Prediction of sugarcane yield by machine learning

Authors: Todd, James; Dufrene, Edwis; PONTIFF, MICHAEL - LSU Agcenter

Submitted to: American Society of Sugar Cane Technologists
Publication Type: Abstract Only
Publication Acceptance Date: 4/30/2019
Publication Date: 6/1/2019
Citation: Todd, J.R., Dufrene Jr, E.O., Pontiff, M. 2019. Prediction of sugarcane yield by machine learning [abstract]. Journal American Society of Sugar Cane Technologists. 39:43.

Interpretive Summary:

Technical Abstract: Yield prediction could be useful when harvest data are not attainable or when selection is necessary before harvest. If harvest yield data are unavailable, plant breeders rely upon previous yield data, field measurements and ratings to make selection decisions. Machine learning techniques can be used to make models with a set of predictors to estimate a target variable. These models can then be applied to data without the target variable to create the estimates. Models of outfield third ratoon cane yield were created using previous year’s data. Predictors of third ratoon cane yield developed from models utilizing combined plant cane through second ratoon yield data correlated better with third ratoon data than second ratoon yield data. Machine learning techniques show potential to improve selection where yield data is missing.