Comparative Analysis of Convolutional Neural Networks Based on Transfer Learning for Foliar Disease Detection in Banana
Authors
-
Vanessa Pamela Briones-Mera
Escuela Superior Politécnica Agropecuaria de Manabí Manuel Félix López, Carrera de Computación, Calceta, Manabí, Ecuador
https://orcid.org/0009-0009-5603-1504
-
Susana Valentina Zambrano-Cedeño
Escuela Superior Politécnica Agropecuaria de Manabí Manuel Félix López, Carrera de Computación, Calceta, Manabí, Ecuador
https://orcid.org/0009-0002-6791-183X
-
Javier Hernán López-Zambrano
Escuela Superior Politécnica Agropecuaria de Manabí Manuel Félix López, Carrera de Computación, Calceta, Manabí, Ecuador
https://orcid.org/0000-0002-3439-4066
DOI:
https://doi.org/10.33936/isrtic.v10i2.8543Keywords:
Banana, Transfer Learning, foliar diseases, convolutional neural networks, Computer visionAbstract
Early detection of foliar diseases in banana crops is essential to minimize economic losses and reduce the indiscriminate use of agrochemicals. This study presents a comparative analysis of the effectiveness of various convolutional neural network architectures using Transfer Learning. A total of 14 state-of-the-art models were evaluated, including families such as ResNet, VGG, MobileNet, and EfficientNet, using a multiclass dataset that covers the most impactful pathologies in the sector. Experimental results demonstrate that, after applying fine-tuning techniques, the EfficientNetV2L model achieved the most outstanding performance with an accuracy of 99.35%. This finding outperforms traditional architectures and highlights the efficiency of compound scaling in capturing complex morphological features in leaves. It is concluded that the integration of these deep learning models provides a high-fidelity tool for automated diagnosis in precision agriculture.
Downloads
References
Arman, S. E., Bhuiyan, M. A. B., Abdullah, H. M., Islam, S., Chowdhury, T. T., & Hossain, M. A. (2023). Banana leaf spot diseases (BananaLSD) dataset (Version 1). Mendeley Data. https://doi.org/10.17632/9tb7k297ff.1
Arman, S. E., Bhuiyan, M. A. B., Abdullah, H. M., Islam, S., Chowdhury, T. T., & Hossain, M. A. (2023). BananaLSD: A banana leaf images dataset for classification of banana leaf diseases using machine learning. Data in Brief, 50, 109608. https://doi.org/10.1016/j.dib.2023.109608
Arriaga, G. S. N., Meza, C. W. G., & Painii, C. V. F. (2022). Uso de drones para el control de sigatoka negra (Mycosphaerella fijiensis) Vinces, Ecuador. ECOAgropecuaria Revista Científica Ecológica Agropecuaria, 1(2). https://doi.org/10.53591/recoa.v1i2.93
Aviles Amador, W. A. (2025). Impacto de los microorganismos endófitos en el manejo de la sigatoka negra (Mycosphaerella fijiensis) en el cultivo de banano (Musa x paradisiaca) en el Ecuador. [Trabajo de Titulación, Universidad Técnica de Babahoyo]. https://dspace.utb.edu.ec/server/api/core/bitstreams/3bb7fca0-07b2-43d1-891a-18fcd06209ad/content
Bangladesh Bureau of Statistics. (2024). Report on the Productivity Survey of Banana Crop. Ministry of Planning, Government of the People's Republic of Bangladesh. https://objectstorage.ap-dcc-gazipur-1.oraclecloud15.com/n/axvjbnqprylg/b/V2Ministry/o/office-bbs/2024/12/fda000e8cdfb4e7fa3b51324c14141e6.pdf
Barbedo, J. G. A. (2020). Detecting and classifying pests in crops using proximal images and machine learning: A review. AI, 1(2), 312-328. https://doi.org/10.3390/ai1020021
