DEFINITION OF MANAGEMENT ZONES FROM MAPS OF ELECTRICAL CONDUCTIVITY AND ORGANIC MATTER

作者：de Freitas Alves Sueli Martins; de Alcantara Gracielly Ribeiro; dos Reis Elton Fialho; de Queiroz Daniel Marcal; Magalhaes Valente Domingos Savio

来源：Bioscience Journal, 2013, 29(1): 104-114.

• Geostatistics
• Precision Agriculture
• Kappa test
• Fuzzy k-means algorithm

This study aimed to define management zones based on spatial variability of soil apparent electrical conductivity and organic matter in areas of tillage. To characterize the spatial geostatistical methods were used. Proven spatial dependence was prepared thematic maps through kriging. For delineation of management zones based on maps of variability was interpolated using the Fuzzy K-means algorithm and to define the optimal number of classes was determined Fuzzy performance index and entropy of the partition changed. The variables used for defining management zones were altitude, the electrical conductivity at 20 cm and 40 cm depth and organic matter. From these seven variables were generated maps of management zones, and later by the Kappa test was analyzed the correlation between the maps generated by the management zones and maps of the physical and chemical properties of soil. As a result there was an optimum number of classes equal to two, with the attributes related to soil texture management zone maps from organic matter or electrical conductivity and the chemical zone management from maps of organic matter or organic matter and altitude showed better results in their classification. The management zones defined from the electrical conductivity at 20 cm allowed us to detect significant differences between the average yield of soybean.

• 出版日期2013-2