DOI:
https://doi.org/10.14483/22487638.22579Published:
2025-12-31Issue:
Vol. 29 No. 86 (2025): Octubre - DiciembreSection:
ResearchAboveground Biomass Estimation of Colombian Cocoa Agroforestry Systems using Multispectral Images and Regression Methods
Estimación de la biomasa aérea de sistemas agroforestales cacaoteros colombianos mediante imágenes multiespectrales y métodos de regresión
Keywords:
aboveground biomass estimation, agroforestry systems, cocoa, multispectral images, regression methods (en).Keywords:
estimación biomasa aérea, sistemas agroforestales, cacao, imágenes multiespectrales, métodos de regresión (es).Downloads
Abstract (en)
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.
Abstract (es)
Contexto: La estimación de la biomasa aérea (AGB) para aplicaciones agrícolas y ambientales tradicionalmente se basa en métodos manuales a nivel del suelo que requieren mucho tiempo. Los enfoques emergentes utilizan datos de teledetección que evalúan respuestas espectrales e índices de vegetación para estimar la AGB de una manera más eficiente. No obstante, estas técnicas enfrentan varios desafíos a la hora de tener en cuenta distribuciones espaciales complejas, especialmente en sistemas agroforestales (SAF).
Objetivo: Este trabajo buscó estimar la AGB en un SAF de cacao colombiano a partir de imágenes multiespectrales adquiridas con un vehículo aéreo no tripulado (UAV). Métodología: En este trabajo se estimó la AGB calculando diferentes índices de vegetación a partir de reflectancias espectrales medidas y evaluando dos modelos de regresión lineal, i.e., regresión de componentes principales (PCR) y regresión de mínimos cuadrados parciales (PLSR), y un modelo de regresión no lineal, una red neuronal de un solo perceptrón. Los puntos de control se obtuvieron mediante una adquisición manual de biomasa en tierra. Resultados: Los experimentos numéricos dieron como resultado un coeficiente de determinación de R2 = 0.58 para el mejor modelo lineal, mientras que el modelo no lineal alcanzó un R2 = 0.86.
Conclusiones: Es posible realizar una estimación eficaz de la AGB en un sistema agroforestal de cacao a partir de datos multiespectrales adquiridos con un UAV y un modelo de regresión no lineal simple.
References
[1] L. Torre, “Biomass estimation using lidar data,” Int. J. Sust. Energy Manage. Plan., vol. 17, p. 79–90, Jun. 2018. https://journals.aau.dk/index.php/sepm/article/view/2037
[2] H. Tao et al., “Estimation of crop growth parameters using UAV-based hyperspectral remote sensing data,” Sensors, vol. 20, no. 5, art. 1296, 2020. https://doi.org/10.3390/s20051296
[3] P. Lourenço, S. Godinho, A. Sousa, and A. C. Gonçalves, “Estimating tree aboveground biomass using multispectral satellite-based data in mediterranean agroforestry system using random forest algorithm,” Remote Sens. App. Soc. Environ., vol. 23, art. 100560, 2021. https://www.sciencedirect.com/science/article/pii/S2352938521000963
[4] S. Brown, Estimating biomass and biomass change of tropical forests: A primer. Rome, Italy: FAO, 1997.
[5] T. Wang et al., “Applications of UAS in crop biomass monitoring: A review,” Front. Plant Sci., vol. 12, art. 616689, 2021. https://doi.org/10.3389/fpls.2021.616689
[6] S. Sankar, M. Lewis, and P. Hosein, “Above ground biomass estimation of a cocoa plantation using machine learning,” in 2022 IEEE Int. Conf. Data Min. Work. (ICDMW), 2022, pp. 1–8.
