Deep learning for weed detection in Mesoamerican agricultural and forest systems
DOI:
https://doi.org/10.15517/eyatrf23Keywords:
precision agriculture, computer vision, convolutional neural networks, image classificationAbstract
Introduction. Weed control is a permanent activity in tropical agricultural and forestry systems. Deep learning offers possibilities for weed detection, identification, and management. Objective. To describe the main advances and applications of deep learning for weed identification and localization and analyze its applicability as a supporting tool for weed management in agricultural and forestry systems in Mesoamerica. Development. A scientific literature review was conducted by searching for articles published between 2016 and 2025 in Scopus, Web of Science, ScienceDirect, and SpringerLink. The review was primarily based on 15 studies that applied deep learning techniques and reported performance metrics, and 15 review articles. The components of the process were identified, and a methodological route for implementation in Mesoamerica was proposed, considering the particularities of tropical agricultural and forestry systems. Deep learning models have shown favorable performance for weed recognition in various agricultural systems. No studies in forest plantations were found in the search conducted, although potential for application during the initial stages of establishment was identified. The roadmap considers the prioritization of crops, forest species, and weeds with the greatest impact, the coordinated development of databases, and the training and implementation of models. Conclusions. Deep learning presents relevant advances for weed identification and localization. Its implementation in Mesoamerica could contribute to management through precision agriculture and forestry strategies but requires representative data, field validation, and integration with decision support systems.
Downloads
References
Agüero-Alvarado, R., Rodríguez-Ruiz, A. M., González-Lutz, M. I., Portuguez-García, P., & Brenes-Prendas, S. (2018). Abundancia y cobertura de arvenses bajo manejo con-vencional y orgánico de café y banano. Agronomía Mesoamericana, 29(1), 85-93. DOI: https://doi.org/10.15517/ma.v29i1.28053
Amend, S., Brandt, D., Di Marco, D., Dipper, T., Gässler, G., Höferlin, M., Gohlke, M., Ke-senheimer, K., Lindner, P., Leidenfrost, R., Michaels, A., Mugele, T., Müller, A., Riffel, T., Sampangi, Y., & Winkler, J. (2019). Weed management of the future. KI - Künstli-che Intelligenz, 33(4), 411-415. DOI: https://doi.org/10.1007/s13218-019-00617-x
Badgujar, C. M., Poulose, A., & Gan, H. (2024). Agricultural object detection with You Only Look Once (YOLO) algorithm: a bibliometric and systematic literature review. Com-puters and Electronics in Agriculture, 223, Artículo 109090. DOI: https://doi.org/10.1016/j.compag.2024.109090
Bah, M. D., Hafiane, A., & Canals, R. (2018). Deep learning with unsupervised data labeling for weed detection in line crops in UAV images. Remote Sensing, 10(11), Artículo 1690. DOI: https://doi.org/10.3390/rs10111690
Benos, L., Tagarakis, A. C., Dolias, G., Berruto, R., Kateris, D., & Bochtis, D. (2021). Ma-chine learning in agriculture: a comprehensive updated review. Sensors, 21(11), Ar-tículo 3758. DOI: https://doi.org/10.3390/s21113758
Cai, Z., & Vasconcelos, N. (2018). Cascade R-CNN: delving into high quality object detec-tion. En D. Forsyth, I. Laptev, A. Oliva, & D. Ramanan (Eds.), 2018 IEEE/CVF Con-ference on Computer Vision and Pattern Recognition (CVPR) (pp. 6154-6162). IEEE. DOI: https://doi.org/10.1109/CVPR.2018.00644
Chicco, D., & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Geno-mics, 21(1), Artículo 6. DOI: https://doi.org/10.1186/s12864-019-6413-7
Ciaglia, F., Zuppichini, F. S., Guerrie, P., McQuade, M., & Solawetz, J. (2022). Roboflow 100: a rich, multi-domain object detection benchmark [Preprint]. arXiv.
