Sugar Tech

, Volume 19, Issue 6, pp 662–668 | Cite as

Use of the Decision Tree Technique to Estimate Sugarcane Productivity Under Edaphoclimatic Conditions

  • João Rossi Neto
  • Zigomar Menezes de Souza
  • Stanley Robson de Medeiros Oliveira
  • Oriel Tiago Kölln
  • Danilo Alves Ferreira
  • João Luís Nunes Carvalho
  • Oscar Antônio Braunbeck
  • Henrique Coutinho Junqueira Franco
Research article

Abstract

A number of biometric evaluations are performed during harvest for measuring the growth and development of the sugarcane crop. From these evaluations, hundreds of data values are generated, containing certain information on the productivity of the culture in that crop and edaphoclimatic region. Accordingly, the objective of this work was to identify, using a decision tree classification technique, the biometric attribute having the greatest effect on the productivity of the plant cane in different planting configurations and edaphoclimatic conditions. To accomplish this, data were evaluated from four experiments with sugarcane, located within the São Paulo municipalities of Teodoro Sampaio, Guaíra, Iracemápolis, and Lençóis Paulista. The classification model was generated using the decision tree technique, a type of intuitive learning that creates a hypothesis based on particular instances that results in general conclusions. The decision trees applied to the data of the four sites showed that the population of plants per hectare has the highest information gain (split attribute) on the class attribute (productivity). Using the “Chi-square” method of attribute selection, the population of plants per hectare was observed to have the largest correlation with the final productivity of the culture. Therefore, the decision tree indicates that the attribute “plant population per area” should be used as the method to evaluate the productive potential of the culture during its growth cycle. It has the best correlation with the final productivity of the crop, in addition to being an attribute easy to measure in the field.

Keywords

Productivity classification Selection of biometric attributes Methods for data classification Saccharum spp 

Notes

Acknowledgements

We thank sugarcane mills Alcídia, Guaíra, Iracema, Porto das Águas, and Zilor for their support in the execution of field experiments, and the BNDES Project/Jet/CTBE for financing the data collection in the field.

Funding

This study was funded by a project of CTBE (Brazilian Bioethanol Science and Technology Centre) and Jacto by Funtec of the BNDES. The author João Rossi Neto received a CAPES masters scholarship during the achievement of the project.

