Aboveground Biomass Estimation of Colombian Cocoa Agroforestry Systems using Multispectral Images and Regression Methods

• Published in: Tecnura
• Main Authors: Claudia Victoria Correa Pugliese, Tatiana Carolina Gelvez Barrera, Laura Viviana Galvis Carreño, Edwin Mauricio Vargas Díaz, Jonathan Arley Monsalve Salazar, Ariolfo Camacho Velasco, Ivan Ramírez, Hoover Fabian Rueda Chacón
• Format: Article
• Language: Spanish
• Published: Universidad Distrital Francisco Jose de Caldas 2025-12-01
• Subjects: aboveground biomass estimation; agroforestry systems; cocoa; multispectral images; regression methods
• Online Access: https://revistas.udistrital.edu.co/index.php/Tecnura/article/view/22579
• ISSN: 0123-921X; 2248-7638

Context: Aboveground biomass (AGB) estimation for agricultural and environmental applications traditionally relies on time- consuming manual methods at ground level. Emerging approaches use remote sensing data evaluating spectral responses and vegetation indices in order to estimate the AGB more efficiently. Nonetheless, such techniques face various challenges in accounting for complex spatial distributions, especially when dealing with agroforestry systems (AFS). Objective: This work aimed to estimate AGB in a Colombian cocoa AFS from multispectral images acquired with an un-manned aerial vehicle (UAV). Methodology: In this work, the AGB was estimated by computing different vegetation indices from the measured spectral reflectances and evaluating two linear regression models, i.e., principal component regression (PCR) and partial least squares regression (PLSR), as well as a nonlinear regression model, a neural network composed by a perceptron with a single layer. Control points were obtained via on-ground biomass manual acquisition. Results: Numerical experiments resulted in a coefficient of determination of R2 = 0.58 for the best linear model, while the nonlinear model reached R2 = 0.86. Conclusions: AGB estimation in a cocoa AFS can be effectively performed using multispectral data acquired with a UAV and a simple nonlinear regression model.