Skip to main content
ARS Home » Midwest Area » Columbia, Missouri » Cropping Systems and Water Quality Research » Research » Publications at this Location » Publication #131434
Title: STATISTICAL AND NEURAL METHODS FOR SITE-SPECIFIC YIELD PREDICTION

Author
item Drummond, Scott
item Sudduth, Kenneth - Ken
item JOSHI, ANUPAM - U OF MD
item BIRRELL, STUART - IA STATE U
item Kitchen, Newell

Submitted to: Transactions of the ASAE
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 11/1/2002
Publication Date: 2/1/2003
Citation: DRUMMOND, S.T., SUDDUTH, K.A., JOSHI, A., BIRRELL, S.J., KITCHEN, N.R. STATISTICAL AND NEURAL METHODS FOR SITE-SPECIFIC YIELD PREDICTION. TRANSACTIONS OF THE AMERICAN SOCIETY OF AGRICULTURAL ENGINEERS. 2003. V. 46(1). P. 5-14.

Interpretive Summary: Producers are currently adopting precision farming techniques and strategies throughout the U.S. These innovative producers are asking agricultural researchers to develop new and improved recommendations for fertilizers and other inputs to better use the additional field information available from precision farming. To provide these site-specific management trecommendations, a better understanding of the complex relationships between crop yield and site and soil characteristics is required. Our goal was to evaluate the predictive abilities of several statistical and neural network methods for relating crop yields to site and soil characteristics. Neural networks are computer software systems that mimic the basic functions and connections of the neurons within the human brain. We collected grain yield, soil property, and topographic data over multiple fields (or sites) and years, for a total of ten site-years. We conducted analyses both by individual site-years and, with inclusion of climatological variables, for the entire dataset. Neural network methods were consistently more accurate on the individual site-year analyses, particularly when compared to linear statistical techniques. None of the tested techniques worked well for analyzing the complete dataset. More years of yield and climate data would be required for this type of analysis to be successful. This information will benefit scientists by providing additional tools for the investigation of crop response to limiting factors such as soil fertility or water holding capacity. Producers and agribusiness will also benefit through the improved recommendations and crop management strategies developed with such techniques.

Technical Abstract: Understanding the relationships between yield and soil and site properties is of critical importance in precision farming. A necessary first step in this process is identifying techniques able to reliably quantify the relationships between measured soil and site characteristics and crop yield. A variety of methods, including stepwise multiple linear regression n(SMLR), projection pursuit regression (PPR), and several types of supervised feed-forward neural networks were investigated in an attempt to identify methods able to relate soil properties and grain yields on a point-by-point basis within ten individual site-years. To avoid overfitting, evaluations were based on predictive ability, using a five- fold cross-validation technique. The neural techniques consistently outperformed both PPR and SMLR and provided minimal prediction errors in every site-year. However, in site-years with relatively fewer observations sand in site-years where a single, overriding factor was not apparent, the improvements achieved by neural networks over both PPR and SMLR were small. A second phase of the experiment involved estimation of crop yield across multiple site-years by including climatological data. The ten site-years of data were appended with climatological variables, and prediction errors were computed. The results showed that significant overfitting had occurred and indicated that a much larger number of climatologically unique site-years would be required in this type of analysis.