Warning models for coffee rust (Hemileia vastatrix Berkeley & Broome) by data mining techniques

Cesare Girolamo Neto, Luiz Henrique Antunes Rodrigues, Carlos Alberto Alves Meira


Coffee rust can cause severe yield losses if control measures are not taken. Warning models are capable of generating useful information regarding to the application of fungicides, decreasing economic losses and environmental impacts. The aim of this study was to develop, compare and select warning models developed by data mining techniques in order to predict the coffee rust in years of high and low fruit load. For 13 years (1998-2011), data was collected from an automatic weather station. The independent variables were 23, obtained from the weather station, and the dependent variable was the monthly progress rate for the coffee rust, which was generated by the values of disease incidence. The most important features were refined by feature selection techniques, and the modeling was performed using four data mining techniques: support vector machines, artificial neural networks, decision trees and random forests. For high fruit load years the best accuracy was 85.3% and for low fruit load years it was 88.9%. Other performance measures like recall and specificity also had high and balanced values. The warning models developed on this study provide further information for monitoring the disease on high fruit load years than other models previously developed, and also provide a possibility for the monitoring on years of low fruit load.


Predictive models; random forest; support vector machines; artificial neural networks; decision trees


ALVES, M. C. et al. A Soft Computing Approach For Epidemiological Studies of Coffee And Soybean Rusts. International Journal of Digital Content Technology and its Applications, v.4, n.1, p.149-154, fev. 2010.

BATCHELOR, W.D.; YANG, X.B; TSCHANZ, A.T. Development of a neural network for soybean rust epidemics. Transactions of the American Society of Agricultural Engineers, v.40, n.1, p.247-252, 1997.

BATISTA, G. E. A. P. A.; PRATI, R. C.; MONARD, M. C. A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explorations, New York, v.6, n.1, p.20-29, jun. 2004.

BREIMAN, L. Random forests. Machine Learning Journal. Hingham, v.45, p.5-32, jan. 2001.

CHALFOUN, S. M. Doenças do cafeeiro: importância, identificação e métodos de controle. Lavras: UFLA/FAEPE. 1997.

CHANG, C-C.; LIN, C-J. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology. v.2, n.3, Art. 27 - 27p., abr. 2011.

CINTRA, M. E. et al. The use of fuzzy decision trees for coffee rust warning in Brazilian crops. In: International Conference on Intelligent Systems Design and Applications, 11, 2011, Córdoba. Proceedings... Córdoba: IEEE, 2011, p. 1347-1352.

FAWCETT, T. An introduction to ROC analysis. Pattern Recognition Letters. New York, v.27, n.8, p.861-874, jun., 2006.

FAYYAD, U.; PIATETSKY-SHAPIRO, G.; SMYTH, P. From data mining to knowledge discovery in databases. AI Magazine, v.17, n.3, p.37-54, jul. 1996.

HALL, M. A. et al. The WEKA Data Mining Software: An Update; SIGKDD Explorations, New York, v.11, n.1, p. 10-18, jun. 2009.

HAN, J.; KAMBER, M.; PEI, J. Data mining: concepts and techniques. 3ed. San Francisco: Morgan Kaufmann Publishers, 2011. 703 p.

HARDWICK, N. V. Disease forecasting. In: COOKE, B. M.; JONES, D. G.; KAYE, B. The epidemiology of plant diseases. 2aed. Holanda:Springer, 2006. p. 239-267.

HAYKIN, S. Neural Networks and Learning Machines. 3ed., Englewood Cliffs: Prentice-Hall. 2009. 936 p.

KUSHALAPPA, A. C.; AKUTSU, M.; LUDWIG, A. Application of survival ratio for monocyclic process of Hemileia vastatrix in predicting coffee rust infection rates. Phytopathology. St. Paul, v.73, n.1, p.96‑103, 1983.

KUSHALAPPA, A. C.; ESKES, A. B. Advances in coffee rust research. Annual Review of Phytopathology, v. 27, p.503‑531, set. 1989.

LEE, M. C.; TO, C. Comparison of Support Vector Machine and Back Propagation Neural Network in Evaluating the Enterprise Financial Distress. International Journal of Artificial Intelligence & Applications, v.1, p. 31-43, 2010.

LUACES, O. et al. Using nondeterministic learners to alert on coffee rust disease. Expert systems with applications, v.38, n.11, p.14276-14283, jan. 2011.

MEIRA, C. A. A.; RODRIGUES, L. H. A.; MORAES, S. A. Análise da epidemia da ferrugem do cafeeiro com árvore de decisão. Tropical Plant Pathology. v.33, n.2, p.114-124, mar./abr. 2008.

MEIRA, C. A. A.; RODRIGUES, L. H. A.; MORAES, S. A. Modelos de alerta para o controle da ferrugem-do-cafeeiro em lavouras com alta carga pendente. Pesquisa Agropecuária Brasileira. v.44, n.3, p.233-242, mar. 2009.

MOLINEROS, J. E. et al. Modeling epidemics of fusarium head blight: trials and tribulations. Phytopathology, v.95, n.6, p.S71, 2005.

MORAES, S. A. et al. Período de incubação de Hemileia vastatrix Berk. e Br. em três regiões do Estado de SP. Summa Phytopathologica. Piracicaba, v.2, n.1, p.32‑38, 1976.

PAUL, P. A.; MUNKVOLD, G. P. A model-based approach to preplanting risk assessment for gray leaf spot of maize. Phytopathology, v.94, n.12, p. 1350‑1357, 2004.

PAUL, P. A.; MUNKVOLD, G. P. Regression and artificial neural network modeling for the prediction of gray leaf spot of maize. Phytopathology, v.95, n.4, p. 388‑396, 2005.

PÉRES-ARIZA, C. B.; NICHOLSON, A. E.; FLORES, M. J. Prediction of Coffee Rust Disease Using Bayesian Networks. In: European Workshop on Probabilistic Graphical Models, 6, 2012, Granada. Proceedings... Granada: PGM, 2012. p. 259-266.

PINTO, A. C. S. et al. Descrição da epidemia da ferrugem do cafeeiro com redes neuronais. Fitopatologia Brasileira, Brasília, v.27, n.5, p.517-524, set./out., 2002.

PRATI, R. C.; BATISTA; G. E. A. P. A.; MONARD, M. C. Curvas ROC para avaliação de classificadores. Revista IEEE América Latina. v.6, n.2, p.215-222, jun. 2008.

SOUZA, V. C. O. et al. Técnicas de extração de conhecimento aplicadas a modelagem de ocorrência da cercosporiose (Cercospora coffeicola Berkeley & Cooke) em cafeeiros na região sul de minas gerais. Coffee Science, Lavras, v.8, n.1, p.91-100, jan./mar. 2013.

USDA. United States Department Of Agriculture. Disponível em: , Acesso em: 15 fev. 2013.

WITTEN, I. H.; FRANK, E.; HALL, M. A. Data mining: practical machine learning tools and techniques. 3aed. San Francisco: Morgan Kaufmann, 2011. 629 p.

ZAMBOLIM, L. et al. Epidemiologia e controle integrado da ferrugem-do-cafeeiro. In: ZAMBOLIM, L. O estado da arte de tecnologias na produção de café. Viçosa: Suprema Gráfica e Editora, 2002. p. 369‑449.

DOI: http://dx.doi.org/10.25186/cs.v9i3.687


  • There are currently no refbacks.