Prediction of the yield of banana crop by means of a generalized regression artificial neural network
Keywords:
generalized regression neural network, prediction, crop yield, physical-chemical caracterization, Musa AABAbstract
Banana is an important crop in Latin America, for both large scale and small farmers. In Venezuela, the main production centers are in the area of Sur del Lago de Maracaibo. Knowing the crop yield is vital due to the need to maximize the investment-pro_t, and availability of such information in advance helps in the decision-making process of the production unit. The purpose of this research is to evaluate the ability of artificial neural networks to predict the yield of a banana crop, employing the best predictors dataset, given the physical characteristics of the soil and the chemical profile of leaf tissue. Generalized regression networks trained with the leave-one-out strategy, and two types of data transformations were used in this study. It was found that neural networks were excellent tools for predicting the yield of banana crop. The physicochemical profiles of soil and leaf tissue were suitable descriptors of the response variable. Among the data evaluated in this study, it was found that the physical data of 20-40 cm of soil was, after standardization of the training data, the best predictor group.
Downloads
References
Bauer, M. M. 1995. Generalized regression neural network for technical use. Master's Thesis, University of Wisonsin-Madison, USA.
Chacín, F., Ascanio, M., Hernández, A., García, J., Cobo, M., Ascanio, A. (2005). Predicción de cosechas en plátano (Musa AAB `Hartón') mediante dos modelos de regresión (Forward y Stepwise). Rev. Fac. Agron. (Maracay), Vol. 31. No. 1. Pp 21-35.
Elissee, A., Pontil, M. (S/A). Leave one out error and stability of learning algorithms with applications. Disponible en: http://www.citeseerx.its.psu.edu
Hernández-Caraballo, E. A. (2011). Predicción del rendimiento potencial de un cultivo de naranja `Valencia' mediante redes neuronales de regresión generalizada. Trabajo de Ascenso (sin publicar). Universidad Centroccidental Lisandro Alvarado. Venezuela.
Hernández, E., Ávila, R., Rivas, F. (2003). Las redes neuronales artificiales en química analítica. Parte I. Fundamentos. Rev. Sociedad Venezolana de Química. Vol. 26. No. 4. Pp 17-25.
International Plant Nutrition Institute (2001). Guía de Campo. Síntomas de deficiencias nutricionales y otros desordenes fisiológicos en el cultivo del banano (Musa AAA). Descripción, causas, prevención y corrección. IPNI. Disponible en:http: //nla:ipni:net/articles/NLA0070 EN/$FILE/G %20Banano:pdf:
Ji, B., Sun, Y., Yang, S., Wan, J. (2007). Artificial neural networks for rice yield prediction in mountainous regions. J. of Agricultural Sci. Vol. 145. Pp 249-261.
Khashei-Siuki, A., Kouchakzadeh, M., Ghahraman, B. (2011). Predicting dryland wheat yield from meteorological data, using expert system, Khorasan Province, Iran. J. Agr. Sci. Tech., Vol. 13. Pp627-640.
Kumar, R., Rajan, S., Singh, A. (2007). Multiple regression models for yield prediction in plantain. Indian J. of Horticulture, Vol. 64. No. 2. Pp 159-162.
Machado-Allison, C., Rivas, J.C., 2004. La agricultura en Venezuela. Ediciones IESA, Venezuela.
Marín, M., Aragón, P., Gómez, C. (2003). Análisis químico de suelo y aguas. Manual de laboratorio. Editorial UPV: Valencia. Pp 175.
Martínez, E., Delgado, E., Rey, J., Giménez, C., Pargas, R., Manzanilla, R. (2009). Producción del plátano en Venezuela y el mercado mundial. INIA Hoy, Vol. 5 mayo-agosto. Pp 125-138.
NC State University (S/F). North Caroline Winegrape Grower's Guide. Chapter 12. Crop Prediction. Disponible en: http ://cals:nscu:edu:/hortsci/extensión/documents/winegrape/winegrapesada12:pdf
Rodríguez, G. (2009). Aspectos sobre la salud radical del banano en suelos de Venezuela. Producción Agropecuaria. Vol. 2. No.1. Pp 49-52.
Rodríguez, V. (2003). Avaliacao do Estado Nutricional e da Fertilidade do Solo na Cultura do Plátano (Musa AAB Subgrupo Plátano cv. Hartón). Tesis Doctoral. USP Piracicaba, Brasil.
Rodríguez, V., Rodríguez, O., Bravo, P. (1999a). Índice de balance de nutrimentos para la predicción del rendimiento del plátano (Musa AAB subgrupo plátano Hartón). Rev. Fac. Agron. LUZ, Vol. 16. Pp 488-494.
Rodríguez, V., Bautista, D., Rodríguez, O., Díaz, L. (1999b). Relación entre el balance nutricional y la biometría del plátano (Musa AAB subgrupo plátano Hartón) y su efecto sobre el rendimiento. Rev. Fac. Agron. LUZ, Vol. 16. Pp 425-432.
Rodríguez, V., Da Silva, A., Rodríguez, O. (2005). Balance nutricional y numero de hojas como variables de predicción del rendimiento del plátano Hartón. Pesq. Agrop. Bras. Vol. 40. Pp 175-177.
Stastny, J., Konecny, V., Trenz, O. (2011). Agricultural data prediction by means of neural networks. Agric. Econ. Czech. Vol. 57. No. 7. Pp 356-361.
Published
How to Cite
Issue
Section
Creative Commons Reconocimiento-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0)
The opinions expressed by the authors do not necessarily reflect the position of the publisher of the publication or of UCLA. The total or partial reproduction of the texts published here is authorized, as long as the complete source and the electronic address of this journal are cited.
The authors fully retain the rights to their works, giving the journal the right to be the first publication where the article is presented. The authors have the right to use their articles for any purpose as long as it is done for non-profit. Authors are recommended to disseminate their articles in the final version, after publication in this journal, in the electronic media of the institutions to which they are affiliated or personal digital media.
