Warning models for coffee rust control in growing areas with large fruit load

Abstract

The objective of this work was to develop decision trees as warning models of coffee (Coffea arabica L.) rust in growing areas with large fruit load. Monthly data of disease incidence in the fi eld collected during eight years were transformed into binary values considering limits of 5 and 10 percentage points in the infection rate. Models were generated from meteorological data and space between plants for each binary infection rate. The warning is indicated when the infection rate is expected to reach or exceed the respective limit in a month. The accuracy obtained by cross-validating the model to the limit of 5 percentage points was 81%, reaching up to 89% according to an optimistic estimate. This model showed good results for other important evaluation measures, such as sensitivity (80%), specifi city (83%), positive reliability (79%), and negative reliability (84%). The model for the limit of 10 percentage points had a 79% accuracy and did not show the same balance among the other evaluation measures. Together, these two models may support the decisions about coffee rust control in the fi eld. The decision tree induction is a viable alternative to conventional modeling techniques, thus facilitating the comprehension of the models.