Sugarcane Yield Prediction Through Data Mining and Crop Simulation Models
- 54 Downloads
The understanding of the hierarchical importance of the factors which influence sugarcane yield can subsidize its modeling, thus contributing to the optimization of agricultural planning and crop yield estimates. The objectives of this study were to identify and ordinate the main variables that condition sugarcane yield, according to their relative importance, as well as to develop mathematical models for predicting sugarcane yield by using data mining (DM) techniques. For this, three DM techniques were applied in the analyses of databases of several sugar mills in the state of São Paulo, Brazil. Meteorological and crop management variables were analyzed through the following DM techniques: random forest; boosting; and support vector machine, and the resulting models were tested through the comparison with an independent data set. Finally, the predictive performances of these models were compared with the performance of a simple agrometeorological model, applied in the same data set. The results allowed to conclude that, within all the variables assessed, the number of cuts was the most important factor considered by all DM techniques. The comparison between the observed yields and those estimated by the DM models resulted in a root mean square error (RMSE) ranging between 19.70 and 20.03 t ha−1, which was much better than the performance of the Agroecological Zone Model, which presented RMSE ≈ 34 t ha−1.
KeywordsYield estimation Random forest Boosting Support vector machines Crop model
RGH and PCS were both responsible for designing the study, analyzing and discussing the results and writing the manuscript. JCQM was responsible for writing the scripts for data organization, consistency and analysis.
Compliance with Ethical Standards
Conflict of interest
The authors declare that they have no conflict of interest.
- Allen, R.G., L.S. Pereira, D. Raes, and M. Smith. 1998. Crop evapotranspiration: guidelines for computing crop water requirements, 56. Rome: FAO - Irrigation and Drainage Paper.Google Scholar
- Camargo, A.P., and P.C. Sentelhas. 1997. Avaliação do desempenho de diferentes métodos de estimativa de evapotranspiração potencial no Estado de são Paulo, Brasil. Revista Brasileira de Meteorologia 5: 89–97.Google Scholar
- Camilo, C.O., and J.C. Silva. 2009. Mineração de dados: conceitos, tarefas, métodos e ferramentas: relatório técnico. Goiânia: Universidade Federal de Goiás, Instituto de Informática.Google Scholar
- Doorenbos, J., and A.H. Kassan. 1979. Yield response to water, 33. Rome: FAO - Irrigation and Drainage Paper.Google Scholar
- Everingham, Y.L., J. Sexton, and A. Robson. 2015. A statistical approach for identifying important climatic influences on sugarcane yields. In Proceedings of Australian Society of Sugar Cane Technologists. Bundaberg, Australia, 8–15.Google Scholar
- Everingham, Y.L., J. Sexton, D. Skocaj, and G.I. Bamber. 2016. Accurate prediction of sugarcane yield using a random forest algorithm. Agronomy for Sustainable Development 27: 1–9.Google Scholar
- Franchini, J.C., E. Torres, S.L. Gonçalves, and O.F. Saraiva. 2007. Contribuição de sistema de manejo para a produção sustentável da soja. Londrina: Embrapa-Soja. Circular Técnica 46.Google Scholar
- Monteiro, L.A., and P.C. Sentelhas. 2014. Potential and actual sugarcane yields in Southern Brazil as a function of climate conditions and crop management. Sugar Tech 16(264–276): 2014.Google Scholar
- Moura, A.M. 2003. Geoprocessamento na gestão e planejamento urbano. Belo Horizonte: Ed. da Autora.Google Scholar
- Pereira, A.R., L.R. Angelocci, and P.C. Sentelhas. 2002. Agrometeorologia: fundamentos e aplicações práticas. Guaíba: Ed. Agropecuária.Google Scholar
- Prado, H. 2008. Pedologia Fácil—Aplicações na agricultura. Piracicaba: ESALQ.Google Scholar
- Refaeilzadeh, P., L. Tang, and H. Liu. 2009. Cross-validation. In Encyclopedia of database systems, ed. L. Liu and M.T. Özsu. New York: Springer.Google Scholar
- Sousa, A.C.M., Z.M. Souza, R.M.P. Claret, and J.L.R. Torres. 2017. Traffic control with auto-pilot as an alternative to decrease soil compaction in sugarcane areas. Tropical and Subtropical Agroecosystems 20: 173–182.Google Scholar
- Thornthwaite, C.W., and J.R. Mather. 1955. The water balance. New Jersey: Drexel Institute of Technology (Publications in Climatology 8).Google Scholar