Use of artificial intelligence in the detection of coffee rust: An exploratory systematic review
DOI:
https://doi.org/10.62486/latia202490Keywords:
Hemileia vastatrix, machine learning, CNN, SVM, Random ForestAbstract
Coffee rust, caused by the fungus Hemileia vastatrix, is a fungal disease that affects coffee production and quality, so its early detection is crucial to prevent massive outbreaks and protect production. This article analyzes the most effective factors, the algorithms used, the accuracy of the models, and the challenges in the detection of coffee rust, through an exploratory systematic review of 35 empirical articles obtained from Scopus, IEEE Xplore and SciELO. The review identifies that the most determinant factors for detection include humidity, temperature and the presence of shade. The most commonly used algorithms are Convolutional Neural Networks (CNN), Support Vector Machines (SVM) and Random Forest, highlighting CNN for its ability to process and analyze images with an accuracy of 99.57%, followed by Artificial Neural Networks (ANN) with 98% and SVM with 96%. However, it is concluded that challenges remain such as the need for high quality labeled datasets, variability in environmental conditions and implementation costs. This study provides a comprehensive overview of recent advances and areas for improvement in coffee rust detection, providing information for researchers, practitioners and decision makers in the agricultural sector.
References
Novtahaning D, Shah HA, Kang JM. Deep Learning Ensemble-Based Automated and High-Performing Recognition of Coffee Leaf Disease. Agriculture [Internet]. 2022;12(11):1909. DOI: https://doi.org/10.3390/agriculture12111909
Esgario JGM, de Castro PBC, Tassis LM, Krohling RA. An app to assist farmers in the identification of diseases and pests of coffee leaves using deep learning. Inf Process Agric [Internet]. 2022;9(1):38–47. DOI: https://doi.org/10.1016/j.inpa.2021.01.004
Soares A da S, Vieira BS, Bezerra TA, Martins GD, Siquieroli ACS. Early Detection of Coffee Leaf Rust Caused by Hemileia vastatrix Using Multispectral Images. Agronomy [Internet]. 2022;12(12):2911. DOI: https://doi.org/10.3390/agronomy12122911
Velásquez D, Sánchez A, Sarmiento S, Velásquez C, Toro M, Montoya E, et al. A Cyber-Physical Data Collection System Integrating Remote Sensing and Wireless Sensor Networks for Coffee Leaf Rust Diagnosis. Sensors [Internet]. 2021;21(16):5474. DOI: https://doi.org/10.3390/s21165474
Velásquez D, Sánchez A, Sarmiento S, Toro M, Maiza M, Sierra B. A Method for Detecting Coffee Leaf Rust through Wireless Sensor Networks, Remote Sensing, and Deep Learning: Case Study of the Caturra Variety in Colombia. Appl Sci [Internet]. 2020;10(2):697. DOI: https://doi.org/10.3390/app10020697
Motisi N, Bommel P, Leclerc G, Robin MH, Aubertot JN, Butron AA, et al. Improved forecasting of coffee leaf rust by qualitative modeling: Design and expert validation of the ExpeRoya model. Agric Syst [Internet]. 2022;197:103352. DOI: https://doi.org/10.1016/j.agsy.2021.103352
Marin DB, Ferraz GA e S, Santana LS, Barbosa BDS, Barata RAP, Osco LP, et al. Detecting coffee leaf rust with UAV-based vegetation indices and decision tree machine learning models. Comput Electron Agric [Internet]. 2021;190:106476. DOI: https://doi.org/10.1016/j.compag.2021.106476
Martinez F, Montiel H, Martinez F. A Machine Learning Model for the Diagnosis of Coffee Diseases. Int J Adv Comput Sci Appl [Internet]. 2022;13(4). DOI: https://doi.org/10.14569/IJACSA.2022.01304110
