Aplicación de aprendizaje automático multimodal para optimizar la producción de cacao mediante agricultura de precisión en zonas tropicales
DOI:
https://doi.org/10.56048/MQR20225.9.4.2025.e1214Palabras clave:
Aprendizaje automático multimodal; agricultura de precisión; inteligencia artificial explicable; cacao; sostenibilidad agrícola; inclusión digital rural.Resumen
Este artículo presenta la propuesta de PREDICT-CACAO, una plataforma inteligente basada en aprendizaje automático multimodal orientada a optimizar la producción de cacao en zonas tropicales. La investigación aborda las limitaciones estructurales del sistema cacaotero, como la baja capacidad predictiva, el uso ineficiente de recursos y la alta incidencia de enfermedades, mediante la integración de datos climáticos, edáficos, visuales e históricos en modelos de machine learning, visión por computador e inteligencia artificial explicable (XAI).
El marco metodológico PREDICT-CACAO, comprende cinco fases: adquisición de datos multiescalares, modelado predictivo de rendimiento y enfermedades, implementación de XAI, desarrollo de una plataforma digital adaptativa y validación participativa en campo. Los resultados esperados incluyen una mejora significativa en la precisión de las predicciones, una detección temprana de enfermedades con más del 90% de efectividad, y una mayor eficiencia en el uso de insumos agrícolas. Asimismo, se proyecta el fortalecimiento de las capacidades tecnológicas de los productores y una mayor apropiación de la agricultura digital en contextos rurales.
El proyecto demuestra que la integración de inteligencia artificial y agricultura de precisión no solo impulsa la productividad y sostenibilidad del cacao, sino que también promueve la inclusión tecnológica, la resiliencia climática y el desarrollo rural sostenible.
Descargas
Métricas
Cited
DOI: 10.56048
Citas
Afsar, M. M., Bakhshi, A. D., Hussain, E., & Iqbal, J. (2024). A deep learning-based framework for object recognition in ecological environments with dense focal loss and occlusion. Neural Computing and Applications, 36(16), 9591–9604. https://doi.org/10.1007/s00521-024-09582-5
Agbotui, D. K., Ingold, M., Wiehle, M., & Buerkert, A. (2023). Can carbon payments improve profitability of traditional conventional and organic cocoa agroforests? A case study in the Eastern Region of Ghana. Agroforestry Systems, 97(5), 813–831. https://doi.org/10.1007/s10457-023-00828-0
Akpoti, K., Dembélé, M., Forkuor, G., Obuobie, E., Mabhaudhi, T., & Cofie, O. (2023). Integrating GIS and remote sensing for land use/land cover mapping and groundwater potential assessment for climate-smart cocoa irrigation in Ghana. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-43286-5
Alexandre, C., Tresch, L., Sarron, J., Lavarenne, J., Bringer, G., Chaham, H. R., Bendahou, H., Carmeni, S., Borianne, P., Koffi, J. M., & Faye, E. (2023). Creating shared value(s) from On-Farm Experimentation: ten key lessons learned from the development of the SoYield® digital solution in Africa. Agronomy for Sustainable Development, 43(3). https://doi.org/10.1007/s13593-023-00888-7
Alvarado, M. C., Sanchez, P. D. C., & Polongasa, S. G. N. (2023). Emerging rapid and non-destructive techniques for quality and safety evaluation of cacao: recent advances, challenges, and future trends. In Food Production, Processing and Nutrition (Vol. 5, Issue 1). BioMed Central Ltd. https://doi.org/10.1186/s43014-023-00157-w
Arakeri, M., Dhatvik, M. P., Kavan, A. V., Murthy, K. S., Nishitha, N. L., & Lakshmi, N. (2024). Intelligent pesticide recommendation system for cocoa plant using computer vision and deep learning techniques. Environmental Research Communications, 6(7). https://doi.org/10.1088/2515-7620/ad58ae
Ashiagbor, G., Asare-Ansah, A. O., Amoah, E. B., Asante, W. A., & Mensah, Y. A. (2023). Assessment of machine learning classifiers in mapping the cocoa-forest mosaic landscape of Ghana. Scientific African, 20. https://doi.org/10.1016/j.sciaf.2023.e01718
