Formulación de un modelo para determinar las zonas actuales y potenciales de cultivo de aguacate Hass (Persea americana Mill) en el departamento de Risaralda a partir de variables edafoclimáticas y de calidad del fruto

DOI: https://doi.org/10.31908/19098367.2993
Palabras clave: Aguacate Hass, Aprendizaje Automático, Random Forest, Zonas Potenciales de Cultivos

Resumen

La agricultura es uno de los pilares fundamentales de cualquier población a nivel mundial y el manejo adecuado de información permite tomar decisiones oportunas para el avance de cualquier empresa que el ser humano desarrolle. Los entes de gobierno nacional y departamental apoyan renglones de la agricultura que emergen como una buena oportunidad de aumentar niveles de producción y de comercialización de productos [1], como es el cultivo del Aguacate (Persea americana Mill) variedad Hass. Entre los desafíos que tiene este tipo de cultivo, es encontrar zonas potenciales de siembra y productividad, con el fin de contribuir en desarrollos tecnológicos en el sector agrario, siendo beneficiarios los cultivadores de Aguacate Hass del departamento de Risaralda. Por lo tanto, con este estudio se propone formular un modelo que permita determinar zonas actuales y potenciales de cultivos de aguacate (Persea americana Mill) variedad Hass, en el departamento, con base en variables edafoclimáticas y de calidad del fruto, aprovechando las tendencias actuales de la agricultura de precisión, incluyendo técnicas derivadas del Aprendizaje Automático, como la utilización de algoritmos de Aprendizaje Supervisado, entre los cuales esta Random Forest

Descargas

La descarga de datos todavía no está disponible.

Biografía del autor

Cesar Manuel Castillo Rodriguez, Universidad Tecnológica de Pereira

Systems Engineer, M.Sc. Computer and Systems Engineering. Professor of the Universidad Tecnológica de Pereira, Faculty of Engineering, with experience in in-person higher education systems andvirtual learning environments. Researcher Group Artificial Intelligence (GIA) from Universidad Tecnológica de Pereira. Areas of interest and teaching related to Data Scienceand Precision Agriculture. Studies are oriented toward the development of projects, the maximization of technological, physical, and environmental resources, andthe consolidation of work groups.

Gloria Edith Guerrero Alvarez, Universidad Tecnológica de Pereira

Chemistry graduated on December 15, 1992 from the National University of Colombia, Bogotá, as a doctor in chemical sciences. The title wasawarded on April 6, 2001 by the National University of Colombia, Bogotá. researcher at Cenipalma headquarters in Bogotá and currently a professor at the Technological University of Pereira assigned to the Chemical Technology program of the Faculty of Technology, linked since February 6, 2004. The areas of interest are: agrochemistry, particularly studies of plant protection plants, use of secondary metabolites for the selection of promising materials, valorization of agricultural and agroindustrial byproducts,and applications of precision agriculture in commercial crops of national interest.

Julio César Chavarro Porras, Universidad Tecnológica de Pereira

Systems and computing engineer, from Universidad Distrital Francisco José de Caldas Bogotá, Colombia. Specialist in physical instrumentation from Universidad Tecnológica de Pereira. Ph.D. engineering, emphasis in computer science. Director Group Artificial Intelligence (GIA) from Universidad Tecnológica de Pereira He has been a professor-researcher of Universidad Tecnológica de Pereira for over26 years. He has been active in research groups whose areas of interest and teaching are related to software engineering and AI.

César Augusto Jaramillo Acevedo, Universidad Tecnológica de Pereira

Systems and computing engineer, MSc in Systems and Computing Engineering from Universidad Tecnológica de Pereira. Director and researcher in projects related to Industry 4.0, precision agriculture, education, and business development. He has been a professor-researcher of Universidad Tecnológica de Pereira for over12 years. He has been active in research groups whose areas of interest and teaching are related to software engineering, compilers, AI, IoT systems, the cloud, distributed systems, and Industry 4.0.

Juan Pablo Arrubla Vélez, Universidad Tecnológica de Pereira

Chemist (Universidad del Quindío, 1999), MSc. in Chemistry (Universidad Industrial de Santander, 2003), Doctor in Environmental Sciences (Universidad Tecnológica de Pereira, 2016); is a professor and researcher at the School of Chemical Technology of the Technological University from Pereira, Colombia since 2006. Has skills and experience in analytical method development, gas chromatography and mass spectrometry, and sample preparation. He has also worked on research in the fields of environmental pollution, natural products, and bioenergy.

Andrés Alfonso Patiño Martínez, Universidad Tecnológica de Pereira

Engineer agronomist from the Universidad de Santa Rosa de Cabal -UNISARC in the department of Risaralda -Colombia (2002), Master's degree in Agricultural Production Systems from the University of Caldas in the department of Caldas -Colombia (2018), and Junior Researcher categorized by Minciencias. He has worked in the research area in fruits, especially Avocado, Blackberry, and Banana. Currently, he serves as the dean of the Faculty of Agricultural Sciences at UNISARC.