Cañetaco Barriga, R. E., & Chalco Siguachi, K. N. (2026). Evaluación de la eficiencia del tamaño de gota en aplicación aérea de fungicidas para controlar Sigatoka Negra (Mycosphaerella fijiensis) con dron en plantaciones de banano [Trabajo de Titulación, Universidad de Cuenca]. https://rest-dspace.ucuenca.edu.ec/server/api/core/bitstreams/f7c3939c-64d3-44ab-90c5-0ce99780cbb2/content
Cedeño Campoverde, K. J. (2024). Sistema de teledetección utilizando drones para la identificación de enfermedades de banano en la hacienda La Lorena [Trabajo de integración curricular, Universidad Técnica Estatal de Quevedo]. https://repositorio.uteq.edu.ec/server/api/core/bitstreams/2ca8ca66-a3c3-4aac-8452-dfd592c8a47b/content
Chollet, F. (2020). Transfer learning & fine-tuning. Keras Documentation. https://keras.io/guides/transfer_learning/
Corporación Financiera Nacional. (2024). Ficha sectorial banano. https://www.cfn.fin.ec/wp-content/uploads/2024/10/Ficha-Sectorial-Banano.pdf
De Oliveira, L. L., Nogueira, T. D. C., Carvalho, C. H. R., De Oliveira Santana, D., Silva, L. M., De Brito Dos Santos Batista, W., & Ullmann, M. R. D. (2025). Um modelo baseado em transferência de aprendizado profundo para detecção do mal-do-Panamá. Revista de Geopolítica, 16(4), e718. https://doi.org/10.56238/revgeov16n4-073
Enríquez Lapo, C. M. (2024). Influencia de factores climáticos en la producción de banano en la provincia de El Oro (Ecuador). Universidad Técnica de Machala.
FAO. 2021. The state of the world's land and water resources for food and agriculture – Systems at breaking point. Synthesis report 2021. Rome.
Ferrer-Sánchez, Y., Barahona-Manzaba, D. G., Plasencia, V. A. H., & Abasolo-Pacheco, F. (2024). Riesgo de expansión de Fusarium oxysporum f. cubense (Nectriaceae) ante el cambio climático en Ecuador continental. Acta Botanica Mexicana,131. https://doi.org/10.21829/abm131.2024.2207
Galarza Vera, J. J. (2024). Evaluación de alternativas fitosanitarias para el manejo de Sigatoka negra (Pseudocercospora fijiensis Morelet) en el cultivo de banano (Musa AAA) [Tesis de grado, Universidad Agraria del Ecuador]. Repositorio Digital de la Universidad Agraria del Ecuador. https://cia.uagraria.edu.ec/Archivos/GALARZA%20VERA%20JONATHAN%20JORDANO.pdf
Genet, Y. H., Sinshaw, N. T., Assefa, B. G., & Mohapatra, S. K. (2024). Sigatoka and Xanthomonas banana leaf disease detection via transfer learning. Scientia Iranica, 0(0), 0. https://doi.org/10.24200/sci.2024.62306.7766
Hosna, A., Merry, E., Gyalmo, J., Alom, Z., Aung, Z., & Azim, M. A. (2022). Transfer learning: a friendly introduction. Journal Of Big Data, 9(1). https://doi.org/10.1186/s40537-022-00652-w
Jiménez, N., Orellana, S., Mazon-Olivo, B., Rivas-Asanza, W., & Ramírez-Morales, I. (2025). Detection of leaf diseases in banana crops using deep learning techniques. AI, 6(3), 61. https://doi.org/10.3390/ai6030061
Li, Y., Nie, J., & Chao, X. (2020). Do we really need deep CNN for plant diseases identification? Computers And Electronics In Agriculture, 178, 105803. https://doi.org/10.1016/j.compag.2020.105803
Manggara, M. G., & Kalifia, A. D. (2025). Komparasi model ResNet50 dan EfficientNetV2M dengan penerapan transfer learning dan fine tuning pada klasifikasi penyakit bercak daun tanaman pisang. www.hostjournals.com. https://doi.org/10.47065/bulletincsr.v6i1.855
Martínez-Solórzano, G. E., & Rey-Brina, J. C. (2021). Bananos (Musa AAA): Importancia, producción y comercio en tiempos de Covid-19. Agron. Mesoam, 1034-1046. https://doi.org/10.15517/am.v32i3.43610
