Application of Unsupervised Clustering Techniques for Management Zone Delineation: Case Study of Variable Rate Irrigation in Southern Alberta, Canada
Publication: Journal of Irrigation and Drainage Engineering
Volume 142, Issue 1
Abstract
Sustainable water management is paramount to effective and efficient irrigation water management. Over decades, excessive irrigation water application has caused erosion, poor crop quality, water logging, salinity, and wastage of scarce water resources. Variable rate irrigation (VRI) is a recent technique that aids the application of irrigation water according to crop needs and soil physical and chemical properties. A challenge in applying VRI is the determination of appropriate water management zones (MZs). Two software and associated clustering techniques stand out as the best in determining the optimal number of MZs: management zone analyst (MZA), based on a fuzzy c-means algorithm, and regionalization with constrained clustering and partitioning (REDCAP), based on combinatorial graph theory. This study assesses the two techniques for VRI application on a 44 ha field in southern Alberta, Canada, using electrical conductivity (EC) and land elevation. Wedges of 8° and 24° generated the same number of optimal MZ classifications, although the heterogeneities in the 8° wedges were greater than those for the 24° wedges, although it seems that using 24° wedges may mask soil properties, such as the apparent soil EC or elevation, that are critical to crop productivity and efficient water application; however, in terms of costs, in this field, 24° wedges with MZA software appear to be the optimal solution. This study highlights the effectiveness of the two techniques and shows how they can be used to create or classify MZs for VRI.
Get full access to this article
View all available purchase options and get full access to this article.
References
AAFRD and IJC (Alberta Agriculture, Food and Rural Development and International Joint Commission). (1984). “Irrigation development in Alberta water use and impact on regional development. St. Mary River and “Southern Tributaries” watersheds.” 〈http://www.ijc.org/rel/pdf/83_stmary-milk_letter.pdf〉 (Jul. 11, 2013).
Assuncao, R. M., Neves, M. C., Cao Mara, A. G., and Freitas, C. D. C. (2006). “Efficient regionalization techniques for socio-economic geographical units using minimum spanning trees.” Int. J. Geograph. Inf. Sci., 20(7), 797–811.
Benassi, F., and Ferrara, R. (2010). “Regionalization with dynamically constrained agglomerative clustering and partitioning. An application on spatial segregation of foreign population in Italy at regional level.” Italian Statistical Society (SIS), Univ. of Padue, Italy.
Bereuter, A. M. (2011). “Management zone delineation techniques on irrigated corn in Nebraska.” 〈http://digitalcommons.unl.edu/agronhortdiss/40〉 (Jun. 1, 2013).
Bezdek, J. C. (1981). Pattern recognition with fuzzy objective function algorithms, Plenum, New York.
Boluwade, A., and Madramootoo, C. A. (2013). “Modeling the impacts of spatial heterogeneity in the castor watershed on runoff, sediment and phosphorus loss using SWAT. I: Impacts of spatial variability of soil properties.” Water Air Soil Pollut., 224(10), 1692.
Boydell, B., and McBratney, A. B. (1999). “Identifying potential within field management zones from cotton yield estimates.” Proc., 2nd Int. Society of Precision Agriculture (ISPA), Monticello, IL, 331–341.
Chiericati, M., Morari, F., Sartori, L., Ortiz, B., Perry, C., and Vellidis, G. (2007). “Delineating management zones to apply site-specific irrigation in the Venice lagoon watershed.” Precision Agriculture ’07. Int. Society of Precision Agriculture (ISPA), J. V. Stafford, ed., Monticello, IL, 599–605.
Fridgen, J. J. (2000). “Development and evaluation of unsupervised clus tering software for sub-field delineation of agricultural fields.” M.S. thesis, Univ. of Missouri, Columbia, MO.
Fridgen, J. J., Kitchen, N. R., Sudduth, K. A., Drummond, S. T., Wiebold, W. J., and Fraisse, C. W. (2004). “Management zone analyst (MZA): Software for subfield management zone delineation.” Agron. J., 96(1), 100–108.
FuzME version 3.5c [Computer software]. Australia, Precision Agricultural Lab, Univ. of Sydney.
Guo, D. (2008). “Regionalization with dynamically constrained agglomerative clustering and partitioning.” Int. J. Geograph. Inf. Sci., 22(7), 801–823.
Irvin, B. J., Ventura, S. J., and Slater, B. K. (1997). “Fuzzy and isodata classification of landform elements from digital terrain data in Pleasant Valley, Wisconsin.” Geoderma, 77(2–4), 137–154.
Jensen, J. R. (1996). Introductory digital image processing: A remote sensing perspective, Prentice Hall, Upper Saddle River, NJ.
Kwiatkowski, J., and Pittman, J. (1997). “Salinity mapping for resource management within the M.D. of Taber, Alberta.” 〈http://www1.agric.gov.ab.ca/$department/deptdocs.nsf/all/sag3268/$FILE/taber.pdf〉 (Jul. 11, 2013).
Management Zone Analyst (MZA) version 1.0 [Computer software]. Columbia, MO, U.S. Dept. of Agriculture (USDA-ARS).
Mausel, P. W., Kamber, W. J., and Lee, J. K. (1990). “Optimum band selection for supervised classification of multispectral data.” Photogramm. Eng. Remote Sens., 56, 55–60.
Minasny, B., and McBratney, A. B. (2002). “FuzME version 3.0, Australian Centre for Precision Agriculture.” Univ. of Sydney, Sydney, Australia.
Odeh, I. O. A., McBratney, A. B., and Chittleborough, D. J. (1992). “Soil pattern recognition with fuzzy-c-means: Application to classification and soil-landform interrelationships.” Soil Sci. Soc. Am. J., 56(2), 505–516.
REDCAP [Computer software]. Columbia, SC, Dept. of Geography, Univ. of South Carolina.
Sadler, E. J., Evans, R. G., Buchleiter, G. W., King, B. A., and Camp, C. R. (2000). “Design considerations for site specific irrigation.” USDA-ARS, Florence, SC.
Information & Authors
Information
Published In
Copyright
© 2015 American Society of Civil Engineers.
History
Received: Jun 7, 2014
Accepted: Jun 15, 2015
Published online: Aug 5, 2015
Published in print: Jan 1, 2016
Discussion open until: Jan 5, 2016
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.