[7] Z. Hosseini, H. Naghavi, H. Latifi, and S. Bakhtiari Bakhtiarvand, “Estimating biomass and carbon sequestration of plantations around industrial areas using very high resolution stereo satellite imagery,” iForest Biogeosci. Forestry, vol. 12, no. 6, art. 533, 2019. https://doi.org/10.3832/ifor3155-012
[8] Y. Li, M. Li, C. Li, and Z. Liu, “Forest aboveground biomass estimation using landsat 8 and sentinel-1a data with machine learning algorithms,” Sci. Rep., vol. 10, no. 1, art. 9952, 2020. https://doi.org/10.1038/s41598-020-67024-3
[9] A. Nyamukuru, C. Whitney, J. R. Tabuti, J. Esaete, and M. Low, “Allometric models for aboveground biomass estimation of small trees and shrubs in african savanna ecosystems,” Trees Forest People, vol. 11, art. 100377, 2023. https://www.sciencedirect.com/science/article/pii/S2666719323000092
[10] R. Aabeyir, S. Adu-Bredu, W. A. Agyare, and M. J. C. Weir, “Allometric models for estimating aboveground biomass in the tropical woodlands of Ghana, West Africa,” Forest Ecosyst., vol. 7, art. 41, 2020. https://doi.org/10.1186/s40663-020-00250-3
[11] A. B. Bazrgar, N. Thevathasan, A. Gordon, and J. Simpson, “Allometric equations for estimating aboveground biomass carbon in five tree species grown in an intercropping agroforestry system in southern ontario, canada,” Agroforestry Syst., vol. 98, no. 3, pp. 739–749, 2024. https://doi.org/10.1007/s10457-023-00942-z
[12] V. L. Morán-Villa et al., “Above-ground biomass estimation by developing allometric equations for theobroma cacao in tabasco, mexico,” Agroforestry Systems, vol. 98, no. 3, pp. 537–549, 2024. [Online]. Available: https://doi.org/10.1007/s10457-023-00928-x
[13] P. Sharma et al., “Geospatial technology in agroforestry: Status, prospects, and constraints,” Environ. Sci. Poll. Res., vol. 30, 30, pp. 116459–116487, 2023. https://doi.org/10.1007/s11356-022-20305-y
[14] M. Zhang et al., “A spatio-temporal fusion strategy for improving the estimation accuracy of the aboveground biomass in grassland based on gf-1 and modis,” Ecol. Ind., vol. 157, art. 111276, 2023. https://www.sciencedirect.com/science/article/pii/S1470160X23014188
[15] A. Hojo, R. Avtar, T. Nakaji, T. Tadono, and K. Takagi, “Modeling forest above-ground biomass using freely available satellite and multisource datasets,” Ecol. Infor., vol. 74, art. 101973, 2023. https://www.sciencedirect.com/science/article/pii/S157495412300002X
[16] P. Lourenço, “Biomass estimation using satellite-based data,” in Forest Biomass, A. C. Gonçalves, A. Sousa, and I. Malico, Eds. Rijeka: IntechOpen, 2021, ch. 3. [Online]. Available: https://doi.org/10.5772/intechopen.93603
[17] D. Kanmegne Tamga, H. Latifi, T. Ullmann, R. Baumhauer, J. Bayala, and M. Thiel, “Estimation of aboveground biomass in agroforestry systems over three climatic regions in West Africa using Sentinel-1, Sentinel-2, ALOS, and GEDI data,” Sensors, vol. 23, no. 1, art. 349, 2022. https://doi.org/10.3390/s23010349
[18] A. Chen et al., “Fusion of lidar and multispectral data for aboveground biomass estimation in mountain grassland,” Remote Sens., vol. 15, no. 2, art. 405, 2023. [Online]. Available: https://www.mdpi.com/2072-4292/15/2/405
[19] Q. Liu et al., “Smartagb: Aboveground biomass estimation of sorghum based on spatial resolution, machine learning and vegetation index,” EAI End. Trans. Internet of Things, vol. 9, no. 1, art. e1, Mar. 2023. https://publications.eai.eu/index.php/IoT/article/view/2904
[20] C. Zheng, A. Abd-Elrahman, V. Whitaker, and C. Dalid, “Prediction of strawberry dry biomass from uav multispectral imagery using multiple machine learning methods,” Remote Sens., vol. 14, no. 18, art. 4511, 2022. https://www.mdpi.com/2072-4292/14/18/4511
[21] S. Luo et al., “Multi-dimensional variables and feature parameter selection for aboveground biomass estimation of potato based on uav multispectral imagery,” Front. Plant Sci., vol. 13, art. 948249, 2022. https://www.frontiersin.org/articles/10.3389/fpls.2022.948249
