Abstract

A prediction function is developed for sugarcane yield using preplant soil nutrition levels, cultivar, and soil type. A tree regression approach is used because the resulting function encompasses the complexity of response between yield, multiple nutrients and other factors, while handling large amounts of data and providing information useful in the development of fertilizer and other production recommendations. Data collected from 148 control plots of experiments performed on commercial fields in the Everglades Agricultural Area of Florida are used to illustrate the method.

Keywords

Binary tree, Soil testing, Florida Everglades Agricultural Area

Creative Commons License


This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Share

COinS
 
Apr 23rd, 3:00 PM

USING TREE REGRESSION TO IDENTIFY NUTRITIONAL AND ENVIRONMENTAL FACTORS AFFECTING SUGARCANE PRODUCTION

A prediction function is developed for sugarcane yield using preplant soil nutrition levels, cultivar, and soil type. A tree regression approach is used because the resulting function encompasses the complexity of response between yield, multiple nutrients and other factors, while handling large amounts of data and providing information useful in the development of fertilizer and other production recommendations. Data collected from 148 control plots of experiments performed on commercial fields in the Everglades Agricultural Area of Florida are used to illustrate the method.