Modelo de visión artificial basada en redes neuronales convolucionales para identificación de mazorca negra en plantaciones de cacao

Cristian Villalobos-Culqui; Cecilia García-Rivas-Plata; Oscar Alejandro Tuesta-Hidalgo

doi:10.51252/rcsi.v5i1.678

Autores/as

Villalobos-Culqui, Cristian Universidad Nacional de San Martín
García-Rivas-Plata, Cecilia Universidad Nacional Ciro Alegría https://orcid.org/0000-0001-7254-1162
Tuesta-Hidalgo, Oscar Alejandro Universidad Nacional Autónoma de Alto Amazonas

DOI:

https://doi.org/10.51252/rcsi.v5i1.678

Palabras clave:

detección temprana, modelos de aprendizaje profundo, análisis de imágenes, clasificación automática, agricultura de precisión

Resumen

La detección temprana de la mazorca negra en plantaciones de cacao representa un desafío clave en el sector agrícola, ya que afecta el rendimiento y la calidad del grano. La falta de métodos avanzados dificulta su identificación oportuna. Este estudio desarrolla modelos de visión artificial basados en redes neuronales convolucionales (CNN) para mejorar su detección. Durante nueve meses, recolectamos y etiquetamos 1982 imágenes de mazorcas afectadas en cinco parcelas del sector Shitarillo, distrito de Alto Saposoa, San Martín. Implementamos YOLOv8, InceptionV3 y VGG19, aplicando transferencia de aprendizaje para optimizar la clasificación. Dividimos los datos en 70% para entrenamiento, 20% para validación y 10% para pruebas. YOLOv8 e InceptionV3 alcanzaron una precisión promedio del 79%, superando a VGG19. Las métricas de evaluación, junto con pruebas ANOVA y Tukey, confirmaron que ambos modelos ofrecieron un desempeño superior sin diferencias significativas entre ellos. YOLOv8 destacó por su mayor robustez y exactitud, lo que sugiere su implementación en sistemas de detección temprana para optimizar el control de la enfermedad en plantaciones de cacao.

Citas

Ahmad, A., Saraswat, D., & El Gamal, A. (2023). A survey on using deep learning techniques for plant disease diagnosis and recommendations for development of appropriate tools. Smart Agricultural Technology, 3, 100083. https://doi.org/10.1016/j.atech.2022.100083

Almadhor, A., Rauf, H., Lali, M., Damaševičius, R., Alouffi, B., & Alharbi, A. (2021). AI-Driven Framework for Recognition of Guava Plant Diseases through Machine Learning from DSLR Camera Sensor Based High Resolution Imagery. Sensors, 21(11), 3830. https://doi.org/10.3390/s21113830

Atila, Ü., Uçar, M., Akyol, K., & Uçar, E. (2021). Plant leaf disease classification using EfficientNet deep learning model. Ecological Informatics, 61, 101182. https://doi.org/10.1016/j.ecoinf.2020.101182

Baculio, N. G., & Barbosa, J. B. (2022). An Objective Classification Approach of Cacao Pods using Local Binary Pattern Features and Artificial Neural Network Architecture (ANN). Indian Journal of Science and Technology, 15(11), 495–504. https://doi.org/10.17485/IJST/v15i11.60

Barburiceanu, S., Meza, S., Orza, B., Malutan, R., & Terebes, R. (2021). Convolutional Neural Networks for Texture Feature Extraction. Applications to Leaf Disease Classification in Precision Agriculture. IEEE Access, 9, 160085–160103. https://doi.org/10.1109/ACCESS.2021.3131002

Basri, Tamin, R., Karim, H. A., Indrabayu, & Areni, I. S. (2020). Mobile image processing application for cacao’s fruits pest and disease attack using deep learning algorithm. ICIC Express Letters, 14. https://doi.org/https://doi.org/10.24507/icicel.14.10.1025

Bishop, C. M., & Bishop, H. (2024). Deep Learning. Springer International Publishing. https://doi.org/10.1007/978-3-031-45468-4

