Version 1
: Received: 8 October 2024 / Approved: 8 October 2024 / Online: 9 October 2024 (10:51:26 CEST)
How to cite:
Ferraz, M. A. J.; Santiago, A. G. D. S. G.; Bruzi, A. T.; Vilela, N. J. D.; Ferraz, G. A. E. S. Defoliation Categorization in Soybean with Machine Learning Algorithms and UAV Multispectral Data. Preprints2024, 2024100617. https://doi.org/10.20944/preprints202410.0617.v1
Ferraz, M. A. J.; Santiago, A. G. D. S. G.; Bruzi, A. T.; Vilela, N. J. D.; Ferraz, G. A. E. S. Defoliation Categorization in Soybean with Machine Learning Algorithms and UAV Multispectral Data. Preprints 2024, 2024100617. https://doi.org/10.20944/preprints202410.0617.v1
Ferraz, M. A. J.; Santiago, A. G. D. S. G.; Bruzi, A. T.; Vilela, N. J. D.; Ferraz, G. A. E. S. Defoliation Categorization in Soybean with Machine Learning Algorithms and UAV Multispectral Data. Preprints2024, 2024100617. https://doi.org/10.20944/preprints202410.0617.v1
APA Style
Ferraz, M. A. J., Santiago, A. G. D. S. G., Bruzi, A. T., Vilela, N. J. D., & Ferraz, G. A. E. S. (2024). Defoliation Categorization in Soybean with Machine Learning Algorithms and UAV Multispectral Data. Preprints. https://doi.org/10.20944/preprints202410.0617.v1
Chicago/Turabian Style
Ferraz, M. A. J., Nelson Júnior Dias Vilela and Gabriel Araújo e Silva Ferraz. 2024 "Defoliation Categorization in Soybean with Machine Learning Algorithms and UAV Multispectral Data" Preprints. https://doi.org/10.20944/preprints202410.0617.v1
Abstract
Traditional disease severity monitoring is subjective and inefficient. This study employs a Parrot multispectral sensor mounted on an unmanned aerial vehicle (UAV) to apply machine learning algorithms, such as Random Forest, for categorizing defoliation levels in R7-stage soybean plants. The research assesses the effectiveness of vegetation indices, spectral bands, and relative vegetation cover as input parameters, demonstrating that machine learning approaches combined with multispectral imagery can provide a more accurate and efficient assessment of Asian soybean rust in commercial soybean fields. The Random Forest algorithm exhibited satisfactory classification performance when compared to recent studies, achieving accuracy, precision, recall, F1-score, specificity and AUC values of 0.94, 0.92, 0.92, 0.92, 0.97 and 0.97, respectively. The input variables identified as most important for the classification model were the WDRVI and MPRI indices, the RedEdge and NIR bands, and relative vegetation cover, with the highest Gini importance index.
Keywords
asian rust; random forest; aerial images; multiline
Subject
Biology and Life Sciences, Agricultural Science and Agronomy
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
,
,
*
,
,
