Can Unmanned Aerial Vehicle Images Be Used to Estimate Forage Production Parameters in Agroforestry Systems in the Caatinga?

• Published in: Applied sciences Vol. 14; no. 11; p. 4896
• Main Authors: Santos, Wagner Ma, Costa, Claudenilde de Jesus Pinheiro, Medeiros, Maria Luana da Silva, Jardim, Alexandre Maniçoba da Rosa Ferraz, Cunha, Márcio Vieira da, Dubeux Junior, José Carlos Batista, Jaramillo, David Mirabedini, Bezerra, Alan Cezar, Souza, Evaristo Jorge Oliveira de
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-06-2024
• Subjects: Agricultural production; Agroforestry; Biomes; buffel grass; bushveld signal grass; Crops; Decision making; Drone aircraft; Ecosystems; Global positioning systems; GPS; Grasses; machine learning; remote sensing; semiarid; Unmanned aerial vehicles; Vegetation; yield; Brazil
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app14114896

The environmental changes in the Caatinga biome have already resulted in it reaching levels of approximately 50% of its original vegetation, making it the third most degraded biome in Brazil, due to inadequate grazing practices that are driven by the difficulty of monitoring and estimating the yield parameters of forage plants, especially in agroforestry systems (AFS) in this biome. This study aimed to compare the predictive ability of different indexes with regard to the biomass and leaf area index of forage crops (bushveld signal grass and buffel grass) in AFS in the Caatinga biome and to evaluate the influence of removing system components on model performance. The normalized green red difference index (NGRDI) and the visible atmospherically resistant index (VARI) showed higher correlations (p < 0.05) with the variables. In addition, removing trees from the orthomosaics was the approach that most favored the correlation values. The models based on classification and regression trees (CARTs) showed lower RMSE values, presenting values of 3020.86, 1201.75, and 0.20 for FB, DB, and LAI, respectively, as well as higher CCC values (0.94). Using NGRDI and VARI, removing trees from the images, and using CART are recommended in estimating biomass and leaf area index in agroforestry systems in the Caatinga biome.