No abstract

No abstract

Resumo -O objetivo deste trabalho foi desenvolver árvores de decisão como modelos de alerta da ferrugem-docafeeiro em lavouras de café (Coffea arabica L.) com alta carga pendente de frutos. Dados de incidência mensal da doença no campo coletados durante oito anos foram transformados em valores binários considerando limites de 5 e 10 pontos percentuais na taxa de infecção. Foi gerado um modelo para cada taxa de infecção binária a partir de dados meteorológicos e do espaçamento entre plantas. O alerta é indicado quando a taxa de infecção, prevista para o prazo de um mês, atingir ou ultrapassar o respectivo limite. A acurácia do modelo para o limite de 5 pontos percentuais foi de 81%, por validação cruzada, chegando até 89% segundo estimativa otimista. Esse modelo apresentou bons resultados para outras medidas de avaliação importantes, como sensitividade (80%), especifi cidade (83%) e confi abilidades positiva (79%) e negativa (84%). O modelo para o limite de 10 pontos percentuais teve acurácia de 79%, e não apresentou o mesmo equilíbrio entre as demais medidas. Em conjunto, esses modelos podem auxiliar na tomada de decisão referente ao controle da ferrugem-do-cafeeiro no campo. A indução de árvores de decisão é alternativa viável às técnicas convencionais de modelagem e facilita a compreensão dos modelos.Termos para indexação: Coffea arabica, Hemileia vastatrix, árvores de decisão, doença de plantas, previsão. Warning models for coffee rust control in growing areas with large fruit loadAbstract -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.

Brazil is the major coffee producer in the world, with 2 million hectares cropped, with 75% of this area with Coffea arabica and 25% with Coffea canephora. Coffee leaf rust (CLR) is one of the main diseases that cause yield losses by reducing healthy leaf area. As CLR is highly influenced by weather conditions, this study aimed to determine the best linearization model to estimate the CLR apparent infection rate, to correlate CLR infection rates with weather variables, and to develop and assess the performance of weather-based infection rate models to be used as a disease warning system. The CLR epidemic was analyzed for 88 site-seasons, while progress curves were assessed by linear, monomolecular, logistic, Gompertz, and exponential linearization models for apparent infection rate determination. Correlations between CLR infection rates and weather variables were conducted at different periods. From these correlations, multiple linear regressions were developed to estimate CLR infection rates, using the most weather-correlated variables. The Gompertz growth model had the best fit with CLR progress curves. Minimum temperature and relative humidity were the weather variables most correlated to infection rate and, therefore, chosen to compose a CLR forecast system. Among the models developed, the one for the condition of high coffee yield at a narrow row spacing was the best, with only 9.4% of false negative occurrences for all the months assessed.

Motivated by an agriculture case study, we discuss how to learn functions able to predict whether the value of a continuous target variable will be greater than a given threshold. In the application studied, the aim was to alert on high incidences of coffee rust, the main coffee crop disease in the world. The objective is to use chemical prevention of the disease only when necessary in order to obtain healthier quality products and reductions in costs and environmental impact. In this context, the costs of misclassifications are not symmetrical: false negative predictions may lead to the loss of coffee crops. The baseline approach for this problem is to learn a regressor from the variables that records the factors affecting the appearance and growth of the disease. However, the number of errors is too high to obtain a reliable alarm system. The approaches explored here try to learn hypotheses whose predictions are allowed to return intervals rather than single points. Thus, * Corresponding author Email address: antonio@aic.uniovi.es (Antonio Bahamonde) May 18, 2010 in addition to alarms and non-alarms, these predictors identify situations with uncertain classification, which we call warnings. We present 3 different implementations: one based on regression, and 2 more based on classifiers. Preprint submitted to Expert Systems with ApplicationsThese methods are compared using a framework where the costs of false negatives are higher than that of false positives, and both are higher than the cost of warning predictions.