Boateng, K. O., Dankyi, E., Amponsah, I. K., Awudzi, G. K., Amponsah, E., & Darko, G. (2023). Knowledge, perception, and pesticide application practices among smallholder cocoa farmers in four Ghanaian cocoa-growing regions. Toxicology Reports, 10, 46–55. https://doi.org/10.1016/j.toxrep.2022.12.008

Che’Ya, N. N., Mohidem, N. A., Roslin, N. A., Saberioon, M., Tarmidi, M. Z., Arif Shah, J., Fazlil Ilahi, W. F., & Man, N. (2022). Mobile Computing for Pest and Disease Management Using Spectral Signature Analysis: A Review. Agronomy, 12(4), 967. https://doi.org/10.3390/agronomy12040967

Cuadra, Y. M. L., Rodríguez, M. Y. C., & Vega, Y. L. C. (2020). El cacao peruano y su impacto en la economía nacional.

Fachin, G., Pinedo, K., Vásquez, J., Flores, E., Doria, M., Alvarado, J., Koch, C., & Bellido, J. J. (2019). Factores ambientales y su relación con la incidencia de carmenta foraseminis (Busck) eichlin (Lepidóptera : Sesiidae) en frutos de theobroma cacao “cacao” en San Martín, Perú. Boletín Científico Centro de Museos Museo de Historia Natural, 23(2), 133–145. https://doi.org/10.17151/bccm.2019.23.2.6

Franco, A. J. D., Merca, F. E., Rodriguez, M. S., Balidion, J. F., Migo, V. P., Amalin, D. M., Alocilja, E. C., & Fernando, L. M. (2019). DNA-based electrochemical nanobiosensor for the detection of Phytophthora palmivora (Butler) Butler, causing black pod rot in cacao (Theobroma cacao L.) pods. Physiological and Molecular Plant Pathology, 107, 14–20. https://doi.org/10.1016/j.pmpp.2019.04.004

Gyamfi, A., Iddrisu, S. A.-J., & Adegbola, O. (2020). Machine Learning-Based Cocoa E-Health System. 2020 13th CMI Conference on Cybersecurity and Privacy (CMI) - Digital Transformation - Potentials and Challenges(51275), 1–7. https://doi.org/10.1109/CMI51275.2020.9322689

INEI. (2022). Informe Técnico No 01 - Marzo 2022 Indicador de la Actividad Productiva Departamental.

Jackulin, C., & Murugavalli, S. (2022). A comprehensive review on detection of plant disease using machine learning and deep learning approaches. Measurement: Sensors, 24, 100441. https://doi.org/10.1016/j.measen.2022.100441

Khalid, M., Sarfraz, M., Iqbal, U., Aftab, M., Niedbała, G., & Rauf, H. (2023). Real-Time Plant Health Detection Using Deep Convolutional Neural Networks. Agriculture, 13(2), 510. https://doi.org/10.3390/agriculture13020510

Khattak, A., Asghar, M. U., Batool, U., Asghar, M. Z., Ullah, H., Al-Rakhami, M., & Gumaei, A. (2021). Automatic Detection of Citrus Fruit and Leaves Diseases Using Deep Neural Network Model. IEEE Access, 9, 112942–112954. https://doi.org/10.1109/ACCESS.2021.3096895

Kumi, S., Kelly, D., Woodstuff, J., Lomotey, R. K., Orji, R., & Deters, R. (2022). Cocoa Companion: Deep Learning-Based Smartphone Application for Cocoa Disease Detection. Procedia Computer Science, 203, 87–94. https://doi.org/10.1016/j.procs.2022.07.013

Li, H., Shi, H., Du, A., Mao, Y., Fan, K., Wang, Y., Shen, Y., Wang, S., Xu, X., Tian, L., Wang, H., & Ding, Z. (2022). Symptom recognition of disease and insect damage based on Mask R-CNN, wavelet transform, and F-RNet. Frontiers in Plant Science, 13. https://doi.org/10.3389/fpls.2022.922797