Debasu Mengistu A, Mengistu SG, Alemayehu DM. An Automatic Coffee Plant Diseases Identification Using Hybrid Approaches of Image Processing and Decision Tree. Indones J Electr Eng Comput Sci [Internet]. 2018;9(3):806. DOI: https://doi.org/10.11591/ijeecs.v9.i3.pp806-811
Codina L. Scoping reviews: características, frameworks principales y uso en trabajos académicos. 2021; Available from: https://www.lluiscodina.com/scoping-reviews-guia/
Munn Z, Peters MDJ, Stern C, Tufanaru C, McArthur A, Aromataris E. Systematic review or scoping review? Guidance for authors when choosing between a systematic or scoping review approach. BMC Med Res Methodol [Internet]. 2018;18(1):143. DOI: https://doi.org/10.1186/s12874-018-0611-x
Kitchenham B, Charters S. Guidelines for performing Systematic Literature Reviews in Software Engineering. Keele Univ y Univ Durham [Internet]. 2007; Available from: https://legacyfileshare.elsevier.com/promis_misc/525444systematicreviewsguide.pdf
Alba JRG, Franco RR, Cerdán MA. Sistemas expertos en agricultura de precisión: revisión sistemática de la literatura. Rev Int Desarro Reg Sustentable [Internet]. 2022;7(1–2):247–64. Available from: http://www.rinderesu.com/index.php/rinderesu/article/view/144
Lozada G, Valencia G, Lasso E, Corrales JC. Coffee Rust Detection Based on a Graph Similarity Approach. In 2018. p. 82–96. DOI: https://doi.org/10.1007/978-3-319-70187-5_7
Dumbá Monteiro de Castro G, Ferreira Vilela E, Luísa Ribeiro de Faria A, Antônio Silva R, Pinto Marques Ferreira W. New vegetation index for monitoring coffee rust using sentinel-2 multispectral imagery. Coffee Sci [Internet]. 2023;18:1–13. DOI: https://doi.org/10.25186/.v18i.2170
Lasso E, Valencia O, Corrales DC, López ID, Figueroa A, Corrales JC. A Cloud-Based Platform for Decision Making Support in Colombian Agriculture: A Study Case in Coffee Rust. In 2018. p. 182–96. DOI: https://doi.org/10.1007/978-3-319-70187-5_14
Rodríguez JP, Girón EJ, Corrales DC, Corrales JC. A Guideline for Building Large Coffee Rust Samples Applying Machine Learning Methods. In 2018. p. 97–110. DOI: https://doi.org/10.1007/978-3-319-70187-5_8
Rodriguez-Gallo Y, Escobar-Benitez B, Rodriguez-Lainez J. Robust Coffee Rust Detection Using UAV-Based Aerial RGB Imagery. AgriEngineering [Internet]. 2023 Aug 21;5(3):1415–31. DOI: https://doi.org/10.3390/agriengineering5030088
Castro W, Oblitas J, Maicelo J, Avila-George H. Evaluation of Expert Systems Techniques for Classifying Different Stages of Coffee Rust Infection in Hyperspectral Images. Int J Comput Intell Syst [Internet]. 2018;11(1):86. DOI: https://doi.org/10.2991/ijcis.11.1.8
Huatangari LQ, Ocaña Zúñiga CL, Huaccha Castillo AE, Acosta Jacinto RE, Milla Pino ME, Julcapoma MR, et al. Detection of Rust Emergence in Coffee Plantations using Data Mining: A Systematic Review. Online J Biol Sci [Internet]. 2022;22(2):157–64. DOI: https://doi.org/10.3844/ojbsci.2022.157.164
Corrales DC, Lasso E, Casas AF, Ledezma A, Corrales JC. Estimation of coffee rust infection and growth through two-level classifier ensembles based on expert knowledge. Int J Bus Intell Data Min [Internet]. 2018;13(4):369. DOI: https://doi.org/10.1504/IJBIDM.2018.094984
Beasley EM, Aristizábal N, Bueno EM, White ER. Spatially explicit models predict coffee rust spread in fragmented landscapes. Landsc Ecol. 2022;37(8):2165–78. DOI: https://doi.org/10.1007/s10980-022-01473-1
Calderón CER, Velandia JB, Ayala SCV. Supervised Model for the Detection of Coffee Leaf Diseases by Image Analysis. Rev Int Sist Intel y Apl en Ing [Internet]. 2023;11(3):405–11.