Atalaya-Marin, N., Goñas, M., Tineo, D., Chuquibala-Checan, B., Arce-Inga, M., Tarrillo, E., Alvarez-Robledo, Y. A., Tafur-Culqui, J., Cabrera-Hoyos, H., & Gómez-Fernández, D. (2025). Integrating remote sensing and in-situ data to determine climate diversity and variability in cocoa systems in the provinces of Jaén and San Ignacio, Cajamarca (NW Perú). Trees, Forests and People, 19. https://doi.org/10.1016/j.tfp.2024.100749
Attiogbé, A. A. C., Abotsi, K. E., Adjossou, K., Parkoo, E. N., Adjonou, K., & Kokou, K. (2022). Climate vulnerability of coffee-cocoa agrosystems in the sub-humid mountain ecosystems in south-west Togo (West Africa). Environmental Systems Research, 11(1). https://doi.org/10.1186/s40068-022-00274-4
Ayikpa, K. J., Ballo, A. B., Mamadou, D., & Gouton, P. (2024). Optimization of Cocoa Pods Maturity Classification Using Stacking and Voting with Ensemble Learning Methods in RGB and LAB Spaces. Journal of Imaging, 10(12). https://doi.org/10.3390/jimaging10120327
Bosompem, M. (2021). Potential challenges to precision agriculture technologies development in Ghana: scientists’ and cocoa extension agents’ perspectives. Precision Agriculture, 22(5), 1578–1600. https://doi.org/10.1007/s11119-021-09801-2
Carrillo, K., Martínez, M., Ramírez, L., Argüello, D., & Chavez, E. (2023). Cadmium (Cd) distribution and soil-plant relationship in cacao farms in Costa Rica. Environmental Monitoring and Assessment, 195(10). https://doi.org/10.1007/s10661-023-11817-2
Cerón-Souza, I., Delgadillo-Duran, D., Polo-Murcia, S. M., Sarmiento-Naizaque, Z. X., & Reyes-Herrera, P. H. (2023). Prioritizing Colombian plant genetic resources for investment in research using indicators about the geographic origin, vulnerability status, economic benefits, and food security importance. Biodiversity and Conservation, 32(7), 2221–2261. https://doi.org/10.1007/s10531-023-02599-7
Chapman, R., Cock, J., Samson, M., Janetski, N., Janetski, K., Gusyana, D., Dutta, S., & Oberthür, T. (2021). Crop response to El Niño-Southern Oscillation related weather variation to help farmers manage their crops. Scientific Reports, 11(1). https://doi.org/10.1038/s41598-021-87520-4
De la Peña, N., & Granados, O. M. (2024). Artificial intelligence solutions to reduce information asymmetry for Colombian cocoa small-scale farmers. Information Processing in Agriculture, 11(3), 310–324. https://doi.org/10.1016/j.inpa.2023.03.001
Deldari, S., Xue, H., Saeed, A., Smith, D. V., & Salim, F. D. (2022). COCOA: Cross Modality Contrastive Learning for Sensor Data. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 6(3). https://doi.org/10.1145/3550316
Donfouet, O., & Ngouhouo, I. (2024). Impact of artificial intelligence on the total productivity of agricultural factors in Africa. Environment, Development and Sustainability. https://doi.org/10.1007/s10668-024-05528-y
Dung, C. D., Trueman, S. J., Wallace, H. M., Farrar, M. B., Gama, T., Tahmasbian, I., & Bai, S. H. (2023). Hyperspectral imaging for estimating leaf, flower, and fruit macronutrient concentrations and predicting strawberry yields. Environmental Science and Pollution Research, 30(53), 114166–114182. https://doi.org/10.1007/s11356-023-30344-8
González-Orozco, C. E., Porcel, M., Byrareddy, V. M., Rahn, E., Cardona, W. A., Velandia, D. A. S., Araujo-Carrillo, G. A., & Kath, J. (2024). Preparing Colombian coffee production for climate change: Integrated spatial modelling to identify potential robusta coffee (Coffea canephora P.) growing areas. Climatic Change, 177(4). https://doi.org/10.1007/s10584-024-03717-2
Harvey, C. A., Pritts, A. A., Zwetsloot, M. J., Jansen, K., Pulleman, M. M., Armbrecht, I., Avelino, J., Barrera, J. F., Bunn, C., Hoyos García, J., Isaza, C., Munoz-Ucros, J., Pérez-Alemán, C. J., Rahn, E., Robiglio, V., Somarriba, E., Valencia, V., & Nl, V. V. (n.d.). Transformation of coffee-growing landscapes across Latin America. A review. https://doi.org/10.1007/s13593-021-00712-0/Published
Indore, N. S., Karunakaran, C., & Jayas, D. S. (2022). Synchrotron tomography applications in agriculture and food sciences research: a review. In Plant Methods (Vol. 18, Issue 1). BioMed Central Ltd. https://doi.org/10.1186/s13007-022-00932-9