Coleman, G. R., Bender, A., Hu, K., Sharpe, S. M., Schumann, A. W., Wang, Z., Bagavathi-annan, M. V., Boyd, N. S., & Walsh, M. J. (2022). Weed detection to weed recogni-tion: reviewing 50 years of research to identify constraints and opportunities for large-scale cropping systems. Weed Technology, 36(6), 741-757. DOI: https://doi.org/10.1017/wet.2022.84
Costello, B., Osunkoya, O. O., Sandino, J., Marinic, W., Trotter, P., Shi, B., Gonzalez, F., & Dhileepan, K. (2022). Detection of parthenium weed (Parthenium hysterophorus L.) and its growth stages using artificial intelligence. Agriculture, 12(11), Artículo 1838. DOI: https://doi.org/10.3390/agriculture12111838
Deng, B., Lu, Y., & Xu, J. (2024). Weed database development: an updated survey of public weed datasets and cross-season weed detection adaptation. Ecological Informa-tics, 81, Artículo 102546. DOI: https://doi.org/10.1016/j.ecoinf.2024.102546
Dwibedi, D., Misra, I., & Hebert, M. (2017). Cut, paste and learn: surprisingly easy synthe-sis for instance detection. En K. Ikeuchi, G. Medioni, M. Pelillo, & E. Mortensen (Eds.), 2017 IEEE International Conference on Computer Vision (ICCV) (pp. 1310-1319). IEEE. DOI: https://doi.org/10.1109/ICCV.2017.146
Dwyer, B., Nelson, J., & Hansen, T. (2025). Roboflow (Versión 1.0) [Software]. https://roboflow.com
Dyrmann, M., Karstoft, H., & Midtiby, H. S. (2016). Plant species classification using deep convolutional neural network. Biosystems Engineering, 151, 72-80. DOI: https://doi.org/10.1016/j.biosystemseng.2016.08.024
Fernandes, P., Pereira da Silva, S. D., Fantinel, R. A., Junior, N. B., de Sousa-Baracho, I. P., Schuh, M. S., Pereira, R. S., & Eugenio, F. C. (2025). Use of hyperspectral sen-sor and random forest for broadleaf and narrowleaf weed differentiation. New For-ests, 56(5), Artículo 46. DOI: https://doi.org/10.1007/s11056-025-10113-w
Gao, J., French, A. P., Pound, M. P., He, Y., Pridmore, T. P., & Pieters, J. G. (2020). Deep convolutional neural networks for image-based Convolvulus sepium detection in sugar beet fields. Plant Methods, 16, Artículo 29. DOI: https://doi.org/10.1186/s13007-020-00570-z
Garibaldi-Márquez, F., Flores, G., & Valentín-Coronado, L. M. (2025). Leveraging deep semantic segmentation for assisted weed detection. Journal of Agricultural Engi-neering, 56(2), Artículo 1741. DOI: https://doi.org/10.4081/jae.2025.1741
Garibaldi-Márquez, F., Martínez-Barba, D. A., Montañez-Franco, L. E., Flores, G., & Valen-tín-Coronado, L. M. (2025). Enhancing site-specific weed detection using deep learning transformer architectures. Crop Protection, 190, Artículo 107075. DOI: https://doi.org/10.1016/j.cropro.2024.107075
Garibaldi-Márquez, F., Valentín-Coronado, L. M., Díaz-Ponce, A., Servín-Palestina, M., García-Hernández, R. V., & Ramos-Cantú, L. (2025). Advances on deep learning for proximal image-based weed recognition and control under authentic farmlands: a state-of-the-art review. Smart Agricultural Technology, 12, Artículo 101405. DOI: https://doi.org/10.1016/j.atech.2025.101405
Georgakis, G., Mousavian, A., Berg, A. C., & Kosecka, J. (2017). Synthesizing training data for object detection in indoor scenes. En N. Amato, S. Srinivasa, N. Ayanian, & S. Kuindersma (Eds.), Robotics: Science and Systems XIII. Robotics: Science and Systems Foundation. DOI: https://doi.org/10.15607/RSS.2017.XIII.043
Girshick, R. (2015). Fast R-CNN. En R. Bajcsy, G. Hager, Y. Ma, E. Mortensen, & S. Fidler (Eds.), 2015 IEEE International Conference on Computer Vision (ICCV) (pp. 1440-1448). IEEE. DOI: https://doi.org/10.1109/ICCV.2015.169
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accu-rate object detection and semantic segmentation. En R. Basri, C. Fermuller, A. Mar-tinez, & R. Vidal (Eds.), 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 580-587). IEEE. DOI: https://doi.org/10.1109/CVPR.2014.81
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press. https://www.deeplearningbook.org/
