Enhancing Decision-Making Processes of Small Farmers in Tropical Crops by Means of Machine Learning Models

  • Héctor Satizábal
  • Miguel Barreto-Sanz
  • Daniel Jiménez
  • Andrés Pérez-Uribe
  • James Cock


Small farmers in developing countries face the problem of deciding where to cultivate and how to manage their crops. In under researched crops, they base many of their decisions on traditional knowledge and personal experience. We surmised that their decision making processes could be enriched by inductive or data-driven models which should provide a means to improve crop management practices. Bio-inspired machine learning techniques like artificial neural networks are promising modelling tools for accomplishing the aforementioned task due to their proven capabilities when dealing with noisy, incomplete, and heterogeneous data. Moreover, bio-inspired techniques appear to perform quite well without strong assumptions on the data. Last but not least, they provide innovative ways to process and visualize highly-dimensional information. In this chapter, we illustrate the benefits of this methodology by presenting two case studies on fruit crops in Colombia. The studies reported here are associated with two related but separate problems: First the association of crop productivity with growing conditions and management and; Secondly the identification of similar or analogue sites between which technology can readily be transferred.


Shuttle Radar Topography Mission Tropical Rainfall Measure Mission Small Farmer Machine Learn Model Crop Response 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This work is part of a cooperation project between Corporación Biotec, the International Center for Tropical Agriculture (CIAT), and the Haute École d’Ingénierie et de Gestion du canton de Vaud (HEIG-VD) named “precision agriculture and the construction of field-crop models for tropical fruits.” The economical support is given by several institutions in Colombia: the Ministerio de Agricultura y Desarrollo Rural (MADR), the Departamento Administrativo de Ciencia, Tecnología e Innovación (COLCIENCIAS), the Agencia Presidencial para la Acción Social y la Cooperación Internacional (ACCI), and the State Secretariat for Education and Research (SER) in Switzerland.


