Publicado
Versiones
- 2025-07-09 (2)
- 2024-08-13 (1)
Identificación de los factores que limitan el rendimiento de la producción de maíz a partir de datos observacionales
Identification of yield-limiting factors on maize production from observational data
DOI:
https://doi.org/10.15446/acag.v72n3.106012Palabras clave:
análisis factorial, cereales, clima, factores del suelo, minería de datos, prácticas agrícolas (es)agricultural practices, cereals, climate, data mining, factorial analysis, soil factors (en)
Descargas
Siguiendo el enfoque de la Agricultura Específica de Sitio, este estudio identificó los factores limitantes de rendimiento del clima, el suelo y el manejo en la producción de maíz. La información se obtuvo de las observaciones de los agricultores sobre los eventos de cultivo, entre 2013 y 2016 en Tolima, una de las regiones con mayor producción de maíz en Colombia. Utilizando técnicas de Random Forest, análisis factorial y clúster, se determinaron los factores de clima, suelo y manejo, relacionados con la variación del rendimiento del cultivo. Mediante el análisis de regresión Random Forest, los factores de clima y suelo explicaron el 23% y el 32% de la variación del rendimiento, respectivamente. La humedad relativa, la temperatura media y la precipitación fueron los factores climáticos más importantes asociados a la variación del rendimiento, mientras que la pendiente y el moteado fueron los factores edáficos más importantes. El análisis factorial en combinación con técnicas de clúster, permitió establecer grupos con condiciones climáticas y edáficas similares. Entre esos grupos se diferenciaron las prácticas agrícolas que favorecen los rendimientos, como la mecanización, la fertilización y el manejo de la humedad del grano. Los resultados muestran un enfoque para caracterizar los sistemas productivos a partir de datos observacionales.
Following the approach of Site-Specific Agriculture, this study identified the yield-limiting factors of climate, soil, and management on maize production. The information was obtained from farmers’ observations on cropping events, between 2013 and 2016 in Tolima, one of the regions with the highest maize production in Colombia. Using Random Forest, factorial analysis and cluster techniques, the climate, soil and management factors related to crop yield variation were determined. Based on Random Forest regression, climate and soil factors explained 23% and 32% of yield variation, respectively. Relative humidity, average temperature, and precipitation were the most important climate factors associated with crop yield variation, while the slope and mottling were the most important soil factors. The factorial analysis in combination with cluster techniques allowed to establish groups with similar climate and soil conditions. Among those groups, the agricultural practices that favour yields, such as mechanization, fertilization, and management of grain moisture, were differentiated. The results showed an approach to characterizing productive systems by leveraging observational data.
Referencias
Álvarez, Diana Milena, Marcela Estrada, and James H. Cock. (2004). “RASTA Rapid Soil and Terrain Assessment: Guía Práctica Para La Caracterización Del Suelo y Del Terreno.” Cali, Colombia.
Benitez, M.-S., Osborne, S. L., & Lehman, R. M. (2017). Previous crop and rotation history effects on maize seedling health and associated rhizosphere microbiome. Scientific Reports, 7(1), 15709. https://doi.org/10.1038/s41598-017-15955-9
Bojanowsky, J. S. (2015). Sirad: Functions for calculating daily solar radiation and evapotranspiration. https://cran.r-project.org/web/packages/sirad/sirad.pdf
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 1–33. https://doi.org/10.1017/CBO9781107415324.004
Cock, J., & Luna, C. A. (1996). Analysis of large commercial databases for decision making. In Sugar 2000 Symposium (pp. 24–25). CSIRO. https://www.researchgate.net/publication/312586486_Analysis_of_large_commercial_databases_for_decision_making
Cock, J. H., Álvarez, D. M., Estrada, M. (2004). RASTA rapid soil and terrain assessment: Guía práctica para la caracterización del suelo y del terreno. Cali, Colombia.
Cock, J., Oberthür, T., Isaacs, C., Läderach, P. R., Palma, A., Carbonell, J., Victoria, J., et al. (2011). Crop management based on field observations: Case studies in sugarcane and coffee. Agricultural Systems, 104(9), 755–769. https://doi.org/10.1016/j.agsy.2011.07.001
Cordano, E., & Eccel, E. (2012). RMAWGEN: Multi-site auto-regressive weather generator (R Package). https://cran.r-project.org/web/packages/RMAWGEN/RMAWGEN.pdf
Cortés B., C. A., Bernal, J., Díaz A., E., & Méndez, J. (2013). Uso del modelo Aquacrop para estimar rendimientos para el cultivo de maíz en los departamentos de Córdoba, Meta, Tolima y Valle de Cauca. FAO.