Montesdeoca Espinoza, L.J., Zambrano Rojas, S.J., Pinargote Bravo, V.J. & Cedeño Valarezo, L.C. (2025). Balanceo de conjuntos de datos basado en redes generativas aplicado a imágenes del sector agrícola. Informática y Sistemas 9(2), pp. 164-176 https://doi.org/10.33936/isrtic.v9i2.7782
Olivares, B. O., Vega, A., Rueda Calderón, M. Á., Rey, J. C., & Lobo, D. (2021). Clasificación de zonas afectadas por la marchitez en banano: Una aplicación con algoritmos de machine learning en Venezuela. Revista Especializada de Ingeniería y Ciencias de la Tierra, 1(1), 1–15. https://revistas.up.ac.pa/index.php/REICIT/article/view/2440/2230
Redacción Expreso. (2023, 26 de agosto). Se dispara la afectación de Sigatoka. Diario Expreso. https://www.expreso.ec/actualidad/economia/dispara-afectacion-sigatoka-171205.html
Sanga, S., Mero, V., Machuve, D., & Mwanganda, D. (2020, 7 abril). Mobile-based deep learning models for banana diseases detection. arXiv.org. https://arxiv.org/abs/2004.03718?utm_source202
Torres Salamea, H. M., Amores Romero, K. S., & Trelles Muñoz, K. G. (2022). Implementación de un sistema para detectar la enfermedad de la Sigatoka Negra en una plantación de banano empleando técnicas de visión artificial. Universidad del Azuay. https://dspace.uazuay.edu.ec/handle/datos/11682
Tripathi, J. N., Ntui, V. O., & Tripathi, L. (2023). Precision genetics tools for genetic improvement of banana. The Plant Genome, 17(2). https://doi.org/10.1002/tpg2.20416
Ünal, C. (2025). Incorporating deep learning into the diagnosis of banana leaf spot diseases for the protection of banana crops. Tarım Bilimleri Dergisi, 31(3), 780-794. https://doi.org/10.15832/ankutbd.1579442
Vera, Ch. J. D., & Carvajal, R. H. R. (2025). Avances en la inteligencia artificial para incrementar el rendimiento en los cultivos. AgroEcosistemas Revista Para la Transformación Agraria Sostenible, 13, e748. https://aes.ucf.edu.cu/index.php/aes/article/view/748
Villanueva, J. R. E., Ustate, L. M. T., Estrada, M. A. G., & Martínez, M. L. C. (2025). Segmentación foliar en sistemas de cultivo de banano: aplicaciones del flujo de trabajo fotogramétrico y teledetección mediante imágenes multiespectrales de aeronaves no tripuladas (UAS). Ciencia E Ingeniería Neogranadina, 35(1), 25-45. https://doi.org/10.18359/rcin.7365
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 27, 3320-3328. https://proceedings.neurips.cc/paper/2014/hash/375c71349b295fbe2dcdca9206f20a06-Abstract.html
Zabala, C. J. J. (2024). Banana Scan: Aplicación Android para la detección de enfermedades en cultivos de banano mediante TinyML. https://hdl.handle.net/20.500.12495/14049
Published
Issue
Section
License
Copyright (c) 2026 Vanessa Pamela Briones-Mera, Susana Valentina Zambrano-Cedeño, Javier Hernán López-Zambrano
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles submitted to this journal for publication will be released for open access under a Creative Commons Attribution Non-Commercial No Derivative Works licence (http://creativecommons.org/licenses/by-nc-nd/4.0).
The authors retain copyright, and are therefore free to share, copy, distribute, perform and publicly communicate the work under the following conditions: Acknowledge credit for the work specified by the author and indicate if changes were made (you may do so in any reasonable way, but not in a way that suggests that the author endorses your use of his or her work. Do not use the work for commercial purposes. In case of remixing, transformation or development, the modified material may not be distributed.