Guevara-Bonilla, M., Meza-Leandro, A. S., Esquivel-Segura, E. A., Arias-Aguilar, D., Tapia-Arenas, A., & Masís-Meléndez, F. (2020). Uso de vehículos aéreos no tripulados (VANTs) para el monitoreo y manejo de los recursos naturales: una síntesis. Revis-ta Tecnología en Marcha, 33(4), 77-88. DOI: https://doi.org/10.18845/tm.v33i4.4528
Hand, D. J. (2009). Measuring classifier performance: a coherent alternative to the area under the ROC curve. Machine Learning, 77(1), 103-123. DOI: https://doi.org/10.1007/s10994-009-5119-5
Hasan, A. M., Sohel, F., Diepeveen, D., Laga, H., & Jones, M. G. (2021). A survey of deep learning techniques for weed detection from images. Computers and Electronics in Agriculture, 184, Artículo 106067. DOI: https://doi.org/10.1016/j.compag.2021.106067
He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask R-CNN. En K. Ikeuchi, G. Me-dioni, M. Pelillo, & E. Mortensen (Eds.), 2017 IEEE International Conference on Computer Vision (ICCV) (pp. 2961-2969). IEEE. DOI: https://doi.org/10.1109/ICCV.2017.322
Herrera, P. J., Dorado, J., & Ribeiro, A. (2014). A novel approach for weed type classifica-tion based on shape descriptors and a fuzzy decision-making method. Sensors, 14(8), 15304-15324. DOI: https://doi.org/10.3390/s140815304
Hu, C., Sapkota, B. B., Thomasson, J. A., & Bagavathiannan, M. V. (2021). Influence of im-age quality and light consistency on the performance of convolutional neural net-works for weed mapping. Remote Sensing, 13(11), Artículo 2140. DOI: https://doi.org/10.3390/rs13112140
Islam, N., Rashid, M. M., Wibowo, S., Xu, C.-Y., Morshed, A., Wasimi, S. A., Moore, S., & Rahman, S. M. (2021). Early weed detection using image processing and machine learning techniques in an Australian chilli farm. Agriculture, 11(5), Artículo 387. DOI: https://doi.org/10.3390/agriculture11050387
Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: a survey. Com-puters and Electronics in Agriculture, 147, 70-90. DOI: https://doi.org/10.1016/j.compag.2018.02.016
Kaur, R., & Singh, S. (2023). A comprehensive review of object detection with deep learn-ing. Digital Signal Processing, 132, Artículo 103812. DOI: https://doi.org/10.1016/j.dsp.2022.103812
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022). Transform-ers in vision: a survey. ACM Computing Surveys, 54(10s), Artículo 200. DOI: https://doi.org/10.1145/3505244
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444. DOI: https://doi.org/10.1038/nature14539
Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., & Shi, W. (2017). Photo-realistic single image super-resolution using a generative adversarial network. En R. Chellappa, Z. Zhang, & A. Hoogs (Eds.), 2017 IEEE Conference on Computer Vision and Pattern Recogni-tion (CVPR) (pp. 105-114). IEEE. DOI: https://doi.org/10.1109/CVPR.2017.19
León, R. G., Agüero, R., & Calderón, D. (2017). Diversity and spatial heterogeneity of weed communities in a sugarcane cropping system in the dry tropics of Costa Rica. Weed Science, 65(2), 206-212. DOI: https://doi.org/10.1614/WS-D-16-00066.1
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2020). Deep learning for generic object detection: a survey. International Journal of Computer Vi-sion, 128(2), 261-318. DOI: https://doi.org/10.1007/s11263-019-01247-4
López-Granados, F. (2011). Weed detection for site-specific weed management: mapping and real-time approaches. Weed Research, 51(1), 1-11. DOI: https://doi.org/10.1111/j.1365-3180.2010.00829.x
Milioto, A., Lottes, P., & Stachniss, C. (2017). Real-time blob-wise sugar beets vs weeds classification for monitoring fields using convolutional neural networks. ISPRS An-nals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, IV-2/W3, 41-48. DOI: https://doi.org/10.5194/isprs-annals-IV-2-W3-41-2017
Minogue, P. J., & Osiecka, A. (2022). Herbicides for weed control in Eucalyptus culture (FOR310). University of Florida Institute of Food and Agricultural Sciences Exten-sion.
