UAV-Based Classification of Intercropped Forage Cactus: A Comparison of RGB and Multispectral Sample Spaces Using Machine Learning in an Irrigated Area

• Published in: AgriEngineering Vol. 6; no. 1; pp. 509 - 525
• Main Authors: Andrade, Oto Barbosa de, Montenegro, Abelardo Antônio de Assunção, Silva Neto, Moisés Alves da, Sousa, Lizandra de Barros de, Almeida, Thayná Alice Brito, de Lima, João Luis Mendes Pedroso, Carvalho, Ailton Alves de, Silva, Marcos Vinícius da, Medeiros, Victor Wanderley Costa de, Soares, Rodrigo Gabriel Ferreira, Silva, Thieres George Freire da, Vilar, Bárbara Pinto
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-03-2024
• Subjects: Agricultural production; Agriculture; Algorithms; Artificial intelligence; Automatic classification; Aviation; Cactus; Classification; Comparative analysis; crop classification; Crops; Intercropping; Irrigated areas; Irrigation; K-nearest neighbors algorithm; Learning algorithms; Machine learning; multispectral bands; Performance evaluation; Precision farming; Probabilistic models; Productivity; Remote sensing; RGB bands; Software; Soil classification; Soils; Support vector machines; Unmanned aerial vehicles; Water conservation; Brazil
• ISSN: 2624-7402; 2624-7402
• DOI: 10.3390/agriengineering6010031

Precision agriculture requires accurate methods for classifying crops and soil cover in agricultural production areas. The study aims to evaluate three machine learning-based classifiers to identify intercropped forage cactus cultivation in irrigated areas using Unmanned Aerial Vehicles (UAV). It conducted a comparative analysis between multispectral and visible Red-Green-Blue (RGB) sampling, followed by the efficiency analysis of Gaussian Mixture Model (GMM), K-Nearest Neighbors (KNN), and Random Forest (RF) algorithms. The classification targets included exposed soil, mulching soil cover, developed and undeveloped forage cactus, moringa, and gliricidia in the Brazilian semiarid. The results indicated that the KNN and RF algorithms outperformed other methods, showing no significant differences according to the kappa index for both Multispectral and RGB sample spaces. In contrast, the GMM showed lower performance, with kappa index values of 0.82 and 0.78, compared to RF 0.86 and 0.82, and KNN 0.86 and 0.82. The KNN and RF algorithms performed well, with individual accuracy rates above 85% for both sample spaces. Overall, the KNN algorithm demonstrated superiority for the RGB sample space, whereas the RF algorithm excelled for the multispectral sample space. Even with the better performance of multispectral images, machine learning algorithms applied to RGB samples produced promising results for crop classification.