Submitted to: Precision Agriculture
Publication Type: Peer reviewed journal
Publication Acceptance Date: 6/30/2008
Publication Date: 3/15/2009
Citation: Jiang, P., He, Z., Kitchen, N.R., Sudduth, K.A. 2009. Bayesian Analysis of Within-Field Variability of Corn Yield Using a Spatial Hierarchical Model. Precision Agriculture. 10(2):111–127. Interpretive Summary: Widespread use of combine harvesters equipped with yield monitoring systems has generated thousands of crop yield maps. These maps can facilitate investigating how crop yield is affected by soil and landscape properties. The purpose of this study was to explore the use of a specific statistical method, called Bayesian Hierarchical Modeling, to evaluate how corn grain yield is impacted by elevation, slope, and apparent soil electrical conductivity. This statistical method has been used in ecological studies and other sciences where spatial data has been collected, but has had limited use with agricultural data sets. We found relationships between yield and soil properties similar to those we have found using other procedures. Importantly, the Bayesian Hierarchical Modeling adequately accounted for relationships between sampling locations in close proximity (often called the spatial effect). The Bayesian model appeared to be a useful tool to gain insights into mapped yield as related to soil, topography, and weather. Farmers will benefit as these insights are incorporated into site-specific management decisions. Tailoring management for crop needs can increase farmer profitability and minimize over-application of fertilizer and pesticide, benefiting the general public with reduced impairment of lakes and streams.
Technical Abstract: Understanding relationships of soil and field topography to crop yield within a field is critical in site-specific management systems. Challenges for efficiently assessing these relationships include spatially correlated yield data and interrelated soil and topographic properties. The objective of this analysis was to apply a spatial Bayesian hierarchical model to examine the effects of soil, topographic, and climate variables on corn yield. The model included a mean structure of spatial and temporal covariates, and an explicit random spatial effect. The spatial covariates included elevation, slope, and apparent soil electrical conductivity, and temporal covariates included mean maximum daily temperature, mean daily temperature range, and cumulative precipitation of July and August. A conditional autoregressive (CAR) model was used to assess the spatial association in yield. Mapped corn yield data from 1997, 1999, 2001 and 2003 for a 36-ha Missouri claypan soil field were used in the analysis. The model building and computation were performed using a free Bayesian modeling software package, WinBUGS. The relationships of covariates to corn yield generally agreed with the literature. The CAR model successfully captured the spatial association in yield. Model standard deviation decreased about 50% with spatial effect accounted for. Further, the approach was able to assess the effects of temporal climate covariates on corn yield with a small number of site-years. The spatial Bayesian model appeared to be a useful tool to gain insights into yield spatial and temporal variability related to soil, topography and growing season weather conditions.