Isong, I. A., John, K., Okon, P. B., Ogban, P. I., & Afu, S. M. (2022). Soil quality estimation using environmental covariates and predictive models: an example from tropical soils of Nigeria. Ecological Processes, 11(1). https://doi.org/10.1186/s13717-022-00411-y
Kalischek, N., Lang, N., Renier, C., Daudt, R. C., Addoah, T., Thompson, W., Blaser-Hart, W. J., Garrett, R., Schindler, K., & Wegner, J. D. (2023). Cocoa plantations are associated with deforestation in Côte d’Ivoire and Ghana. Nature Food, 4(5), 384–393. https://doi.org/10.1038/s43016-023-00751-8
Kanmegne Tamga, D., Latifi, H., Ullmann, T., Baumhauer, R., Thiel, M., & Bayala, J. (2023). Modelling the spatial distribution of the classification error of remote sensing data in cocoa agroforestry systems. Agroforestry Systems, 97(1), 109–119. https://doi.org/10.1007/s10457-022-00791-2
Kulesza, E., Thomas, P., Prewitt, S. F., Shalit-Kaneh, A., Wafula, E., Knollenberg, B., Winters, N., Esteban, E., Pasha, A., Provart, N., Praul, C., Landherr, L., dePamphilis, C., Maximova, S. N., & Guiltinan, M. J. (2024). The cacao gene atlas: a transcriptome developmental atlas reveals highly tissue-specific and dynamically-regulated gene networks in Theobroma cacao L. BMC Plant Biology, 24(1). https://doi.org/10.1186/s12870-024-05171-9
Lara-Estrada, L., Rasche, L., & Schneider, U. A. (n.d.). Land in Central America will become less suitable for coffee cultivation under climate change. https://doi.org/10.1007/s10113-021-01803-0/Published
Lesiv, M., Schepaschenko, D., Buchhorn, M., See, L., Dürauer, M., Georgieva, I., Jung, M., Hofhansl, F., Schulze, K., Bilous, A., Blyshchyk, V., Mukhortova, L., Brenes, C. L. M., Krivobokov, L., Ntie, S., Tsogt, K., Pietsch, S. A., Tikhonova, E., Kim, M., … Fritz, S. (2022). Global forest management data for 2015 at a 100 m resolution. Scientific Data, 9(1). https://doi.org/10.1038/s41597-022-01332-3
Lie Cabrestante, J. M., Difuntorum, A. V, & Gino Wata, M. (2024). Disease Identification and Severity Analysis on Lanzones Leaf Using Android-Based Application. https://doi.org/10.1145/3647649
Logacjov, A. (2024). Self-supervised Learning for Accelerometer-based Human Activity Recognition: A Survey. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 8(4). https://doi.org/10.1145/3699767
Longchamps, L., Tisseyre, B., Taylor, J., Sagoo, L., Momin, A., Fountas, S., Manfrini, L., Ampatzidis, Y., Schueller, J. K., & Khosla, R. (2022). Yield sensing technologies for perennial and annual horticultural crops: a review. In Precision Agriculture (Vol. 23, Issue 6, pp. 2407–2448). Springer. https://doi.org/10.1007/s11119-022-09906-2
Lopes, J. F., da Costa, V. G. T., Barbin, D. F., Cruz-Tirado, L. J. P., Baeten, V., & Barbon Junior, S. (2022). Deep computer vision system for cocoa classification. Multimedia Tools and Applications, 81(28), 41059–41077. https://doi.org/10.1007/s11042-022-13097-3
Marcel Heming, N., Schroth, G., Talora, D. C., & Faria, D. (n.d.). Cabruca agroforestry systems reduce vulnerability of cacao plantations to climate change in southern Bahia. https://doi.org/10.1007/s13593-022-00780-w/Published
Masolele, R. N., Marcos, D., De Sy, V., Abu, I. O., Verbesselt, J., Reiche, J., & Herold, M. (2024). Mapping the diversity of land uses following deforestation across Africa. Scientific Reports, 14(1). https://doi.org/10.1038/s41598-024-52138-9
Obando, Ó. E. T., Escobar, J. A. D., & Torres, E. A. (2023). Socio-economic aspects associated with water management in cocoa cultivation in Valle del Cauca, Colombia. Acta Agronomica, 72(4), 368–376. https://doi.org/10.15446/acag.v72n4.113615
Omeka, M. E., Igwe, O., Onwuka, O. S., Nwodo, O. M., Ugar, S. I., Undiandeye, P. A., & Anyanwu, I. E. (2024). Efficacy of GIS-based AHP and data-driven intelligent machine learning algorithms for irrigation water quality prediction in an agricultural-mine district within the Lower Benue Trough, Nigeria. Environmental Science and Pollution Research, 31(41), 54204–54233. https://doi.org/10.1007/s11356-023-25291-3
Orji, R., Deters, R., Kumi, S., & Lomotey, R. K. (2024). Automatic detection and diagnosis of cocoa diseases using mobile tech and deep learning. International Journal of Sustainable Agricultural Management and Informatics, 10(1). https://doi.org/10.1504/ijsami.2024.10059217
