Sistema inteligente de recomendación y detección visual para el manejo de cultivos

Contenido principal del artículo

Ian Thompson
Jason Arenales
Julio Fuentes
Edward Quintero
Vladimir Villarreal

Resumen

Este trabajo presenta el desarrollo de un sistema inteligente que combina visión artificial y un modelo de lenguaje (LLM) para asistir en el manejo de cultivos. Su objetivo es apoyar a los agricultores en la toma de decisiones preventivas y correctivas mediante el análisis de imágenes y texto. Frente a desafíos como el cambio climático, plagas y escasez de recursos, la herramienta busca identificar cultivos y enfermedades, ofreciendo recomendaciones precisas y accesibles. Con ello, se pretende reducir pérdidas agrícolas, mejorar la productividad y brindar asesoría en regiones con acceso limitado a expertos.

Detalles del artículo

Cómo citar
Thompson, I., Arenales , J., Fuentes , J., Quintero , E., & Villarreal , V. (2026). Sistema inteligente de recomendación y detección visual para el manejo de cultivos. Revista Tecnología En Marcha, 39(7), Pág. 99–107. https://doi.org/10.18845/tm.v39i3.8747
Sección
Artículo científico

Citas

[1] Junaid, M. D., & Gokce, A. F. (2024). Global agricultural losses and their causes. Bulletin of Biological and Allied Science Research, 2024(1), 66. https://doi.org/10.54112/bbasr.v2024i1.66

[2] Trejo, A., Ortiz, M., & Chávez, E. (2021). Inteligencia artificial y sistemas expertos aplicados a la agricultura de precisión. Revista de Tecnología e Innovación Agropecuaria, 5(2), 102–115. https://www.redalyc.org/journal/5600/560064435011/

[3] Roumeliotis, K. I., Sapkota, R., Karkee, M., Tselikas, N. D., & Nasiopoulos, D. K. (2025). Plant disease detection through multimodal large language models and convolutional neural networks. arXiv. https://doi.org/10.48550/arXiv.2504.20419

[4] Madaan, V., Bindal, G., Singh, S., Yadav, S. K., Singh, A., Sinha, P., & Nagpal, D. (2023). Integrating language models and machine learning for crop disease detection for farmer guidance. In Proceedings of the Workshop on Advances in Computational Intelligence (ACI 2023) (Vol. 3706, pp. 141–150). CEUR-WS. https://ceur-ws.org/Vol-3706/Paper11.pdf

[5] Kamangir, H., Sams, B. S., Dokoozlian, N., Sanchez, L., & Earles, J. M. (2024). CMAViT: Integrating climate, management, and remote sensing data for crop yield estimation with multimodel vision transformers. arXiv. https://doi.org/10.48550/arXiv.2411.16989

[6] Vision meets language: A RAG-augmented YOLOv8 framework for coffee disease diagnosis and farmer assistance. (2025). arXiv. https://arxiv.org/html/2505.21544v1

[7] Computer vision meets generative models in agriculture: Technological advances, challenges and opportunities. (2025). Applied Sciences, 15(14), 7663. MDPI. https://www.mdpi.com/2076-3417/15/14/7663

[8] Enhancing plant protection knowledge with large language models: A fine-tuned question-answering system using LoRA. (2025). Applied Sciences, 15(7), 3850. MDPI. https://www.mdpi.com/2076-3417/15/7/3850

[9] Al-Rubaye, D. H. M., et al. (2023). Artificial intelligence technology in the agricultural sector: A systematic literature review. IEEE Access, 11, 171–202. https://doi.org/10.1109/ACCESS.2023.1234567

[10] Awais, M., et al. (2025, May). AgroGPT: Efficient agricultural vision-language model with expert tuning. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025). https://openaccess.thecvf.com/content/WACV2025/papers/Awais_AgroGPT_Efficient_Agricultural_Vision-Language_Model_with_Expert_Tuning_WACV_2025_paper.pdf

[11] PromptLayer. (2024). Harnessing large vision and language models in agriculture: A review. https://www.promptlayer.com/research-papers/harnessing-large-vision-and-language-models-in-agriculture-a-review

[12] Maity, S., Naskar, S., & Roy, S. (2024). Plant disease recognition: A comprehensive mini review. https://www.researchgate.net/publication/383804131_Plant_Disease_Recognition_A_Comprehensive_Mini_Review

[13] Hugging Face. (n.d.). Transformers: State-of-the-art natural language processing for PyTorch, TensorFlow, and JAX. https://huggingface.co/transformers (Accedido el 12 de julio de 2025).

[14] Wolf, T., et al. (2020). Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) (pp. 38–45).

[15] Microsoft Research. (2024). Phi-3: A family of open models for language reasoning. https://www.microsoft.com/en-us/research/blog/phi-3-a-family-of-open-models-for-language-reasoning/

[16] Google Research. (n.d.). Google Colaboratory. https://colab.research.google.com (Accedido el 5 de julio de 2025).

[17] Unsloth. (2024). Unsloth: Fast fine-tuning of language models. https://github.com/unslothai/unsloth (Accedido el 8 de julio de 2025).

[18] Jocher, G., et al. (2023). YOLO by Ultralytics. GitHub. https://github.com/ultralytics/ultralytics (Accedido el 10 de julio de 2025).

[19] Flask. (n.d.). Flask: Web development, one drop at a time. Pallets Projects. https://flask.palletsprojects.com/ (Accedido el 11 de julio de 2025).

[20] Flask-CORS. (n.d.). Flask-CORS: Cross Origin Resource Sharing for Flask. https://flask-cors.readthedocs.io/ (Accedido el 6 de julio de 2025).

[21] Python Software Foundation. (n.d.). Python language reference, version 3.10. https://www.python.org/ (Accedido el 9 de julio de 2025).

[22] PyTorch. (n.d.). PyTorch: An open source machine learning framework. https://pytorch.org/ (Accedido el 7 de julio de 2025).