Mora-Delgado, J., & Acosta Arce, L. (2001). Uso, clasificación y manejo de la vegetación asociada al cultivo de café (Coffea arabica) desde la percepción campesina en Costa Rica. Agroforestería en las Américas, 8(32), 20-27.
Mora-Fallas, A., Goëau, H., Joly, A., Bonnet, P., & Mata-Montero, E. (2020). Instance seg-mentation for automated weeds and crops detection in farmlands. Tecnología en Marcha, 33(5), 13-17.
Murad, N. Y., Mahmood, T., Forkan, A. R. M., Morshed, A., Jayaraman, P. P., & Siddiqui, M. S. (2023). Weed detection using deep learning: a systematic literature review. Sen-sors, 23(7), Artículo 3670. DOI: https://doi.org/10.3390/s23073670
Murillo-Gamboa, O., Guevara-Bonilla, M., Badilla-Valverde, Y., & Esquivel-Segura, E. (2024). Manual de cultivo de melina (Gmelina arborea Roxb.) en ciclo corto. Institu-to Tecnológico de Costa Rica.
Mursalin, M., & Mesbah-Ul-Awal, M. (2014). Towards classification of weeds through digital image. In 2014 Fourth International Conference on Advanced Computing & Communication Technologies (pp. 1-4). IEEE. DOI: https://doi.org/10.1109/ACCT.2014.101
Ozcift, A., & Gulten, A. (2011). Classifier ensemble construction with rotation forest to im-prove medical diagnosis performance of machine learning algorithms. Computer Methods and Programs in Biomedicine, 104(3), 443-451. DOI: https://doi.org/10.1016/j.cmpb.2011.03.018
Patel, D., & Kumbhar, B. (2016). Weed and its management: a major threat to crop econo-my. Journal of Pharmaceutical Science and Bioscientific Research, 6(6), 753-758. https://www.jpsbr.org/volume_6/JPSBR_Vol_6_Issue_1_htm_files/JPSBR16RS6010.pdf
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: unified, re-al-time object detection. En R. Bajcsy, F.-F. Li, & T. Tuytelaars (Eds.), 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 779-788). IEEE Computer Society. DOI: https://doi.org/10.1109/CVPR.2016.91
Reedha, R., Dericquebourg, E., Canals, R., & Hafiane, A. (2022). Transformer neural net-work for weed and crop classification of high resolution UAV images. Remote Sens-ing, 14(3), Artículo 592. DOI: https://doi.org/10.3390/rs14030592
Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137-1149. DOI: https://doi.org/10.1109/TPAMI.2016.2577031
Ricci, M. D. S. F., Virgínio Filho, E. D. M., & Costa, J. R. (2008). Diversidade da comunida-de de plantas invasoras em sistemas agroflorestais com café em Turrialba, Costa Rica. Pesquisa Agropecuária Brasileira, 43(7), 825-834. DOI: https://doi.org/10.1590/S0100-204X2008000700006
Rodríguez, A. M., & Agüero, R. (2000). Identificación de malezas trepadoras del banano (Musa sp.) en la zona Caribe de Costa Rica. Agronomía Mesoamericana, 11(1), 123-125. DOI: https://doi.org/10.15517/am.v11i1.17395
Rojas, L. A., Rodríguez, J. M., Villalobos, H., Arias, M., & Méndez, E. (2003). Malezas aso-ciadas al cultivo de la caña de azúcar. Tecnología en Marcha, 16(1), 66-79. https://revistas.tec.ac.cr/index.php/tec_marcha/article/view/1457
Rubilar, R. A., Allen, H. L., Fox, T. R., Cook, R. L., Albaugh, T. J., & Campoe, O. C. (2018). Advances in silviculture of intensively managed plantations. Current Forestry Re-ports, 4(1), 23-34. DOI: https://doi.org/10.1007/s40725-018-0072-9
Russell, S., & Norvig, P. (2021). Intelligence artificielle: une approche moderne (L. Miclet, F. Popineau, & C. Cadet, Trads.; 4.ª ed.). Pearson. (Trabajo original publica-do en 2020).
