Investigating Machine Learning techniques applied in cotton crop management

• Carlos Gabriel S. Rodrigues UFMT
• Carlos Rafael N. de A. Silva UFMT
• Allan Vitor W. Toledo UFMT
• Claudia A. Martins UFMT
• Raul T. Santos UFMT

DOI: https://doi.org/10.5753/eri-mt.2023.236620

Abstract

Cotton is the raw material for several products that are used daily. Its production requires care so that productivity meets expectations. Computational techniques can assist in monitoring and production performance. Therefore, this work aims to use images obtained from cotton production and, using machine learning techniques, seek tools that can assist in the management of cotton cultivation so that the productivity of the plantation can be analyzed. In this work, several experiments were carried out with regression algorithms using R² as a principal metric.

Keywords: classification, machine learning, precision agriculture, cotton

References

Adamchuk, Viacheslav I.; Perk, Richard L.; and Schepers, James S., "EC03-702 Precision Agriculture: Applications of Remote Sensing in Site-Specific Management" (2003). Historical Materials from University of Nebraska-Lincoln Extension. 705.

Budach, Lukas et al. The effects of data quality on machine learning performance. arXiv preprint arXiv:2207.14529, 2022.

Gavahale, Kiran R. et al. Uma visão geral da pesquisa sobre detecção de doenças em folhas de plantas usando técnicas de processamento de imagem. Iosr journal of computer engineering (iosr-jce) , v. 16, n. 1, pág. 10-16, 2014.

Gulhane, Viraj A.; Kolekar, Maheshkumar H. Diagnóstico de doenças em folhas de algodoeiro usando classificador de análise de componentes principais. In: Conferência Anual IEEE Índia de 2014 (INDICON). IEEE, 2014. pág. 1-5.

Habib, M. T. et al. Machine vision based papaya disease recognition. Journal of King Saud University-Computer and Information Sciences, v. 32, n. 3, p. 300-309, 2020.

Oliveira, Mailson Freire de. Previsão e estimativa de variáveis de cultivo utilizando níveis e formas de sensoriamento remoto e técnicas de aprendizado de máquina. 2021.

Patrício, D. I.; Rieder, R. Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review. Computers and electronics in agriculture, v. 153, p. 69-81, 2018.

Rodrigues, Luiz Souza; Pereira, Danilo Roberto. Aprendizado de Máquina Aplicado em Imagem NDVI para previsão da produtividade da Cana-de-Açúcar. In: Colloquium Exactarum. ISSN: 2178-8332. 2021. p. 82-98.

Sharma, Abhinav et al. Machine learning applications for precision agriculture: A comprehensive review. IEEE Access, v. 9, p. 4843-4873, 2020.

USDA (2017) “World Agricultural Production”, In: Circular Series, [link].

API deisgn for machine larning software: experiences from the scikit-learn project, Buitinck et al., 2013. Documentação do scikit-learn. Disponível em: [link]. Acesso em: 5 de agosto de 2023.

Scikit-Learn: Machine Learning in Python, Pedregosa et al, JMLR 12, pp 2825-2830, 2011.