Modeling zone management in precision agriculture through Fuzzy C-Means technique at spatial database

Predict the optimal number of zones to manage tasks evolved in precision agriculture applications is challenging issue in classification tasks. Important decisions in the farm required maps of yield classes which contain relative large, similar and spatially contiguous partitions and sometimes without a priori knowledge of the field. The main goal of this study was to apply Fuzzy C-means (FCM), an unsupervised classification technique, in a geo-referenced yield and grain moisture dataset in order to find optimal number for homogeneous zones. Those data were produced by Long-Term Ecological Research in a Biological Station (KBS-LTER), Michigan, during growing season at 2008. The best results presented by this algorithm ranged from 8 to 10 zones which were validated using the indexes Partition Coefficient (PC), Classification Entropy (CE) and Dunn’s Index (DI). Even though, only two attributes were collected in the dataset, the Fuzzy C-means has shown promissing results for zone mapping.

[1]  Peter A. Burrough,et al.  Fuzzy mathematical methods for soil survey and land evaluation , 1989 .

[2]  Lijian Shi,et al.  Zone mapping application for precision-farming: a decision support tool for variable rate application , 2010, Precision Agriculture.

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

[4]  János Abonyi,et al.  Fuzzy Clustering Based Segmentation of Time-Series , 2003, IDA.

[5]  J. Bezdek,et al.  FCM: The fuzzy c-means clustering algorithm , 1984 .

[6]  Yubin Lan,et al.  Review: Development of soft computing and applications in agricultural and biological engineering , 2010 .

[7]  Y. Huanga,et al.  Development of soft computing and applications in agricultural and biological engineering , 2010 .

[8]  R. Lark,et al.  Classification as a first step in the interpretation of temporal and spatial variation of crop yield , 1997 .

[9]  Hermann Auernhammer,et al.  Precision farming — the environmental challenge , 2001 .

[10]  G. P. Robertson,et al.  Temporal Yield Variability under Conventional and Alternative Management Systems , 2007 .

[11]  A. B. McBratney,et al.  Identifying Potential Within-Field Management Zones from Cotton-Yield Estimates , 2002, Precision Agriculture.

[12]  C. Fraisse,et al.  Management Zone Analyst ( MZA ) : Software for Subfield Management Zone Delineation , 2003 .

[13]  A. Burak Göktepe,et al.  Soil clustering by fuzzy c-means algorithm , 2005, Adv. Eng. Softw..

[14]  H. D. Cheng,et al.  Threshold selection based on fuzzy c-partition entropy approach , 1998, Pattern Recognit..

[15]  Noel A Cressie,et al.  Statistics for Spatial Data, Revised Edition. , 1994 .

[16]  David Lamb,et al.  PA—Precision Agriculture: Remote-Sensing and Mapping of Weeds in Crops , 2001 .

[17]  Alex B. McBratney,et al.  Soil pattern recognition with fuzzy-c-means : application to classification and soil-landform interrelationships , 1992 .

[18]  E. Trauwaert.  On the meaning of Dunn's partition coefficient for fuzzy clusters , 1988 .

[19]  R. V. Rossel,et al.  Spatial prediction for precision agriculture , 1996 .

[20]  Michael Edward Hohn,et al.  An Introduction to Applied Geostatistics: by Edward H. Isaaks and R. Mohan Srivastava, 1989, Oxford University Press, New York, 561 p., ISBN 0-19-505012-6, ISBN 0-19-505013-4 (paperback), $55.00 cloth, $35.00 paper (US) , 1991 .