Artificial intelligence in seeding density optimization and yield simulation for oat

Abstract

A B S T R A C TArtificial intelligence may represent an efficient strategy for simulation and optimization of important processes in agriculture. The main goal of the study is to propose the use of artificial intelligence, namely artificial neural networks and genetic algorithms, respectively, in the simulation of oat grain yield and optimization of seeding density, considering the main succession systems of southern Brazil. The study was conducted in a randomized complete block design with four replicates, following a 4 x 2 factorial scheme, for seeding densities (100, 300, 600 and 900 seeds m -2 ) and oat cultivars (Brisasul and URS Taura), in succession systems of corn/oats and soybean/oats. A multi-layered artificial neural network and a genetic algorithm were implemented in Java programming language, and the results obtained from this implementation were compared with traditional polynomial regression. The use of artificial intelligence through neural networks and genetic algorithms allows the efficient simulation of oat grain yield and better optimization of seeding density in comparison to polynomial regression, considering the main succession systems in southern Brazil.Inteligência artificial na otimização da densidade de semeadura e simulação da produtividade da aveia R E S U M O O uso de inteligência artificial pode representar uma estratégia eficiente de simulação e otimização de processos importantes na agricultura. O objetivo deste estudo é propor o uso de inteligência artificial via redes neurais artificiais e algoritmos genéticos, respectivamente, na simulação da produtividade de grãos de aveia (Avena sativa) e na otimização da densidade de semeadura, nos principais sistemas de sucessão do sul do Brasil. O estudo foi conduzido em blocos ao acaso com quatro repetições em esquema fatorial 4 x 2, para as densidades de semeadura (100, 300, 600 e 900 sementes m -2 ) e cultivares de aveia (Brisasul e URS Taura), nos sistemas de sucessão milho/aveia e soja/aveia. Implementou-se uma rede neural artificial de múltiplas camadas e um algoritmo genético, em linguagem de programação Java, e comparou-se os resultados obtidos desta implementação com análises tradicionais de regressão polinomial. O uso de inteligência artificial via redes neurais artificiais e algoritmos genéticos permite simular com eficiência a produtividade de grãos de aveia e melhor otimização da densidade de semeadura na comparação com regressão polinomial, considerando os principais sistemas de sucessão no sul do Brasil.

Agronomic performance of white oats cultivated under fertigation with treated sewage effluent and definition of critical limits of Normalized Difference Vegetation Index

“…Plant density is an essential factor of GY in white oats. A higher number of panicles per square meter increases the GY of white oats to a certain extent (Dornelles et al 2018), since high densities increase intraspecific competition among tillers. For cultivar 'IAC 7' (the same as that used in the present study), densities between 410 and 500 panicles.m -2 generated a GY ranging from 5,241 to 7,024 kg.ha -1 (Soratto et al 2012); this range was observed for the number of panicles per square meter in the present study.…”

Comparison of Methods for Harvest Prediction in ‘Gigante’ Cactus Pear

“…Soares et al (2014) fitted regression models with similar R 2 when estimating the matter of the bunches in 'Tropical' bananas. The coefficients of determination of the models presented in this study, such as those related to the estimation of production in other crops (Leal et al, 2015;Kaytez et al, 2015;Dornelles et al, 2018) can be considered of low magnitude, since the predictive descriptors explained in a limited way the performance of the predicted variable After intense training for the composition of the ANNs, two architectures with the greatest potential to predict cactus pear yield were determined based on the coefficient of determination, mean square error and mean square of the deviations. The models 7-5-1 and 6-2-1 (Table 3) were selected using the criteria of relevance and greater predictive capacity.…”

The impact of artificial intelligence on commercial management

“…What kind of intelligent machines and what functions will they be able to perform, and most of all, what place will a human being occupy when this happens? Dornelles (2018) carried out a study that aimed to use ANN-based AI and genetic algorithms, to predict oat grain yield (oat sativa) and to optimize seeding density in the main succession systems of Southern Brazil. Dornelles (2018) concludes that the use of AI, through ANN techniques and genetic algorithms, allows efficiently simulating oat grain yield with better optimization of sowing density when compared to traditional polynomial regression models.…”

“…About 53% of respondents (Table 4) consider that AI tools may replace commercial functions that will depend on business-to-business strategy, vision, and profitability. On the other hand, 53% of respondents also mention that companies view AI tools as a means of assisting in the development of daily tasks, as advocated by Lustosa (2004), Mosque (2017), Dornelles (2018). On this vein, respondents show some reticence regarding this theme, when asked about the possible view that the company has about its functions.…”

“…Sharma et al (2014),Lustosa (2004),Mesquita (2017),Dornelles (2018) Verify which AI tools are used by commercials, and to understand the perception about the use of these tools Q2 -Are AI tools a substitute for business professionals, or will they help in the development of their functions?Martinez and Casillas (2013), Sharma et al (2014), Zoltners et al (2018), Khatibi et al (2003), Costa (2009), Sarfati (2016), Lustosa (2004) Q3 -How do companies view these types of AI tools? Sharma et al (2014), Costa (2009), Sarfati (2016), Obermayer and Emanuel (2016), Mesquita (2017), Paiva and Prevedello (2017) Q4 -Are AI tools seen as a competitive advantage?…”