings of the 6th international conference. Minneapolis, MN: ASA, CSSA, and Madison, WI: SSSA.Google Scholar
  28. Lark, R. M. (1998). Forming spatially coherent regions by classification of multivariate data: An example from the analysis of maps of crop yield. International Journal of Geographical Information Science, 12, 83–98.CrossRefGoogle Scholar
  29. Li, Y., Shi, Z., Li, F., & Li, H. (2007). Delineation of site-specific management zones using fuzzy clustering analysis in a coastal saline land. Computers and Electronics in Agriculture, 56, 174–186.CrossRefGoogle Scholar
  30. McCann, B. L., Pennock, D. J., van Kessel, C., & Walley, F. L. (1996). The development of management units for site specific farming. In P. C. Robert et al. (Eds.), Proceedings of the 3rd international conference on precision agriculture (pp. 295–302). Madison, WI: ASA, CSSA, and SSSA.Google Scholar
  31. McNemar, Q. (1947). Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika, 12, 153–157.CrossRefPubMedGoogle Scholar
  32. Moore, I. D., Gessler, P. E., & Peterson, G. A. (1993). Soil attribute prediction using terrain analysis. Soil Science Society of America Journal, 57, 443–452.CrossRefGoogle Scholar
  33. Morari, F., Castrignanò, A., & Pagliarin, C. (2009). Application of multivariate geostatistics in delineating management zones within a gravelly vineyard using geo-electrical sensors. Computers and Electronics in Agriculture, 69, 97–107.CrossRefGoogle Scholar
  34. Moulin, A. P., Beckie, H. J., & Pennock, D. J. (1998). Strategies for variable rate nitrogen fertilization in hummocky terrain. Canadian Journal of Soil Science, 77, 589–595.Google Scholar
  35. Mulla, D. J. (1991). Using geostatistics and GIS to manage spatial patterns in soil fertility. In G. Kranzler (Ed.), Proceedings of Automated Agriculture for the 21st Century (pp. 336–345). St. Joseph, MI: SAE.Google Scholar
  36. Nolan, S. C., Goddard, T. W., & Lohstraeter, G. (2000). Assessing management units on rolling topography. In Precision agriculture [CD-ROM]. Proceedings of the 5th international conference on precision and other resource management. Madison, WI: ASA, CSSA, and SSSA.Google Scholar
  37. Odeh, I. O. A., McBratney, A. B., & Chittleborough, D. J. (1992). Soil pattern recognition with fuzzy-c-means: application to classification and soil–landform interrelationships. Soil Science Society of America Journal, 56, 505–516.CrossRefGoogle Scholar
  38. Pagliai, M. (1997). Metodi di analisi fisica del suolo (Physical methods of soil analysis). Italian Ministry of Agriculture. Milan: Franco Angeli. (in Italian).Google Scholar
  39. [RSI] Research Systems Incorporated. (1999). ENVI user’s guide. Version 3.2. Boulder, CO: RSI.Google Scholar
  40. Sarle, W. S. (1982). Cluster analysis by least squares. In Proceedings of the seventh annual SAS users group international conference (pp. 651–653). Cary, NC: SAS Institute Inc.Google Scholar
  41. SAS/STAT Software Release 9.2. (2008). Cary, NC: SAS Institute Inc.Google Scholar
  42. Scott, D. W. (1992). Multivariate density estimation: theory, practice, and visualization. New York: Wiley.CrossRefGoogle Scholar
  43. Silverman, B. W. (1986). Density estimation. New York: Chapman and Hall.Google Scholar
  44. Soil Survey Staff. (1999). Soil taxonomy (second edition). Washington, DC: USDA, National natural resources Conservation Service.Google Scholar
  45. Stafford, J. V., Lark, R. M., & Bolam, H. C. (1998). Using yield maps to regionalize fields into potential management units. In P. C. Robert et al. (Eds.), Proceedings of the 4th international conference on precision agriculture (pp. 225–237). Madison, WI: ASA, CSSA, and SSSA.Google Scholar
  46. Tou, J. T., & Gonzalez, R. C. (1974). Pattern recognition principles. Reading, MA: Addison-Wesley.Google Scholar
  47. Violante, P. (2000). Metodi di analisi chimica del suolo (Chemical methods of soil analysis), Italian Ministry of Agriculture. Milan: Franco Angeli.Google Scholar
  48. Wackernagel, H. (2003). Multivariate geostatistics: An introduction with applications (3rd ed., p. 388). Berlin: Springer Verlag.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • F. Guastaferro
    • 1
  • A. Castrignanò
    • 1
    Email author
  • D. De Benedetto
    • 1
  • D. Sollitto
    • 1
  • A. Troccoli
    • 2
  • B. Cafarelli
    • 3
  1. 1.CRA-SCA, Research Unit for Cropping Systems in Dry EnvironmentsBariItaly
  2. 2.CRA-CER, Experimental Center for the CerealsFoggiaItaly
  3. 3.Department of Economical, Mathematical and Statistical Science (DSEMS)University of FoggiaFoggiaItaly

Personalised recommendations