SUGARCANE PRODUCTION PREDICTION USING LOW-CODE PYCARET FRAMEWORK
DOI:
https://doi.org/10.31510/infa.v22i2.2371Keywords:
AutoML, TCH, Sugarcane, PyCaret, Framework, Precision AgricultureAbstract
This paper presents a study of the low-code PyCaret framework. This framework selects Machine Learning (AutoML) models automatically, encompassing preprocessing, feature selection, and result prediction. In the agribusiness field, one of the framework's potential applications is forecasting agricultural productivity, measured in tons of sugarcane per hectare (TCH), in Brazilian mills. Therefore, this study focused on applying the low-code framework to forecast TCH, evaluating several regression models. The study also compared the two methods that, according to the framework, performed the best performance based on the adopted evaluation metrics. The results presented after model validation in real agricultural scenarios indicated the presence of outliers and other issues that explained the selection of certain algorithms. The study contributes to the understanding of the use of AutoML in precision agriculture by presenting algorithms, model validation, and limitations of the framework's use.
Downloads
References
ALI, M. PyCaret: An open source, low-code machine learning library in Python. PyCaret version, [s. l.], v. 2, 2020. .
BENJAMIN, S. G.; JAMES, E. P.; SZOKE, E. J.; SCHLATTER, P. T.; BROWN, J. M. The 30 December 2021 Colorado Front Range windstorm and Marshall Fire: Evolution of surface and 3D structure, NWP guidance, NWS forecasts, and decision support. Weather and Forecasting, [s. l.], v. 38, n. 12, p. 2551–2573, 2023. . DOI: https://doi.org/10.1175/WAF-D-23-0086.1
CHAI, T.; DRAXLER, R. R. Root mean square error (RMSE) or mean absolute error (MAE). Geoscientific model development discussions, [s. l.], v. 7, n. 1, p. 1525–1534, 2014. . DOI: https://doi.org/10.5194/gmdd-7-1525-2014
CONAB. Safra 2024/25 de cana-de-açúcar encerra com produção estimada em 676,96 milhões de toneladas. 2025. Companhia Nacional de Abastecimento. Disponível em: https://www.gov.br/conab/pt-br/assuntos/noticias/safra-2024-25-de-cana-de-acucar-encerra-com-producao-estimada-em-676-96-milhoes-de-toneladas. Acesso em: 25 set. 2025.
FILHO, M. As Métricas Mais Populares para Avaliar Modelos de Machine Learning. 6 maio 2018. Disponível em: https://mariofilho.com/as-metricas-mais-populares-para-avaliar-modelos-de-machine-learning/. Acesso em: 25 set. 2025.
HASTIE, T. The elements of statistical learning: data mining, inference, and prediction. [S. l.]: Springer, 2009. DOI: https://doi.org/10.1007/978-0-387-84858-7
HE, X.; ZHAO, K.; CHU, X. AutoML: A survey of the state-of-the-art. Knowledge-Based Systems, [s. l.], v. 212, p. 106622, 5 jan. 2021. https://doi.org/10.1016/j.knosys.2020.106622. DOI: https://doi.org/10.1016/j.knosys.2020.106622
HUBER, P. J. Robust Estimation of a Location Parameter. In: KOTZ, S.; JOHNSON, N. L. (orgs.). Breakthroughs in Statistics. Springer Series in Statistics. New York, NY: Springer New York, 1992. p. 492–518. DOI 10.1007/978-1-4612-4380-9_35. Disponível em: http://link.springer.com/10.1007/978-1-4612-4380-9_35. Acesso em: 25 set. 2025. DOI: https://doi.org/10.1007/978-1-4612-4380-9_35
KE, G.; MENG, Q.; FINLEY, T.; WANG, T.; CHEN, W.; MA, W.; YE, Q.; LIU, T.-Y. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, [s. l.], v. 30, 2017. Disponível em: https://proceedings.neurips.cc/paper/2017/hash/6449f44a102fde848669bdd9eb6b76fa-Abstract.html. Acesso em: 25 set. 2025.
PAREKH. PyCaret 3.0 | Docs. 19 mar. 2023. Disponível em: https://pycaret.gitbook.io/DOCS. Acesso em: 25 set. 2025.
PEDREGOSA, F.; VAROQUAUX, G.; GRAMFORT, A.; MICHEL, V.; THIRION, B.; GRISEL, O.; BLONDEL, M.; PRETTENHOFER, P.; WEISS, R.; DUBOURG, V. Scikit-learn: Machine learning in Python. the Journal of machine Learning research, [s. l.], v. 12, p. 2825–2830, 2011. .
POPPER, K. The logic of scientific discovery. [S. l.]: Routledge, 2005. Disponível em: https://www.taylorfrancis.com/books/mono/10.4324/9780203994627/logic-scientific-discovery-karl-popper-karl-popper. Acesso em: 25 set. 2025. DOI: https://doi.org/10.4324/9780203994627
SCARPARI, M. S. Modelos para a previsão da produtividade da cana-de-açúcar (Saccharum spp.) através de parâmetros climáticos. 2002. PhD Thesis – Universidade de São Paulo, 2002. Disponível em: https://www.teses.usp.br/teses/disponiveis/11/11136/tde-17122002-165859/publico/maximiliano.pdf. Acesso em: 25 set. 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Revista Interface Tecnológica
This work is licensed under a Creative Commons Attribution 4.0 International License.
Os direitos autorais dos artigos publicados pertencem à revista Interface Tecnológica e seguem o padrão Creative Commons (CC BY 4.0), que permite o remixe, adaptação e criação de obras derivadas do original, mesmo para fins comerciais. As novas obras devem conter menção ao(s) autor(es) nos créditos.
1.png)
1.png)