Li, L., Zhang, S., & Wang, B. (2021). Plant Disease Detection and Classification by Deep Learning—A Review. IEEE Access, 9, 56683–56698. https://doi.org/10.1109/ACCESS.2021.3069646

Mashood Nasir, I., Bibi, A., Hussain Shah, J., Attique Khan, M., Sharif, M., Iqbal, K., Nam, Y., & Kadry, S. (2021). Deep Learning-based Classification of Fruit Diseases: An Application for Precision Agriculture. Computers, Materials & Continua, 66(2), 1949–1962. https://doi.org/10.32604/cmc.2020.012945

MIDAGRI. (2022). Commodities Cacao_ abr-jun 2022. https://repositorio.midagri.gob.pe/bitstream/20.500.13036/1363/1/Commodities%20Cacao_%20abr-jun%202022.pdf

Mohammad Yazdi Pusadan, Syahrullah, Merry, & Ahmad Imam Abdullah. (2022). k-Nearest Neighbor and Feature Extraction on Detection of Pest and Diseases of Cocoa. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 6(3), 471–480. https://doi.org/10.29207/resti.v6i3.4064

Mushi, G. E., Di Marzo Serugendo, G., & Burgi, P.-Y. (2022). Digital Technology and Services for Sustainable Agriculture in Tanzania: A Literature Review. Sustainability, 14(4), 2415. https://doi.org/10.3390/su14042415

Mzoughi, O., & Yahiaoui, I. (2023). Deep learning-based segmentation for disease identification. Ecological Informatics, 75, 102000. https://doi.org/10.1016/j.ecoinf.2023.102000

Olofintuyi, S. S. (2022). Early Cocoa Blackpod Pathogen Prediction with Machine Learning Ensemble Algorithm based on Climatic Parameters. Journal of Information and Organizational Sciences, 46(1), 1–14. https://doi.org/10.31341/jios.46.1.1

Palacios Bejarano, C. A., Afanador Kafuri, L., & Pardo García, J. M. (2021). Identificación de aislados de Phytophthora spp. obtenidos de cultivos de cacao en Antioquia, Colombia. Acta Agronómica, 70(1), 17–26. https://doi.org/10.15446/acag.v70n1.70619

Pandian, J., Kumar, V., Geman, O., Hnatiuc, M., Arif, M., & Kanchanadevi, K. (2022). Plant Disease Detection Using Deep Convolutional Neural Network. Applied Sciences, 12(14), 6982. https://doi.org/10.3390/app12146982

Picon, A., Seitz, M., Alvarez-Gila, A., Mohnke, P., Ortiz-Barredo, A., & Echazarra, J. (2019). Crop conditional Convolutional Neural Networks for massive multi-crop plant disease classification over cell phone acquired images taken on real field conditions. Computers and Electronics in Agriculture, 167, 105093. https://doi.org/10.1016/j.compag.2019.105093

Roy, S., Ray, R., Dash, S. R., & Giri, M. K. (2021). Plant Disease Detection Using Machine Learning Tools With an Overview on Dimensionality Reduction. In Data Analytics in Bioinformatics (pp. 109–144). Wiley. https://doi.org/10.1002/9781119785620.ch5

Singh, V., Sharma, N., & Singh, S. (2020). A review of imaging techniques for plant disease detection. Artificial Intelligence in Agriculture, 4, 229–242. https://doi.org/10.1016/j.aiia.2020.10.002

Vásquez-Cortez, L. H., Rojas-Sánchez, J., Pazmiño-Pérez, Á., & Rodríguez-Cevallos, S. L. (2024). Desarrollo de una bebida energizante a base de cacao y guayusa. Revista Peruana de Investigación Agropecuaria, 3(2), e66. https://doi.org/10.56926/repia.v3i2.66

Wang, Y., Rajkumar Dhamodharan, U. S., Sarwar, N., Almalki, F. A., Naith, Q. H., R, S., & D, M. (2024). A hybrid approach for rice crop disease detection in agricultural IoT system. Discover Sustainability, 5(1), 99. https://doi.org/10.1007/s43621-024-00285-4