[22] P. K. R. Nair, “Carbon sequestration studies in agroforestry systems: a reality-check,” Agroforestry Syst., vol. 86, no. 2, pp. 243–253, 2012. https://doi.org/10.1007/s10457-011-9434-z
[23] W. Ballesteros-Possú, J. C. Valencia, and J. F. Navia-Estrada, “Assessment of a cocoa-based agroforestry system in the southwest of colombia,” Sustainability, vol. 14, no. 15, art. 9447, 2022. https://www.mdpi.com/2071-1050/14/15/9447
[24] P. C. Abbott et al., “An analysis of the supply chain of cacao in Colombia,” Purdue University and International Center for Tropical Agriculture, Technical Report, 2018. [Online]. Available: https://www.purdue.edu/colombia/partnerships/cacaoforpeace/docs/Cacao%20for%20Peace%20Final%20English.pdf
[25] UPRA, “Plan de ordenamiento productivo: Análisis situacional de la cadena productiva del cacao y su agroindustria en colombia,” Unidad de Planeación Rural Agropecuaria, Dirección del Uso Eficiente del Suelo y Adecuación de Tierras, Technical Report, 2023. [Online]. Available: https://upra.gov.co/es-co/Paginas/pop-cacao.aspx
[26] UPRA, “Resultados preliminares: evaluaciones agropecuarias,” Unidad de Planeación Rural Agropecuaria, Technical Report, 2023. [Online]. Available: https://upra.gov.co/es-co/Evas_Documentos/Resultados_EVA_2023.pdf
[27] V. E. Mena-Mosquera and H. J. A. C, “Potencial de reducción de emisiones y captura de carbono en bosques y sistemas agroforestales con cacao en el pacífico colombiano,” Rev. Bio. Trop., vol. 69, no. 4, pp. 1252–1263, 2021.
[28] R. Singh et al., “Optimising carbon fixation through agroforestry: Estimation of aboveground biomass using multi-sensor data synergy and machine learning,” Ecol. Infor., vol. 79, art. 102408, 2024. https://www.sciencedirect.com/science/article/pii/S1574954123004375
[29] I. T. Jolliffe, “A note on the use of principal components in regression,” J. Royal Stat. Soc. Ser. C App. Stat., vol. 31, no. 3, pp. 300–303, 1982. http://www.jstor.org/stable/2348005
[30] G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning: with Applications in R. London, UK: Springer, 2013. [Online]. Available: https://faculty.marshall.usc.edu/gareth-james/ISL/
[31] S. Wold, M. Sjostrom, and L. Eriksson, “Pls-regression: A basic tool of chemometrics,” Chemometrics Intell. Lab. Syst., vol. 58, pp. 109–130, 2001.
[32] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016, http://www.deeplearningbook.org.
[33] H. Andrade, M. Segura, E. Somarriba, and M. Villalobos, “Valoración biofísica y financiera de la fijación de carbono por uso del suelo en fincas cacaoteras indígenas de Talamanca, Costa Rica,” in Agrofores. Amér., vol. 46, pp. 45-50, 2008. https://repositorio.catie.ac.cr/bitstream/handle/11554/10054/A11506e.pdf?sequence=1&isAllowed=y
[34] S. de Jong, “Simpls: An alternative approach to partial least squares regression,” Chemometrics Intell. Lab. Syst., vol. 18, no. 3, pp. 251–263, 1993. https://www.sciencedirect.com/science/article/pii/016974399385002X
[35] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015. https://doi.org/10.1038/nature14539
[36] R. Budiarto and B. G. Dewanto, “Unmanned aerial vehicles for assessing biomass and carbon stocks in mangrove forests: A systematic review,” Sust. Fut., vol. 10, art. 101425, 2025. https://doi.org/10.1016/j.sftr.2025.101425
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
License
Copyright (c) 2025 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 Chacon
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Esta licencia permite a otros remezclar, adaptar y desarrollar su trabajo incluso con fines comerciales, siempre que le den crédito y concedan licencias para sus nuevas creaciones bajo los mismos términos. Esta licencia a menudo se compara con las licencias de software libre y de código abierto “copyleft”. Todos los trabajos nuevos basados en el tuyo tendrán la misma licencia, por lo que cualquier derivado también permitirá el uso comercial. Esta es la licencia utilizada por Wikipedia y se recomienda para materiales que se beneficiarían al incorporar contenido de Wikipedia y proyectos con licencias similares.