Delerce, S., Dorado, H., Grillon, A., Rebolledo, M. C., Prager, S. D., Patiño, V. H., Garcés Varón, G., & Jiménez, D. (2016). Assessing weather-yield relationships in rice at local scale using data mining approaches. PloS ONE, 11(8), e0161620. https://doi.org/10.1371/journal.pone.0161620
FENALCE. (2010a). Aspectos técnicos de la producción de maíz en Colombia. Federación Nacional de Cerealistas.
FENALCE. (2010b). El cultivo de maíz, historia e importancia. El Cerealista.
FENALCE. (2017). Informe de gestión 2017-A. http://fenalce.org/siembras/archivos_lt/lt_246IG-FNC-2017-A.pdf
Grömping, U. (2015). Variable importance in regression models. Wiley Interdisciplinary Reviews: Computational Statistics, 7(2), 137–152. https://doi.org/10.1002/wics.1346
Husson, F., Josse, J., & Pagès, J. (2010). Principal component methods - hierarchical clustering - partitional clustering: Why would we need to choose for visualizing data? Technical Report of the Applied Mathematics Department (Agrocampus). http://www.sthda.com/english/upload/hcpc_husson_josse.pdf
Instituto Geográfico Agustín Codazzi (IGAC). (2004). Estudio general de suelos y zonificación de tierras. Departamento de Tolima.
Isaacs, C., Carrillo, C., Carbonell, J. A., Anderson, A., & Ortiz, U. (2004). Desarrollo de un sistema interactivo de información en web con el enfoque de agricultura específica por sitio (Serie Técnica 34). Cenicaña. https://www.cenicana.org/pdf_privado/serie_tecnica/st_34/st_34.pdf
Isaacs, C. H., Carbonell, J. A., Amaya, A., Torres, J. S., Victoria, J. I., Quintero, R., Palma, A. E., & Cock, J. H. (2007). Site specific agriculture and productivity in the Colombian sugar industry. In Proceedings of the 26th Congress International Society of Sugar Cane Technologists (ISSCT) (pp. 339–350). Proc. Int. Soc. Sugar Cane Technol., 26.
Jeong, J. H., Resop, J. P., Mueller, N. D., Fleisher, D. H., Yun, K., Butler, E. E., Timlin, D. J., Shim, K. M., Gerber, J. S., Reddy, V. R., & Kim, S. H. (2016). Random forests for global and regional crop yield predictions. PloS ONE, 11(6), e0156571. https://doi.org/10.1371/journal.pone.0156571
Jiménez, D., Cock, J., Jarvis, A., Garcia, J., Satizábal, H. F., Van Damme, P., Pérez-Uribe, A., & Barreto-Sanz, M. A. (2011). Interpretation of commercial production information: A case study of lulo (Solanum quitoense), an under-researched Andean fruit. Agricultural Systems, 104(3), 258–270. https://doi.org/10.1016/j.agsy.2010.10.004
Jiménez, D., Cock, J., Satizábal, H. F., Barreto S, M. A., Pérez-Uribe, A., Jarvis, A., & Van Damme, P. (2009). Analysis of Andean blackberry (Rubus glaucus) production models obtained by means of artificial neural networks exploiting information collected by small-scale growers in Colombia and publicly available meteorological data. Computers and Electronics in Agriculture, 69(2), 198–208. https://doi.org/10.1016/j.compag.2009.08.008
Jiménez, D., Dorado, H., Cock, J., Prager, S. D., Delerce, S., Grillon, A., Andrade Bejarano, M., Benavides, H., & Jarvis, A. (2016). From observation to information: Data-driven understanding of on farm yield variation. PloS ONE, 11(3), e0150015. https://doi.org/10.1371/journal.pone.0150015
Jiménez, D., Pérez-Uribe, A., Satizábal, H. F., Barreto, M., Van Damme, P., & Tomassini, M. (2008). A survey of artificial neural network-based modeling in agroeclogy. In B. Prasad (Ed.), Soft computing applications in industry (Vol. 226, pp. 1–17). Springer. https://doi.org/10.1007/978-3-540-77465-5_13
Kamar, S. S. A., Khan, M. H., & Uddin, M. S. (2018). Effect of irrigation and mulch on maize yield (Zea mays) in southern areas of Bangladesh. Journal of Agricultural Crop Research, 6(June), 28–37. http://www.sciencewebpublishing.net/jacr/archive/2018/June/pdf/Kamar%20et%20al.pdf
Kihara, J., Tamene, L. D., Massawe, P., & Bekunda, M. (2015). Agronomic survey to assess crop yield, controlling factors and management implications: A case-study of Babati in northern Tanzania. Nutrient Cycling in Agroecosystems, 102(1), 5–16. https://doi.org/10.1007/s10705-014-9648-3
Kosaki, T., Wasano, K., & Juo, A. S. R. (1989). Multivariate statistical analysis of yield-determining factors. Soil Science and Plant Nutrition, 35(4), 597–607.
