Two approach comparison to define crop management zones (MZs)
Author(s) -
Schenatto Kelyn,
Godoy de Souza Eduardo,
Cláudio Leones Bazzi,
Nelson Miguel Betzek,
Gavioli Alan
Publication year - 2016
Publication title -
african journal of agricultural research
Language(s) - English
Resource type - Journals
ISSN - 1991-637X
DOI - 10.5897/ajar2016.11453
Subject(s) - autocorrelation , fuzzy logic , field (mathematics) , precision agriculture , cluster analysis , mathematics , agriculture , statistics , agricultural engineering , computer science , geography , engineering , artificial intelligence , archaeology , pure mathematics
The use of yield-level management zones (MZs) has demonstrated high potential for site-specific management of crop inputs in traditional row crops. Two approaches were use: all variables approach (all_Var) and stable variables approach (sta_Var). In each approach, variables selected had significant correlation with yield, while all redundant and non-autocorrelated variables were discarded. Two fields were use in this study: Field 1 (17.0 ha soybean field located in Cascavel, Parana, Brazil); and Field 2 (35.0 ha corn field located in Wiggins, Colorado, US.). Two, three, four, and five MZs were created using fuzzy c-means clustering technique. The proposed methodology for define MZs is simple and allowed create good-quality MZs. It also founded that not-stable-over-time variables are not useful to define MZs. Key words: Precision agriculture, spatial variability, fuzzy clustering, autocorrelation, cross-correlation.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom