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

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.

[1]  Dayou Liu,et al.  Mathematical modeling for active and dynamic diagnosis of crop diseases based on Bayesian networks and incremental learning , 2013, Math. Comput. Model..

[2]  Marek J. Druzdzel,et al.  Knowledge Engineering for Bayesian Networks: How Common Are Noisy-MAX Distributions in Practice? , 2006, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[3]  Kerrie Mengersen,et al.  Utility of Bayesian networks in QMRA-based evaluation of risk reduction options for recycled water. , 2016, The Science of the total environment.

[4]  Epidemias de ferrugem asiática no Rio Grande do Sul explicadas pelo fenômeno ENOS e pela incidência da doença na entressafra , 2016 .

[5]  Mark P. Styczynski,et al.  From genome-scale data to models of infectious disease: A Bayesian network-based strategy to drive model development. , 2015, Mathematical biosciences.

[6]  E. M. Reis,et al.  Models and applications for risk assessment and prediction of Asian soybean rust epidemics , 2006 .

[7]  Sheila Ariana Xavier,et al.  Older leaf tissues in younger plants are more susceptible to soybean rust , 2017 .

[8]  L. C. Carneiro,et al.  Influência do estádio fenológico e da idade dos trifólios de soja na infecção de Phakopsora pachyrhizi , 2009 .

[9]  Erlei Melo Reis,et al.  Development and validation of a fungicide scoring system for management of late season soybean diseases in Argentina , 2015 .

[10]  E. M. Reis,et al.  In vivo sensitivity of Phakopsora pachyrhizi to DMI and QoI fungicides , 2015 .

[11]  N. J. Fox,et al.  Challenges and priorities for modelling livestock health and pathogens in the context of climate change. , 2016, Environmental research.

[12]  L. L. May De Mio,et al.  Detection of the F129L mutation in the cytochrome b gene in Phakopsora pachyrhizi. , 2016, Pest management science.

[13]  O. Saab,et al.  Application of prediction models of asian soybean rust in two crop seasons, in Londrina, Pr , 2016 .

[14]  C. Godoy,et al.  Eficiência do controle da ferrugem asiática da soja em função do momento de aplicação sob condições de epidemia em Londrina, PR , 2009 .

[15]  Spectral characterization and quantification of Phakopsora pachyrhizi urediniospores by Fourier transformed infrared with attenuated total reflectance , 2019, European Journal of Plant Pathology.

[16]  R. Oliver,et al.  Governing principles can guide fungicide-resistance management tactics. , 2014, Annual review of phytopathology.

[17]  Ian R. Craig,et al.  Sensitivity of Phakopsora pachyrhizi towards quinone-outside-inhibitors and demethylation-inhibitors, and corresponding resistance mechanisms. , 2014, Pest management science.

[18]  C. Godoy,et al.  Risk and management of fungicide resistance in the Asian soybean rust fungus Phakopsora pachyrhizi. , 2012 .

[19]  Scott A Sisson,et al.  Modelling pathogen log10 reduction values achieved by activated sludge treatment using naïve and semi naïve Bayes network models. , 2015, Water research.

[20]  C. Godoy,et al.  Ferrugem-asiática da soja no Brasil: passado, presente e futuro , 2016 .

[21]  D. A. Andrade,et al.  Ferrugem asiática: uma ameaça à sojicultura brasileira. , 2002 .

[22]  Maryam Ramezani,et al.  Design a new mixed expert decision aiding system using fuzzy ELECTRE III method for vendor selection , 2009, Expert Syst. Appl..

[23]  W. Igarashi,et al.  Duração e porcentagem de molhamento foliar determinados pelo espaçamento entrelinhas, e influência sobre a ferrugem asiática da soja , 2014 .

[24]  H. Takahashi,et al.  Balance among calcium, magnesium and potassium levels affecting Asian Soybean Rust severity , 2015 .

[25]  J. S. Melching,et al.  Effects of Duration, Frequency, and Temperature of Leaf Wetness Periods on Soybean Rust , 1989 .

[26]  C. Godoy,et al.  Variação da sensibilidade de populações de Phakopsora pachyrhizi a fungicidas inibidores da desmetilação no Brasil. , 2015 .

[27]  P. Paul,et al.  Temporal Dynamics of Soybean Rust Associated With Leaf Area Index in Soybean Cultivars of different Maturity Groups. , 2015, Plant disease.

[28]  Marcelo de Carvalho Alves,et al.  Adaptive neuro-fuzzy inference systems for epidemiological analysis of soybean rust , 2011, Environ. Model. Softw..

[29]  First detection of a SDH variant with reduced SDHI sensitivity in Phakopsora pachyrhizi , 2018 .