Comparison Between Machine Learning Models for Yield Forecast in Cocoa Crops in Santander, Colombia

Main Article Content

Autores

Henry Lamos-Díaz, Ph. D. https://orcid.org/0000-0003-1778-9768
David Esteban Puentes-Garzón, M.Sc. https://orcid.org/0000-0001-8178-2339
Diego Alejandro Zarate-Caicedo, Ph. D. https://orcid.org/0000-0001-9630-3927

Abstract

The identification of influencing factors in crop yield (kg·ha-1) provides essential information for decision-making processes related to the prediction and improvement of productivity, which gives farmers the opportunity to increase their income. The current study investigates the application of multiple machine learning algorithms for cocoa yield prediction and influencing factors identification. The Support Vector Machines (SVM) and Ensemble Learning Models (Random Forests, Gradient Boosting) are compared with Least Absolute Shrinkage and Selection Operator (LASSO) regression models. The considered predictors were climate conditions, cocoa variety, fertilization level and sun exposition in an experimental crop located in Rionegro, Santander. Results showed that Gradient Boosting is the best prediction alternative with Coefficient of determination (R2) = 68%, Mean Absolute Error (MAE) = 13.32, and Root Mean Square Error (RMSE) = 20.41. The crop yield variability is explained mainly by the radiation one month before harvest, the accumulated rainfall on the harvest month, and the temperature one month before harvest. Likewise, the crop yields are evaluated based on the kind of sun exposure, and it was found that radiation one month before harvest is the most influential factor in shade-grown plants. On the other hand, rainfall and soil moisture are determining variables in sun-grown plants, which is associated with the water requirements. These results suggest a differentiated management for crops depending on the kind of sun exposure to avoid compromising productivity, since there is no significant difference in the yield of both agricultural managements.

Keywords:

Article Details

Licence

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

All articles included in the Revista Facultad de Ingeniería are published under the Creative Commons (BY) license.

Authors must complete, sign, and submit the Review and Publication Authorization Form of the manuscript provided by the Journal; this form should contain all the originality and copyright information of the manuscript.

The authors who publish in this Journal accept the following conditions:

a. The authors retain the copyright and transfer the right of the first publication to the journal, with the work registered under the Creative Commons attribution license, which allows third parties to use what is published as long as they mention the authorship of the work and the first publication in this Journal.

b. Authors can make other independent and additional contractual agreements for the non-exclusive distribution of the version of the article published in this journal (eg, include it in an institutional repository or publish it in a book) provided they clearly indicate that the work It was first published in this Journal.

c. Authors are allowed and recommended to publish their work on the Internet (for example on institutional or personal pages) before and during the process.
review and publication, as it can lead to productive exchanges and a greater and faster dissemination of published work.

d. The Journal authorizes the total or partial reproduction of the content of the publication, as long as the source is cited, that is, the name of the Journal, name of the author (s), year, volume, publication number and pages of the article.

e. The ideas and statements issued by the authors are their responsibility and in no case bind the Journal.

References

[1] D. Jiménez, J. Cock, A. Jarvis, J. Garcia, H. F. Satizábal, P. Van-Damme, A. Peréz-Uribe, and M. Barreto-Sanz, “Interpretation of commercial production information: A case study of lulo (Solanum quitoense), an under-researched Andean fruit,” Agricultural Systems, vol. 104 (3), pp. 258-270, Mar. 2011. https://doi.org/10.1016/j.agsy.2010.10.004

[2] J. W. Jones, J. M. Antle, B. Basso, K. J. Boote, R. T. Conant, I. Foster, H. C. J. Godfay, M. Herrero, R. E. Howitt, S. Janssen, B. A. Keating, R. Munoz-Carpena, C. H. Porter, C. Rosenzweig, and T. R. Wheeler, “Brief history of agricultural systems modeling,” Agricultural Systems, vol. 155, pp. 240-254, Jul. 2017. https://doi.org/10.1016/j.agsy.2016.05.014

[3] I. Diaz, S. M. Mazza, E. F. Combarro, L. I. Gimenez, and J. E. Gaiad, “Machine learning applied to the prediction of citrus production,” Spanish Journal of Agricultural Research, vol. 15 (2), e0205, Jun. 2017. https://doi.org/10.5424/sjar/2017152-9090

[4] S. T. Drummond, K. A. Sudduth, A. Joshi, S. J. Birrell, and N. R. Kitchen, “Statistical and neural methods for site-specific yield prediction,” Transactions of the ASAE, vol. 46 (1), pp. 5-14, 2003. https://doi.org/10.13031/2013.12541

[5] J. L. De Paepe, and R. Alvarez, “Wheat Yield Gap in the Pampas: Modeling the Impact of Environmental Factors,” Agronomy, Soils & Environmental Quality, vol. 108 (4), pp. 1367-1378, 2016. https://doi.org/10.2134/agronj2015.0482

[6] J. D. R. Soares, M. Pasqual, W. S. Lacerda, S. O. Silva, and S. L. R. Donato, “Comparison of techniques used in the prediction of yield in banana plants,” Scientia Horticulturae, vol. 167, pp. 84-90, Mar. 2014. https://doi.org/10.1016/j.scienta.2013.12.012

[7] A. Shekoofa, Y. Emam, N. Shekoufa, M. Ebrahimi, and E. Ebrahimie, “Determining the Most Important Physiological and Agronomic Traits Contributing to Maize Grain Yield through Machine Learning Algorithms: A New Avenue in Intelligent Agriculture,” PLoS One, vol. 9 (5), e97288, May 2014. https://doi.org/10.1371/journal.pone.0097288

