A Bayesian Probability Model Can Simulate the Knowledge of Soybean Rust Researchers to Optimize the Application of Fungicides

Gregory Vinícius Conor Figueiredo, Lucas Henrique Fantin, Marcelo Giovanetti Canteri, José Carlos Ferreira da Rocha, David de Souza Jaccoud Filho

Source Title: International Journal of Agricultural and Environmental Information Systems (IJAEIS)10(4)

ISSN: 1947-3192|EISSN: 1947-3206|EISBN13: 9781522566755|DOI: 10.4018/IJAEIS.2019100103

Cite Article Cite Article

MLA

Figueiredo, Gregory Vinícius Conor, et al. "A Bayesian Probability Model Can Simulate the Knowledge of Soybean Rust Researchers to Optimize the Application of Fungicides." IJAEIS vol.10, no.4 2019: pp.37-51. http://doi.org/10.4018/IJAEIS.2019100103

APA

Figueiredo, G. V., Fantin, L. H., Canteri, M. G., Ferreira da Rocha, J. C., & Filho, D. D. (2019). A Bayesian Probability Model Can Simulate the Knowledge of Soybean Rust Researchers to Optimize the Application of Fungicides. International Journal of Agricultural and Environmental Information Systems (IJAEIS), 10(4), 37-51. http://doi.org/10.4018/IJAEIS.2019100103

Chicago

Figueiredo, Gregory Vinícius Conor, et al. "A Bayesian Probability Model Can Simulate the Knowledge of Soybean Rust Researchers to Optimize the Application of Fungicides," International Journal of Agricultural and Environmental Information Systems (IJAEIS) 10, no.4: 37-51. http://doi.org/10.4018/IJAEIS.2019100103

Export Reference

Favorite Full-Issue Download

View Full Text HTML

View Full Text PDF

Abstract

Asian rust is the main soybean disease in Brazil, causing up to 80% of yield reduction. The use of fungicides is the main form of control; however, due to farmer's concern with outbreaks many unnecessary applications are performed. The present study aims to verify the usefulness of a probability model to estimate the timing and the number of fungicides sprays required to control Asian soybean rust, using Bayesian networks and knowledge engineering. The model was developed through interviews with rust researchers and a literature review. The Bayesian network was constructed with the GeNIe 2.0 software. The validation process was performed by 42 farmers and 10 rust researchers, using 28 test cases. Among the 28 tested cases, generated by the system, the agreement with the model was 47.5% for the farmers and 89.3% for the rust researchers. In general, the farmers overestimate the number. The results showed that the Bayesian network has accurately represented the knowledge of the expert, and also could help the farmers to avoid the unnecessary applications.