A new alternative to determine weed control in agricultural systems based on artificial neural networks (ANNs)

• Published in: Field crops research Vol. 263; p. 108075
• Main Authors: Monteiro, Alex Lima, Freitas Souza, Matheus de, Lins, Hamurábi Anizio, Teófilo, Taliane Maria da Silva, Barros Júnior, Aurélio Paes, Silva, Daniel Valadão, Mendonça, Vander
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2021
• Subjects: Artificial intelligence; Decision making; Modeling; Weed interference; Weed interference; Decision making; Artificial intelligence; Modeling
• ISSN: 0378-4290; 1872-6852
• DOI: 10.1016/j.fcr.2021.108075

•The use of RNAs was tested to estimate the beginning of weed control considering model crops.•The ANN-MLP models were efficient in determining the ideal moment for weed control.•RNAs allow us to estimate the beginning of weed control.•Combined non-destructive and destructive entries do not require other, more specific entries.•The period is the main factor that interferes with the degree of weed interference in sesame and melon. Weed control is a necessary practice to avoid crop yield losses. Therefore, farmers should answer the following question: when to start weed control? Currently, there are no learning models to assist the producer to answer this question. Thus, the objectives were to: 1) evaluate the ability of artificial neural networks (ANNs) to estimate the beginning of weed control for different classes of acceptable yield losses; 2) validate a new alternative for modeling and predicting competition between weeds and crops. ANNs determined the ideal moment to control weeds based on non-destructive and destructive variables. The inputs C3/C4 ratio, coexistence period, density of weeds, and crop (categorical variable to differentiate sesame and melon) provided accuracy and F-score values above 0.95 during training, validation, and testing steps for ANN in non-destructive method. When using the destructive variables, C3/C4 ratio plus coexistence period, fresh matter of weeds, and crop provided accuracy and F-score values above 0.90 during training, validation, and testing steps. The combination of non-destructive and destructive inputs also generated an ANN with high accuracy and F-score, above 0.95, during training, validation, and testing steps. Machine learning can be used in crop-weed competition modeling.