Sugarcane yield models, as most crop predicting models, are subject to the existence of spatial autocorrelation between observations. In this work, we used machine learning techniques to generate sugarcane yield models by splitting blocks of data, grouped by distance, in training and test sets in the cross validation phase, in contrast with separating single observations, as if they were independent. Although models generated using blocks of data led to a better estimation of the error in new data, both approaches generated similar error values.
Predicting the final yield of a crop is one of the most important aspects of a mill's agricultural planning. However, numerous factors must be considered to ensure a realistic forecast. Data mining techniques are capable of generating models that predict these values by relating a large amount of data. In this project, we studied learning curves, a tool used in the analysis of a model's performance according to the amount of data available. In an analysis of a database for a sugarcane production, we compared three different modeling techniques, suitable for regression models in the prediction of the final productivity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.