Buitrón EJG, Corrales DC, Avelino J, Iglesias JA, Corrales JC. Rule-based expert system for detection of coffee rust warnings in colombian crops. Pinto D, Singh V, editors. J Intell Fuzzy Syst [Internet]. 2019;36(5):4765–75. DOI: https://doi.org/10.3233/JIFS-179025
Carvalho HF, Ferrão LFV, Galli G, Nonato JVA, Padilha L, Maluf MP, et al. On the accuracy of threshold genomic prediction models for leaf miner and leaf rust resistance in arabica coffee. Tree Genet Genomes [Internet]. 2023;19(1):11. DOI: https://doi.org/10.1007/s11295-022-01581-8
Marcos AP, Silva Rodovalho NL, Backes AR. Coffee Leaf Rust Detection Using Genetic Algorithm. In: 2019 XV Workshop de Visão Computacional (WVC) [Internet]. IEEE; 2019. p. 16–20. DOI: https://doi.org/10.1109/WVC.2019.8876934
Marcos AP, Silva Rodovalho NL, Backes AR. Coffee Leaf Rust Detection Using Convolutional Neural Network. In: 2019 XV Workshop de Visão Computacional (WVC) [Internet]. IEEE; 2019. p. 38–42. DOI: https://doi.org/10.1109/WVC.2019.8876931
Paulos EB, Woldeyohannis MM. Detection and Classification of Coffee Leaf Disease using Deep Learning. In: 2022 International Conference on Information and Communication Technology for Development for Africa (ICT4DA) [Internet]. IEEE; 2022. p. 1–6. DOI: https://doi.org/10.1109/ICT4DA56482.2022.9971300
Lasso E, Motisi N, Avelino J, Corrales JC. FramePests: A Comprehensive Framework for Crop Pests Modeling and Forecasting. IEEE Access [Internet]. 2021;9:115579–98. DOI: https://doi.org/10.1109/ACCESS.2021.3104537
Lasso E, Corrales DC, Avelino J, de Melo Virginio Filho E, Corrales JC. Discovering weather periods and crop properties favorable for coffee rust incidence from feature selection approaches. Comput Electron Agric [Internet]. 2020;176:105640. DOI: https://doi.org/10.1016/j.compag.2020.105640
Hitimana E, Sinayobye OJ, Ufitinema JC, Mukamugema J, Rwibasira P, Murangira T, et al. An Intelligent System-Based Coffee Plant Leaf Disease Recognition Using Deep Learning Techniques on Rwandan Arabica Dataset. Technologies [Internet]. 2023;11(5):116. DOI: https://doi.org/10.3390/technologies11050116
Wu W, Wang G, Wang H, Gbokie T, He C, Huang X, et al. Development of a loop-mediated isothermal amplification assay for rapid and sensitive detection of Hemileia vastatrix in coffee plantations. Trop Plant Pathol [Internet]. 2024;49(4):515–24. DOI: https://doi.org/10.1007/s40858-023-00627-z
Belan LL, Belan LL, da Matta Rafael A, Gonçalves Gomes CA, Alves FR, Cintra de Jesus Junior W, et al. Standard area diagram with color photographs to estimate the severity of coffee leaf rust in Coffea canephora. Crop Prot [Internet]. 2020;130:105077. DOI: https://doi.org/10.1016/j.cropro.2020.105077
Chavarro AF, Renza D, Ballesteros DM. Influence of Hyperparameters in Deep Learning Models for Coffee Rust Detection. Appl Sci [Internet]. 2023;13(7):4565. DOI: https://doi.org/10.3390/app13074565
Caballero EMT, Duke AMR. Implementation of Artificial Neural Networks Using NVIDIA Digits and OpenCV for Coffee Rust Detection. In: 2020 5th International Conference on Control and Robotics Engineering (ICCRE) [Internet]. IEEE; 2020. p. 246–51. DOI: https://doi.org/10.1109/ICCRE49379.2020.9096435
