Artificial Intelligence in the Simulation of Fungicide Management Scenarios for Satisfactory Yield and Food Safety in oat Crops

Abstract

Purpose: The objective of the study is to analyze the management of the fungicide that seeks a longer interval between the last application and the harvest of oat grains, with an indication of the cultivars with the highest satisfactory productivity without application in the grain filling. Validate artificial neural network models in the expectation of satisfactory productivity with food security, through the interaction between management, pathogen, genotype, and environment. Method/design/approach: The study was conducted in 2015, 2016, 2017, in a randomized block design, in a 22 x 4 factorial scheme, for 22 white oat cultivars (recommended and no longer present in the current Brazilian recommendation) and 4 fungicide application conditions (no application; one application at 60 days after emergence (DAE); two applications, 60 and 75 DAE; and three applications, at 60, 75, 90 DAE), with three repetitions. Results and conclusion: The oat cultivars URS Altiva, URS, Guará, URS Charrua, FAEM 4 Carlasul, IPR Aphrodite, and UPFPS Farroupilha showed satisfactory yields in absence of fungicide applications. URS Altiva, FAEM 4 Carlasul, and IPR Aphrodite showed significant yield increases with fungicide application before grain filling. Artificial neural networks are efficient in predicting productivity and are a reliable alternative for simulating scenarios to validate more sustainable management practices. Originality/value: An unprecedented study seeking more sustainable managements to reduce the use of fungicides in the control of oat diseases and development of simulation models by artificial intelligence, providing opportunities for analysis of different scenarios of the complex interaction plant, pathogen, and environment.

Simulação do Progresso de doenças Foliares da Aveia por Redes Neurais Artificiais à Redução de Uso de Agrotóxicos

“…Na simulação são encontrados os valores de neurais articiais para prever a produtividade de grãos de aveia pela biomassa ao longo do ciclo, a dose de nitrogênio e variáveis meteorológicas. Dornelles et al (2023)[8] também relatam a importância de simulação das doenças de aveia, reconhecendo uma alternativa para simulação de cenários para validação de manejos mais sustentáveis. Nesta perspectiva, as redes neurais articiais se apresentam como uma tecnologia bastante promissora para o desenvolvimento de aplicações na agricultura, permitindo a simulação e previsão de cenários com alta precisão.4 Considerações FinaisNesta pesquisa foi mostrado que redes neurais articiais apresentam alta capacidade de aprendizado na expressão da área foliar necrosada envolvendo as variáveis temperatura do ar mínima e máxima, umidade relativa do ar mínima e máxima, juntamente a aplicação sequencial de fungicida e os dias do ciclo de desenvolvimento da aveia.Proceeding Series of the Brazilian Society of Computational and Applied Mathematics.…”