Two classification methods for developing and interpreting productivity zones using site properties

Abstract

Crop performance is often shown as areas of differing grain yield. Many producers utilize simple GIS color ramping techniques to produce visual yield maps with delineated clusters. However, a more quantitative approach such as an unsupervised clustering procedure is generally used by scientists since it is much less arbitrary. Intuitively the yield clusters are due to soil and terrain properties, but there is no clear criterion for the delineation. We compared the effectiveness of two delineation or classification procedures: quadratic discriminant analysis (QDA) and k-nearest neighbor discriminant analysis (k-NN) for the study of how yield temporal patterns relate to site properties. This study used three production fields, one in Monticello, IL, and two in Centralia, MO. Clusters were defined using maize (Zea mays L.) and soybean (Glycine max (L.) Merr.) yield from three seasons. The k-NN had greater and more consistent successful classification rates than did QDA. Classification success rate varied from 0.465 to 0.790 for QDA while the k-NN classification rate varied from 0.794 to 0.874. This shows that areas of certain temporal yield patterns correspond to areas of specific site properties. Although profiles of site properties differ by crop and production field, areas of consistent low maize yield had greater shallow electrical conductivity (EC shallow ), than those of consistent high maize yield. Furthermore, areas of consistent high soybean yield had lower soil reflectance than those areas of consistent low yields.

Selection of ancillary data to derive production management units in sweet corn (Zea Mays var. rugosa) using MANOVA and an information criterion

“…For example, Fridgen et al (2000) proposed a weighted statistic that compares the within-zone variance relative to the total field variance, whereas Cupitt and Whelan (2001) used a confidence interval based on the uncertainty of interpolation relative to the mean differences in crop response between units. Martin et al (2006) used a hybrid approach that interpreted the stability of both a statistical value (the cubic clustering criterion) and variance partitioning (the R 2 of their model fit to the data).…”

“…Ping et al (2005) used a multivariate ANOVA (MANOVA) approach to identify soil variables that affected lint yield in cotton, and then used these selected variables to define MUs. Similarly, recent applications of discriminant analysis have been reported to associate predefined yield-based MUs with edaphic, topographic and crop reflectance variables (Martin et al 2006;Cox and Gerard 2007). These multivariate analyses all aim to interpret how ancillary data (soil variables, topographic variables, canopy vigour, etc.)…”