Kuhn, M., Wing, J., Weston, S., Williams, A., Keefer, C., Engelhardt, A., Cooper, T., et al. (2023). Caret: Classification and regression training. https://cran.r-project.org/package=caret
Long, N. V., Assefa, Y., Schwalbert, R., & Ciampitti, I. A. (2017). Maize yield and planting date relationship: A synthesis-analysis for US high-yielding contest-winner and field research data. Frontiers in Plant Science, 8, 2106. https://doi.org/10.3389/fpls.2017.02106
Ministerio de Agricultura y Desarrollo Rural (MADR). (2017). Evaluaciones agropecuarias municipales. Bogotá, Colombia. http://www.agronet.gov.co
Marques da Silva, J. R., & Silva, L. L. (2008). Evaluation of the relationship between maize yield spatial and temporal variability and different topographic attributes. Biosystems Engineering, 101(2), 183–190. https://doi.org/10.1016/j.biosystemseng.2008.07.003
Mendiburu, F. de. (2013). Statistical procedures for agricultural research (R package version 1.3-68). https://cran.r-project.org/web/packages/agricolae/agricolae.pdf
Miao, J., & Niu, L. (2016). A survey on feature selection. Procedia Computer Science, 91, 919–926. https://doi.org/10.1016/J.PROCS.2016.07.111
Morales-Ruiz, A., Loeza-Corte, J. M., Díaz-López, E., Morales-Rosales, E. J., Franco-Mora, O., Mariezcurrena-Berasaín, M. D., & Estrada-Campuzano, G. (2016). Efficiency on the use of radiation and corn yield under three densities of sowing. International Journal of Agronomy, 2016, 6959708. https://doi.org/10.1155/2016/6959708
Oke, O. F. (2016). Effects of agro-climatic variables on yield of Zea mays L. in a humid tropical rainforest agroecosystem. African Journal of Agricultural Research, 6(1), 148–151. https://core.ac.uk/download/pdf/234664471.pdf
Ritchie, S. W., & Hanway, J. J. (1982). How a corn plant develops (Special Report No. 48). Iowa State University of Science and Technology, Cooperative Extension Service. https://publications.iowa.gov/18027/1/How%20a%20corn%20plant%20develops001.pdf
Runge, E. C. A. (1968). Effects of rainfall and temperature interactions during the growing season on corn yield. Agronomy Journal, 60(5), 503. https://doi.org/10.2134/agronj1968.00021962006000050018x
Sagarin, R., & Pauchard, A. (2010). Observational approaches in ecology open new ground in a changing world. Frontiers in Ecology and the Environment, 8(7), 379–386. https://doi.org/10.1890/090001
Sandri, M., & Zuccolotto, P. (2006). Variable selection using random forests. In Data analysis, classification and the forward search (pp. 263–270). Springer. https://doi.org/10.1007/3-540-35978-8_30
Sebastien, L., Julie, J., & Francois, H. (2008). FactoMineR: An R package for multivariate analysis. Journal of Statistical Software, 25, 1–18. https://doi.org/10.18637/jss.v025.i01
Shmueli, G. (2010). "To Explain or to Predict?." Statist. Sci. 25 (3) 289 – 310. https://doi.org/10.1214/10-STS330
Westcott, N. E., Hollinger, S. E., & Kunkel, K. E. (2005). Use of real-time multisensor data to assess the relationship of normalized corn yield with monthly rainfall and heat stress across the central United States. Journal of Applied Meteorology, 44(11), 1667–1676. https://doi.org/10.1175/JAM2303.1
Cómo citar
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Descargar cita
Licencia

Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.
Política sobre Derechos de autor:Los autores que publican en la revista se acogen al código de licencia creative commons 4.0 de atribución, no comercial, sin derivados.
Es decir, que aún siendo la Revista Acta Agronómica de acceso libre, los usuarios pueden descargar la información contenida en ella, pero deben darle atribución o reconocimiento de propiedad intelectual, deben usarlo tal como está, sin derivación alguna y no debe ser usado con fines comerciales.