[8] J. R. Romero, P. F. Roncallo, P. C. Akkiraju, I. Ponzoni, V. C. Echenique, and J. A. Carballido, “Using classification algorithms for predicting durum wheat yield in the province of Buenos Aires,” Computers and Electronics in Agriculture, vol. 96, pp. 173-179, Aug. 2013. https://doi.org/10.1016/j.compag.2013.05.006

[9] X. Huang, G. Huang, C. Yu, S. Ni, and L. Yu, “A multiple crop model ensemble for improving broad-scale yield prediction using Bayesian model averaging,” Field Crops Research, vol. 211, pp. 114-124, Sep. 2017. https://doi.org/10.1016/j.fcr.2017.06.011

[10] A. A. V. da Silva, I. A. F. Silva, M. C. M. Teixeira Filho, S. Buzetti, and M. C. M. Teixeira, “Estimate of wheat grain yield as function of nitrogen fertilization using neuro fuzzy modeling,” Revista Brasileira de Engenharia Agrícola e Ambiental, vol. 18 (2), pp. 180-187, Feb. 2014. https://doi.org/10.1590/S1415-43662014000200008

[11] I. Lopez, J. Plazas, and J. C. Corrales, “A tool for classification of cacao production in Colombia based on multiple classifier systems,” in 17th International Conference Computational Science and Its Applications – ICCSA 2017, Trieste, Italy, Jul. 2017. https://doi.org/10.1007/978-3-319-62395-5_5

[12] E. Somarriba, and J. Beer, “Productivity of Theobroma cacao agroforestry systems with timber or legume service shade trees,” Agroforestry Systems, vol. 81, pp. 109-121, 2011. https://doi.org/10.1007/s10457-010-9364-1

[13] P. A. Zuidema, P. A. Leffelaar, W. Gerritsma, L. Mommer, and N. P. R. R. Anten, “A physiological production model for cocoa (Theobroma cacao): model presentation, validation and application,” Agricultural Systems, vol. 84 (2), pp. 195-225, May 2005. https://doi.org/10.1016/j.agsy.2004.06.015

[14] L. F. García Carrión, Catalogo de cultivares de cacao del Perú, Lima: Ministerio de Agricultura y Riego, 2010.

[15] V. Vapnik, The nature of Statistical Learning Theory, New York: Springer-Verlag, 1995.

[16] H. Drucker, C. J. C. Burges, L. Kaufman, A. J. Smola, and V. Vapnik, "Support Vector Regression Machines," Neural Information Processing Systems, vol. 9, pp. 1-11, 1997.

[17] T. Dietterich, Ensemble Methods in Machine Learning. In: Multiple Classifier Systems, Heidelberg: Springer Berlin, 2000.

[18] J. H. Friedman, “Greedy Function Approximation: A Gradient Boosting Machine,” Annals of Statistics, vol. 29 (5), pp. 1189-1232, 2001.

[19] L. Breiman, “Random forests,” Machine Learning, vol. 45 (1), pp. 5-32, 2001. https://doi.org/10.1023/A:1010933404324

[20] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, and B. Thirion, “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825-2830, 2011.

[21] T. M. Logan, S. McLeod, and S. Guikema, “Predictive models in horticulture: A case study with Royal Gala apples,” Scientia Horticulturae, vol. 209, pp. 201-213, Sep. 2016. https://doi.org/10.1016/j.scienta.2016.06.033

[22] A. Daymond, and P. Hadley, “The effects of temperature and light integral on early vegetative growth and chloroplyll fluorescence of four contrasting genotypes of cacao,” Annals of Applied Biology, vol. 145 (3), pp. 257-262, 2004. https://doi.org/10.1111/j.1744-7348.2004.tb00381.x

[23] Y. Ahenkorah, B. Halm, M. Appiah, and G. Akrofi, “Twenty Years’ Results from a Shade and Fertilizer Trial on Amazon Cocoa (Theobroma cacao) in Ghana,” Experimental Agriculture, vol. 23 (1), pp. 31-39, Jan. 1987. https://doi.org/10.1017/s0014479700003380

[24] O. Deheuvels, J. Avelino, E. Somarriba, and E. Malezieux, “Vegetation structure and productivity in cocoa-based agroforestry systems in Talamanca, Costa Rica,” Agriculture, Ecosystems & Environment, vol. 149, pp. 181-188, Mar. 2012. https://doi.org/doi: 10.1016/j.agee.2011.03.003

[25] W. Vanhove, N. Vanhoudt, and P. Van Damme, “Effect of shade tree planting and soil management on rehabilitation success of a 22-year-old degraded cocoa (Theobroma cacao L.) plantation,” Agriculture, Ecosystems & Environment, vol. 219, pp. 14-25, Mar. 2016. https://doi.org/doi: 10.1016/j.agee.2015.12.005

[26] B. Utomo, A. A. Prawoto, S. Bonnet, A. Bangviwat, and S. H. Gheewala, “Environmental performance of cocoa production from monoculture and agroforestry systems in Indonesia,” Journal of Cleaner Production, vol. 134 (Part B), pp. 583-591, Oct. 2016. https://doi.org/10.1016/j.jclepro.2015.08.102

Downloads

Download data is not yet available.

Most read articles by the same author(s)