Incahuanaco-Quispe F, Hinojosa-Cardenas E, Pilares-Figueroa DA, Beltrán-Castañón CA. CoffeeSE: Interpretable Transfer Learning Method for Estimating the Severity of Coffee Rust. In 2022. p. 340–55. DOI: https://doi.org/10.1007/978-3-031-04447-2_23
Sousa IC de, Nascimento M, Silva GN, Nascimento ACC, Cruz CD, Silva FF e, et al. Genomic prediction of leaf rust resistance to Arabica coffee using machine learning algorithms. Sci Agric [Internet]. 2021;78(4). DOI: https://doi.org/10.1590/1678-992x-2020-0021
S R, R S. Clustering-based Hemileia Vastatrix Disease Prediction in Coffee Leaf using Deep Belief Network. In: 2023 8th International Conference on Communication and Electronics Systems (ICCES) [Internet]. IEEE; 2023. p. 1094–100. DOI: https://doi.org/10.1109/ICCES57224.2023.10192835
Kumar M, Gupta P, Madhav P, Sachin. Disease Detection in Coffee Plants Using Convolutional Neural Network. In: 2020 5th International Conference on Communication and Electronics Systems (ICCES) [Internet]. IEEE; 2020. p. 755–60. DOI: https://doi.org/10.1109/ICCES48766.2020.9138000
Estrada-Peraza E, Alvarez-Huezo E, Girón-Morales G, Rodriguez-Gallo Y. RGB Image-Based Coffee Rust Detection: Application of Vegetation Indices and Algorithm Development. In: 2023 IEEE Central America and Panama Student Conference (CONESCAPAN) [Internet]. IEEE; 2023. p. 23–8. DOI: https://doi.org/10.1109/CONESCAPAN60431.2023.10328429
Chemura A, Mutanga O, Sibanda M, Chidoko P. Machine learning prediction of coffee rust severity on leaves using spectroradiometer data. Trop Plant Pathol [Internet]. 2018;43(2):117–27. DOI: https://doi.org/10.1007/s40858-017-0187-8
Gagliardi S, Avelino J, Beilhe LB, Isaac ME. Contribution of shade trees to wind dynamics and pathogen dispersal on the edge of coffee agroforestry systems: A functional traits approach. Crop Prot [Internet]. 2020;130:105071. DOI: https://doi.org/10.1016/j.cropro.2019.105071
Cruz-Estrada LG, Luna-Ramírez WA. Early Detection of Rust in Coffee Plantations Through Convolutional Neural Networks. In 2023. p. 894–904. DOI: https://doi.org/10.1007/978-3-031-37963-5_62
Suparyanto T, Firmansyah E, Wawan Cenggoro T, Sudigyo D, Pardamean B. Detecting Hemileia vastatrix using Vision AI as Supporting to Food Security for Smallholder Coffee Commodities. IOP Conf Ser Earth Environ Sci [Internet]. 2022;998(1):012044. DOI: https://doi.org/10.1088/1755-1315/998/1/012044
Montalbo FJP, Hernandez AA. An Optimized Classification Model for Coffea Liberica Disease using Deep Convolutional Neural Networks. In: 2020 16th IEEE International Colloquium on Signal Processing & Its Applications (CSPA) [Internet]. IEEE; 2020. p. 213–8. DOI: https://doi.org/10.1109/CSPA48992.2020.9068683
Faisal M, Leu JS, Darmawan JT. Model Selection of Hybrid Feature Fusion for Coffee Leaf Disease Classification. IEEE Access [Internet]. 2023;11:62281–91. DOI: https://doi.org/10.1109/ACCESS.2023.3286935
Published
Issue
Section
License
Copyright (c) 2024 Richard Injante, Karen Chamaya (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