Compliance with Ethical Standards

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. Beadle, C.L. 1985. Plant growth analysis. In Techniques in bioproductivity and photosynthesis, 2nd ed, ed. J. Coombs, D.O. Hall, S.P. Long, and J.M.O. Scurlock, 20–24. Oxford: Pergamon Press.CrossRefGoogle Scholar
  2. Cabena, P., P. Hadjinian, R. Stadler, J. Verhees, and A. Zanasi. 1998. Discovering data mining: From concept to implementation, 1st ed. Upper Saddle River, NJ: Prentice-Hall Publishing.Google Scholar
  3. Cavalett, O., T.L. Junqueira, M.O.S. Dias, C.D. Jesus, P.E. Mantelatto, M.P. Cunha, H.C.J. Franco, T.F. Cardoso, R. Maciel Filho, C.E.V. Rossell, and A. Bonomi. 2012. Environmental and economic assessment of sugarcane first generation biorefineries in Brazil. Clean Technologies and Environmental Policy 14: 399–410. doi: 10.1007/s10098-011-0424-7.CrossRefGoogle Scholar
  4. Cohen, J.A. 1960. A coefficient of agreement of nominal scales. Educational and Psychological Measurement 20: 37–46. doi: 10.1177/001316446002000104.CrossRefGoogle Scholar
  5. Dalchiavon, F., M.P. Carvalho, R. Montanari, M. Andreotti, and A.R. Panosso. 2014. Produtividade da cana-de-açúcar: variabilidade linear e espacial entre componentes tecnológicos e da produção. Bioscience Journal 30: 390–400.Google Scholar
  6. Dias, F.L.F., J.A. Mazza, S. Matsuoka, D. Perecin, and R.F. Maule. 1999. Productivity of sugarcane in relation to climate and soils of the northwestern São Paulo state. Revista Brasileira de Ciência do Solo 23: 627–634. doi: 10.1590/S0100-06831999000300016.CrossRefGoogle Scholar
  7. Ehsanullah, K.J., M. Jamil, and A. Ghafar. 2011. Optimizing the row spacing and seeding density to improve yield and quality of sugarcane. Crop and Environment 2: 1–5.Google Scholar
  8. Elmasri, R., and S.B. Navathe. 2005. Sistemas de Banco de Dados, 4th ed. São Paulo, SP: Pearson Education.Google Scholar
  9. Fernandes, J.L., J.V. Rocha, and R.A.C. Lamparelli. 2011. Sugarcane yield estimates using time series analysis of spot vegetation images. Scientia Agricola 68: 139–146. doi: 10.1590/S0103-90162011000200002.CrossRefGoogle Scholar
  10. Ferraro, D.O., D.E. Rivero, and C.M. Ghersa. 2009. An analysis of the factors that influence sugarcane yield in Northern Argentina using classification and regression trees. Field Crop Research 112: 149–157. doi: 10.1016/j.fcr.2009.02.014.CrossRefGoogle Scholar
  11. Marin, F.R., R.V. Ribeiro, and P.E.R. Marchiori. 2014. How can crop modeling and plant physiology help to understand the plant responses to climate change? A case study with sugarcane. Theoretical and Experimental Plant Physiology 26: 49–63. doi: 10.1007/s40626-014-0006-2.CrossRefGoogle Scholar
  12. Miller, D., J. Mccarthy, and A. Zakzeski. 2009. A fresh approach to agricultural statistics: Data mining and remote sensing. In 2009 joint statistical meetings, 3144–3155. American Statistical Association, Washington, DC.Google Scholar
  13. Nonato, R.T., and S.R.M. Oliveira. 2013. Data mining techniques for identification of sugarcane crop areas in images of Landsat 5. Engenharia Agricola 33: 1268–1280. doi: 10.1590/S0100-69162013000600019.CrossRefGoogle Scholar
  14. Pawar, M.W., D.B. More, V.T. Amodkar, and J. Snehal. 2005. Effect of intersettling spacing on sugarcane yield and quality. Sugar Tech 7: 87–89. doi: 10.1007/BF02942424.CrossRefGoogle Scholar
  15. Quinlan, J.R. 1993. C4.5: Programs for machine learning, 1st ed. Burlington, MA: Morgan Kaufmann Press.Google Scholar
  16. Singels, A., and M.A. Smit. 2009. Sugarcane response to row spacing-induced competition for light. Field Crop Research 113: 149–155. doi: 10.1016/j.fcr.2009.04.015.CrossRefGoogle Scholar
  17. Singh, N.P., R.D.N. Verma, R.G. Singh, and S.B. Singh. 2000. Effect of plant geometry and nitrogen level on yield and juice quality of sugarcane. Sugar Tech 2: 40–43. doi: 10.1007/BF02945743.CrossRefGoogle Scholar
  18. Witten, I.H., and E. Frank. 2005. Data mining: Practical machine learning tools and techniques, 2nd ed. Burlington, MA: Morgan Kaufmann Press.Google Scholar
  19. Witten, I.H., E. Frank, and M.A. Hall. 2011. Data mining: Practical machine learning tools and techniques, 3rd ed. Burlington, MA: Morgan Kaufmann Press.Google Scholar

Copyright information

© Society for Sugar Research & Promotion 2017

Authors and Affiliations

  • João Rossi Neto
    • 1
  • Zigomar Menezes de Souza
    • 1
  • Stanley Robson de Medeiros Oliveira
    • 2
  • Oriel Tiago Kölln
    • 3
  • Danilo Alves Ferreira
    • 3
  • João Luís Nunes Carvalho
    • 3
  • Oscar Antônio Braunbeck
    • 3
  • Henrique Coutinho Junqueira Franco
    • 3
  1. 1.Department of Water and SoilState University of Campinas/FEAGRICampinasBrazil
  2. 2.EMBRAPA/Embrapa Agriculture InformaticsCampinasBrazil
  3. 3.Biomass Production DivisionCNPEM/Brazilian Bioethanol Science and Technology CentreCampinasBrazil

Personalised recommendations