Sapkota, B. B., Popescu, S., Rajan, N., Leon, R. G., Reberg-Horton, C., Mirsky, S., & Ba-gavathiannan, M. V. (2022). Use of synthetic images for training a deep learning model for weed detection and biomass estimation in cotton. Scientific Reports, 12(1), Artículo 19580. DOI: https://doi.org/10.1038/s41598-022-23399-z
Sarangi, D., & Jhala, A. J. (2018). A statewide survey of stakeholders to assess the prob-lem weeds and weed management practices in Nebraska. Weed Technology, 32(5), 642-655. DOI: https://doi.org/10.1017/wet.2018.35
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013). OverFeat: integrated recognition, localization and detection using convolutional networks [Pre-print]. arXiv.
Shanmugam, S., Assunção, E., Mesquita, R., Veiros, A., & Gaspar, P. D. (2020). Automated weed detection systems: a review. KnE Engineering, 5(6), 271-284. DOI: https://doi.org/10.18502/keg.v5i6.7046
Shehzadi, T., Hashmi, K. A., Liwicki, M., Stricker, D., & Afzal, M. Z. (2025). Object detection with transformers: a review. Sensors, 25(19), Artículo 6025. DOI: https://doi.org/10.3390/s25196025
Shetty, J., & Jogi, P. S. (2019). Study on different region-based object detection models applied to live video stream and images using deep learning. En D. Pandian, X. Fer-nando, Z. Baig, & F. Shi (Eds.), Proceedings of the International Conference on ISMAC in Computational Vision and Bio-Engineering 2018 (ISMAC-CVB) (pp. 51-60). Springer. DOI: https://doi.org/10.1007/978-3-030-00665-5_6
Skovsen, S., Dyrmann, M., Mortensen, A. K., Laursen, M. S., Gislum, R., Eriksen, J., Fark-hani, S., Karstoft, H., & Jørgensen, R. N. (2019). The GrassClover image dataset for semantic and hierarchical species understanding in agriculture. En L. Davis, P. Torr, S.-C. Zhu, W. Brendel, & M. R. Amer (Eds.), 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 2676-2684). IEEE Computer Society. DOI: https://doi.org/10.1109/CVPRW.2019.00325
Souza Silva, J. A. O., Soares de Siqueira, V., Mesquita, M., Rodrigues Vale, L. S., Borges Marques, T. do N., Bezerra da Silva, J. L., da Silva, M. V., Nunes Lacerda, L., de Oliveira-Júnior, J. F., de Lima, J. L. M. P., & Fonseca Elias de Oliveira, H. (2024). Deep learning for weed detection and segmentation in agricultural crops using im-ages captured by an unmanned aerial vehicle. Remote Sensing, 16(23), Artículo 4394. DOI: https://doi.org/10.3390/rs16234394
Szegedy, C., Toshev, A., & Erhan, D. (2013). Deep neural networks for object detection. En C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, & K. Q. Weinberger (Eds.), Advances in neural information processing systems 26 (pp. 2553-2561). Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2013/hash/f7cade80b7cc92b991cf4d2806d6bd78-Abstract.html
Tetila, E. C., Junior, G. W., Higa, G. T. H., da Costa, A. B., Amorim, W. P., Pistori, H., & Bar-bedo, J. G. A. (2025). Deep learning models for detection and recognition of weed species in corn crop. Crop Protection, 195, Artículo 107237. DOI: https://doi.org/10.1016/j.cropro.2025.107237
Tetila, E. C., Moro, B. L., Astolfi, G., da Costa, A. B., Amorim, W. P., de Souza Belete, N. A., & Barbedo, J. G. A. (2024). Real-time detection of weeds by species in soybean us-ing UAV images. Crop Protection, 184, Artículo 106846. DOI: https://doi.org/10.1016/j.cropro.2024.106846
Xiao, Y., Tian, Z., Yu, J., Zhang, Y., Liu, S., Du, S., & Lan, X. (2020). A review of object de-tection based on deep learning. Multimedia Tools and Applications, 79(33-34), 23729-23791. DOI: https://doi.org/10.1007/s11042-020-08976-6
Zhang, Y., Wang, M., Zhao, D., Liu, C., & Liu, Z. (2023). Early weed identification based on deep learning: a review. Smart Agricultural Technology, 3, Artículo 100123. DOI: https://doi.org/10.1016/j.atech.2022.100123
Zimdahl, R. L., & Basinger, N. T. (2024). Fundamentals of weed science (6.ª ed.). Acade-mic Press.
Downloads
Published
License
Copyright (c) 2026 Mario Guevara-Bonilla, Ramón León-González, Robin Gómez-Gómez (Autor/a)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