  1. Acosta, O., Perez, A., & Vaillant, F. (2009). Chemical characterization, antioxidant properties, and volatile constituents of naranjilla (Solanum quitoense Lam.) cultivated in Costa Rica. Archivos Latinoamericanos de Nutricion, 59(1), 88–94.Google Scholar
  2. Alvarez, D. M., Estrada, M., & Cock, J. H. (2004). RASTA (Rapid Soil and Terrain Assessment). Palmira: Universidad Nacional De Colombia.Google Scholar
  3. Barreto, M., & Pérez-Uribe, A. (2007). Improving the correlation hunting in a large quantity of SOM component planes. Artificial Neural Networks - ICANN 2007, Porto, Portugal. Lecture Notes in Computer Science, 379–388. Springer Berlin / Heidelberg.Google Scholar
  4. Bell, T. L. (1987). Space-time stochastic model of rainfall for satellite remote-sensing studies. Journal of Geophysical Research-Atmospheres, 92(D8), 9631–9643.CrossRefGoogle Scholar
  5. Bioversity International. (2005a). Information sheet on Rubus glaucus in Accessed August 10, 2009.
  6. Bioversity International. (2005b). Information sheet on Solanum quitoense in Accessed August 16, 2009.
  7. Bishop, C. M. (1995). Neural networks for pattern recognition. Oxford: Oxford University Press.Google Scholar
  8. Estrada, L. E. (1992). Genetic potential of lulo (Solanum quitoense Lam.) and factors that limit its expression. Acta Horticulturae, 310, 171–182.Google Scholar
  9. Farr, T. G., & Kobrick, M. (2000). Radar tropography mission produces a wealth of data. American Geophysical Union Eos, 81, 583–585.CrossRefGoogle Scholar
  10. Flórez, S. L., Lasprilla, D. M., Chaves, B., Fischer, G., & Magnitskiy, S. (2008). Growth of Lulo (Solanum quitoense Lam.) plants affected by salinity and substrate. Revista Brasileira de Fruticultura, 30, 402–408.CrossRefGoogle Scholar
  11. Franco, G., & Giraldo, M. J. (2002). El cultivo de la mora (5th ed.). Manizales: CORPOICA.Google Scholar
  12. Franco, G., Bernal, J. E., Giraldo, M. J., Tamayo, J., Castaño, P., Tamayo, V., Gallego, J., Leomad, J., Botero, M. J., Rodríguez, J., Guevara, N., Morales, J., Londoño, M., Ríos, G., Rodríguez, J., Cardona, J., Zuleta, J., Castaño, J., & Ramírez, C. (2002). El cultivo del Lulo: Manual técnico Corporación Colombiana de Investigación Agropecuaria (CORPOICA). Manizales: Regional nueve. Agosto de 2002.Google Scholar
  13. Fritzke, B. (1995). A growing neural gas learns topologies (Advances in neural information processing systems 7). Cambridge: MIT Press.Google Scholar
  14. Fritzke, B. (1997). Unsupervised ontogenic networks. Fiesler, Beale, Editors, Handbook of neural computation. IOP Publishing Ltd. and Oxford University Press. Chapter 2.4.Google Scholar
  15. Hijmans, R. J., Cameron, S. E., Parra, J. L., Jones, P. G., & Jarvis, A. (2005). Very high resolution interpolated climate surfaces for global land areas. International Journal of Climatology, 25(15), 1965–1978.CrossRefGoogle Scholar
  16. Jiménez, D., Pérez-Uribe, A., Satizábal, H. F., Barreto, S., Miguel, A., Van Damme, P., & Tomassini, M. (2008). A survey of artificial neural network-based modeling in agroecology. In B. Prasad (Ed.), Softcomputing applications in industry (pp. 247–269). Berlin/Heidelberg: Springer.Google Scholar
  17. Jiménez, D., Cock, J., Satizábal, H. F., Barreto, M., 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.CrossRefGoogle Scholar
  18. Jiménez, D., Cock, J., Jarvis, A., Garcia, J., Satizábal, H. F., Van Damme, P., Pérez- Uribe, A., & Barreto-Sanz, M. (2011). Interpretation of commercial production information: A case study of Lulo (Solanum quitoense), an under-researched Andean fruit. Agricultural Systems, 104(3), 258–270.CrossRefGoogle Scholar
  19. Kohonen, T. (1995). Self-organizing maps. New York: Springer.CrossRefGoogle Scholar
  20. National Research Council. (1989). Lost crops of the Incas: Little known plants of the Andes with promise for worldwide cultivation. Washington, DC: National Academy Press.Google Scholar
  21. Osorio, C., Duque, C., & Batista-Viera, F. (2003). Studies on aroma generation in Lulo (Solanum quitoense): Enzymatic hydrolysis of glycosides from leaves. Food Chemistry, 81(3), 333–340.CrossRefGoogle Scholar
  22. Pulido, S., Bojacá, C. R., Salazar, M., & Chaves, B. (2008). Node appearance model for Lulo (Solanum quitoense Lam.) in the high altitude tropics. Biosystems Engineering, 101(4), 383–387.CrossRefGoogle Scholar
  23. Rauber, A., Merkl, D., & Dittenbach, M. (2002). The growing hierarchical self-organizing map: Exploratory analysis of high-dimensional data. IEEE Transactions on Neural Networks, 13(6), 1331–1341.CrossRefGoogle Scholar
  24. Satizábal, H. F., & Pérez-Uribe, A. (2007). Relevance metrics to reduce input dimensions. Artificial Neural Networks – ICANN 2007. Lecture Notes in Computer Science, vol. 4688 (pp. 39–48). doi:  10.1007/978–3–540–74690–4_5.
  25. Satizábal, H. F., Pérez-Uribe, A., & Tomassini, M. (2008). Prototype proliferation in the growing neural gas algorithm. Artificial Neural Networks – ICANN 2008. Lecture Notes in Computer Science, vol. 5164 (pp. 793–802). doi:  10.1007/978–3–540–87559–8_82.
  26. Schultz, A., Wieland, R., & Lutze, G. (2000). Neural networks in agroecological modelling- stylish application or helpful tool? Computers and Electronics in Agriculture, 29(1–2), 73–97.CrossRefGoogle Scholar
  27. Sora, D. S., Fischer, G., & Florez, R. (2006). Refrigerated storage of mora de castilla (Rubus glaucus) fruits in modified atmosphere packaging. Agronomia Colombiana, 24(2), 306–316.Google Scholar
  28. Vesanto, J., & Ahola, J. (1999). Hunting for correlations in data using the self-organizing map. Proceedings of the International ICSC Congress on Computational Intelligence Methods and Applications – CIMA. June 22–25 (pp. 279–285). Rochester: ICSC Academic Press.Google Scholar

Copyright information

© Springer Paris 2012

Authors and Affiliations

  • Héctor Satizábal
    • 1
  • Miguel Barreto-Sanz
    • 2
    • 1
  • Daniel Jiménez
    • 3
    • 4
  • Andrés Pérez-Uribe
    • 1
  • James Cock
    • 3
  1. 1.Institute for Information and Communication Technologies (IICT)University of Applied Science Western Switzerland (HEIG-VD)Yverdon-les-BainsSwitzerland
  2. 2.Faculté des Hautes Etudes Commerciales (HEC)University of LausanneLausanneSwitzerland
  3. 3.Decision and Policy Analysis (DAPA)International Centre for Tropical Agriculture (CIAT)PalmiraColombia
  4. 4.Faculty of BioScience Engineering: Agricultural ScienceGhent UniversityGhentBelgium

Personalised recommendations