Pinardi, S., Salis, M., Sartor, G., & Meo, R. (2023). EU−Africa: Digital and Social Questions in a Multicultural Agroecological Transition for the Cocoa Production in Africa. Social Sciences, 12(7). https://doi.org/10.3390/socsci12070398
Ramos, M. J., Beilhe, L. B., Alvarado, J., Rapidel, B., & Allinne, C. (2024). Disentangling shade effects for cacao pest and disease regulation in the Peruvian Amazonia. Agronomy for Sustainable Development, 44(1). https://doi.org/10.1007/s13593-024-00948-6
Riaño, M. A., Rodriguez, A. O. R., Velandia, J. B., García, P. A. G., & Marín, C. E. M. (2023). Design and application of an ontology to identify crop areas and improve land use. Acta Geophysica, 71(3), 1409–1426. https://doi.org/10.1007/s11600-022-00808-5
Schmidt, J. E., DuVal, A., Isaac, M. E., & Hohmann, P. (2022). At the roots of chocolate: understanding and optimizing the cacao root-associated microbiome for ecosystem services. A review. In Agronomy for Sustainable Development (Vol. 42, Issue 2). Springer-Verlag Italia s.r.l. https://doi.org/10.1007/s13593-021-00748-2
Şener, A., & Ergen, B. (2024). Advanced CNN Approach for Segmentation of Diseased Areas in Plant Images. Journal of Crop Health, 76(6), 1569–1583. https://doi.org/10.1007/s10343-024-01054-z
Seyum, E. G., Bille, N. H., Abtew, W. G., Munyengwa, N., Bell, J. M., & Cros, D. (2022). Genomic selection in tropical perennial crops and plantation trees: a review. In Molecular Breeding (Vol. 42, Issue 10). Springer Science and Business Media B.V. https://doi.org/10.1007/s11032-022-01326-4
Singh, K., Fuentes, I., Al-Shammari, D., Fidelis, C., Butubu, J., Yinil, D., Sharififar, A., Minasny, B., Guest, D. I., & Field, D. J. (2023). E-Agriculture Planning Tool for Supporting Smallholder Cocoa Intensification Using Remotely Sensed Data. Remote Sensing, 15(14). https://doi.org/10.3390/rs15143492
Somarriba, E., Saj, S., Orozco-Aguilar, L., Somarriba, A., & Rapidel, B. (2024). Shade canopy density variables in cocoa and coffee agroforestry systems. Agroforestry Systems, 98(3), 585–601. https://doi.org/10.1007/s10457-023-00931-2
Talero-Sarmiento, L., Roa-Prada, S., Caicedo-Chacon, L., & Gavanzo-Cardenas, O. (2025). A Data-Driven Approach to Improve Cocoa Crop Establishment in Colombia: Insights and Agricultural Practice Recommendations from an Ensemble Machine Learning Model. AgriEngineering, 7(1). https://doi.org/10.3390/agriengineering7010006
Vásquez-Ordóñez, A. A., Torres-López, W., & Monmany-Garzia, A. C. (2024). A multi-scale approach to study palm-weevils in a tropical agroecosystem. Landscape Ecology, 39(3). https://doi.org/10.1007/s10980-024-01796-1
Vera, D. B., Oviedo, B., Casanova, W. C., & Zambrano-Vega, C. (2024). Deep Learning-Based Computational Model for Disease Identification in Cocoa Pods (Theobroma cacao L.). http://arxiv.org/abs/2401.01247
Villalobos-Culqui, C., García-Rivas-plata, C., & Tuesta-Hidalgo, O. A. (2025). Artificial vision model based on convolutional neural networks for black pod identification in cacao plantations. Revista Cientifica de Sistemas e Informatica, 5(1). https://doi.org/10.51252/rcsi.v5i1.678
Zhang-Zheng, H., Deng, X., Aguirre-Gutiérrez, J., Stocker, B. D., Thomson, E., Ding, R., Adu-Bredu, S., Duah-Gyamfi, A., Gvozdevaite, A., Moore, S., Oliveras Menor, I., Prentice, I. C., & Malhi, Y. (2024). Why models underestimate West African tropical forest primary productivity. Nature Communications , 15(1). https://doi.org/10.1038/s41467-024-53949-0
Publicado
Cómo citar
Número
Sección
Categorías
Licencia
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
®
Los autores se comprometen a respetar la información académica de otros autores, y a ceder los derechos de autor a la Revista MQRInvestigar, para que el artículo pueda ser editado, publicado y distribuido. El contenido de los artículos científicos y de las publicaciones que aparecen en la revista es responsabilidad exclusiva de sus autores. La distribución de los artículos publicados se realiza bajo una licencia 