Citas

Perfetti, J.J., Bravo-Ureta, B.E., García, A., Pantoja, J., Delgado, M., Blanco, J., Jara, R., Moraga, C., Paredes, G., Naranjo, J., et al.: Adecuación de tierras y el desarrollo de la agricultura colombiana: políticas e instituciones. Fedesarrollo 447, 456 (2019)

El-Bendary, N., Elhariri, E., Hazman, M., Saleh, S.M., Hassanien, A.E.: Cultivation-time recommender system based on climatic conditions for newly reclaimed lands in egypt. Procedia Computer Science 96, 110–119 (2016)

Singh, R., Kumari, T., Verma, P., Singh, B.P., Raghubanshi, A.S.: Compatible package-based agriculture systems: an urgent need for agro-ecological balance and climate change adaptation. Soil Ecology Letters 4(3), 187–212 (2022)

Dreher, M.L., Davenport, A.J.: Hass avocado composition and potential health effects. Critical reviews in food science and nutrition 53(7), 738–750 (2013)

Ramírez-Gil, J.G., Ramelli, E.G., Osorio, J.G.M.: Economic impact of the avocado (cv. hass) wilt disease complex in Antioquia, Colombia, crops under different technological management levels. Crop protection 101, 103–115 (2017)

MADR, M.d.A.y.D.R.: CADENA DE AGUACATE, Indicadores e instrumentos. Lect Econ. 2019;52(52):165–94 (2019)

Martínez, D.H.F., Galvis, C.P.U.: Tic para la investigación, desarrollo e innovación del sector agropecuario (2018)

Orozco, O. A., Llano Ramírez, G.: Sistemas de información enfocados en tecnologías de agricultura de precisión y aplicables a la caña de azúcar, una revisión. Revista Ingenierías Universidad de Medellín 15(28), 103–124 (2016)

Van Klompenburg, T., Kassahun, A., Catal, C.: Crop yield prediction using machine learning: A systematic literature review. Computers and Electronics in Agriculture 177, 105709 (2020)

Machado, D.F.T., Silva, S.H.G., Curi, N., Menezes, M.D.d.: Soil type spatial prediction from random forest: different training datasets, transferability, accuracy and uncertainty assessment. Scientia Agricola 76, 243–254 (2019)

Jyothika, P., Ramana, K.V., Narayana, L.: Crop recommendation system to maximize crop yield using deep neural network.

Vite Cevallos, H., Carvajal Romero, H., Barrezueta Unda, S.: Aplicación de algoritmos de aprendizaje automático para clasificar la fertilidad de un suelo bananero. Conrado 16(72), 15–19 (2020)

Katarya, R., Raturi, A., Mehndiratta, A., Thapper, A.: Impact of machine learning techniques in precision agriculture. In: 2020 3rd International Conference on Emerging Technologies in Computer Engineering: Machine Learning and Internet of Things (ICETCE), pp. 1–6 (2020). IEEE

Geetha, V., Punitha, A., Abarna, M., Akshaya, M., Illakiya, S., Janani, A.: An effective crop prediction using random forest algorithm. In: 2020 International Conference on System, Computation, Automation and Networking (ICSCAN), pp. 1–5 (2020). IEEE

Pozdnoukhov, A., Kanevski, M.: Machine learning algorithms for analysis and modeling of geospatial data. In: Annual Conference of International Accociation for Mathematical Geology (IAMG 07), Beijing, China, 25-31 August (2007)

Carranza, J.P., Salomón, M.J., Piumetto, M.A., Monzani, F., MONTENEGRO CALVIMONTE, M., Córdoba, M.A.: Random forest como técnica de valuación masiva del valor del suelo urbano: una aplicación para la ciudad de río cuarto, córdoba, argentina. In: Congresso Brasileiro de Cadastro Técnico Multifinalitário-COBRAC (2018)

Sekulic, A., Kilibarda, M., Heuvelink, G.B., Nikoli ́c, M., Bajat, B.: Random Forest Spatial Interpolation. Remote Sensing 12(10), 1687 (2020)

Mariano, C., Monica, B.: A random forest-based algorithm for data-intensive spatial interpolation in crop yield mapping. Computers and Electronics in Agriculture 184, 106094 (2021)

Kuhn, M. Johnson, K. Kuhn, M, Johnson, K. Classification trees and rule-based models. Applied predictive modeling, 369–413 (2013)

Talebi, H., Peeters, L.J., Otto, A., Tolosana-Delgado, R.: A truly spatial random forests algorithm for geoscience data analysis and modelling. Mathematical Geosciences 54, 1–22 (2022)

Rajeshwari, M., Shunmuganathan, N., Sankarasubramanian, R.: Performance of soil prediction using machine learning for data clustering methods. Journal of Algebraic Statistics 13(2), 858–864 (2022).

FAO - GAEZ Data Portal.: Data sheet Persea americana. Available from: https://gaez.fao.org/pages/ecocrop-find-plant (2023)

Publicado
2024-06-25
Cómo citar
Castillo Rodriguez, C., Guerrero Alvarez, G., Chavarro Porras, J., Jaramillo Acevedo, C., Arrubla Vélez, J., & Patiño Martínez, A. (2024). Formulación de un modelo para determinar las zonas actuales y potenciales de cultivo de aguacate Hass (Persea americana Mill) en el departamento de Risaralda a partir de variables edafoclimáticas y de calidad del fruto. Entre Ciencia E Ingeniería, 18(35), 41-45. https://doi.org/10.31908/19098367.2993
Número
Vol. 18 Núm. 35 (2024)
Sección
Artículos
Derechos de autor 2024 Entre Ciencia e Ingeniería