Abstract
Brazil is one of the largest sugarcane producers. It directly affects job creation and national gross domestic product, as well as bringing a large amount of foreign money to the country. Hence, this paper proposes investigating the application of neural networks—multilayer perceptron, extreme learning machines (ELM) and echo state networks (ESN)—for predicting the following cane derivatives prices: sugar, hydrous ethanol, and anhydrous ethanol. The main characteristic of ELM and ESN is their simple and fast training process, being based on the analytic calculation of the coefficients of a linear combiner. Their intermediate layer stands untuned, and the weights in this layer are randomly and independently defined. The computational results show that the application of the ELM achieved the best overall results, showing that they are viable candidates for these kinds of problems.
Similar content being viewed by others
References
Alves, L.R.A., and M.R.P. Bacchi. 2004. Export offer of sugar from Brazil, In Portuguese: “Oferta de exportação de açúcar do Brasil”. Revista de Economia e Sociologia Rural 42 (1): 9–33.
Antonopoulos, V.Z., and A.V. Antonopoulos. 2017. Daily reference evapotranspiration estimates by artificial neural networks technique and empirical equations using limited input climate variables. Computers and Electronics in Agriculture 132: 86–96.
Box, G.E.P., G.M. Jenkins, and G.C. Reinsel. 1994. Time series analysis: Forecasting and control, 3rd ed. Oakland, California: Holden Day.
Castro, L.N. 2006. Fundamentals of natural computing: Basic concepts, algorithms and applications. Boca Raton: Chapman & Hall.
CEPEA, Center for Advanced Studies in Applied Economy (Centro de Estudos Avançados em Economia Aplicada)—ESALQ/USP. Available in: http://cepea.esalq.usp.br. Accessed 1 July 2015.
Dan, J., W. Guo, W. Shi, B. Fang, and T. Zhang. 2014. Deterministic echo state networks based stock price forecasting. Abstract and Applied Analysis 2014:1–6. https://doi.org/10.1155/2014/137148.
Dantas, G.A., L.F.L. Legey, and A. Mazzone. 2013. Energy from sugarcane bagasse in Brazil: An assessment of the productivity and cost of different technological routes. Renewable and Sustainable Energy Reviews 21: 356–364.
David, S.A., D.D. Quintino, C.M.C. Inacio Jr., and J.A.T. Machado. 2018. Fractional dynamic behavior in ethanol prices series. Journal of Computational and Applied Mathematics 339: 85–93.
de Mattos Neto, P.S.G., F. Madeiro, T.A.E. Ferreira, and G.D.C. Cavalcanti. 2014. Hybrid intelligent system for air quality forecasting using phase adjustment. Engineering Applications of Artificial Intelligence 32: 185–191.
de Mattos Neto, P.S.G., G.D.C. Cavalcanti, and F. Madeiro. 2017. Nonlinear combination method of forecasters applied to PM time series. Pattern Recognition Letters 95: 65–72.
Drabik, D.H.G., D.R. Just, and G.R. Timilsina. 2015. The economics of Brazil’s ethanol-sugar markets, mandates, and tax exemptions. American Journal of Agricultural Economics 97 (5): 1433–1450.
EPE, Energy Research Company (Empresa de Pesquisa Energética). 2014. National energy balance 2014, In Portuguese: “Balanço energético nacional 2014”. Brazilian Ministry of Mines and Energy.
Figueira, S.R., H.L. Burnquist, and M.R.P. Bacchi. 2010. Forecasting fuel ethanol consumption in Brazil by time series models: 2006–2012. Applied Economics 42 (7): 865–874.
Firmino, P.R.A., P.S.G. de Mattos Neto, and T.A.E. Ferreira. 2015. Error modeling approach to improve time series forecasters. Neurocomputing 153: 242–254.
Haykin, S. 1999. Neural networks: A comprehensive foundation, 2nd ed. Upper Saddle River, NJ: Prentice-Hall.
Huang, G.-B., Q.-Y. Zhu, and C.-K. Siew. 2004. Extreme learning machine: A new learning scheme of feedforward neural networks. In Proceedings of international joint conference on neural networks, 985–990.
Huang, G.-B., Q.-Y. Zhu, and C.-K. Siew. 2006. Extreme learning machine: Theory and applications. Neurocomputing 70 (1–3): 489–501.
Jaeger, H. 2001. The echostate approach to analyzing and training recurrent neural networks, Bremem: German National Research Center for Information Technology. Technical Report GMD Report 148.
Jaeger, H. 2002. Short termmemory in echostate networks, Bremem: German National Research Center for Information Technology. Technical Report GMD 152.
Jati, K. 2013. Sugar price analysis in Indonesia. International Journal of Social Science and Humanity 3 (4): 369.
Lee, T.S.G., and E.A. Bressan. 2006. The potential of ethanol production from sugarcane in Brazil. Sugar Tech 8 (4): 195–198.
Lima, N.C., and G.H.S. de Souza. 2014. The demand for ethanol and its characterization in the Brazilian fuel Market, In Portuguese: “A demanda do etanol e sua caracterização no mercado brasileiro de combustíveis”. Organizações Rurais & Agroindustriais, Lavras 16 (4): 532–544.
Luna, I., and R. Ballini. 2011. Top-down strategies based on adaptive Fuzzy rule-based systems for daily time series forecasting. International Journal of Forecasting 27: 708–724.
Melo, B., A.Z. Milioni, and C.L. Nascimento Jr. 2007. Daily and monthly sugar price forecasting using the mixture of local expert models. Pesquisa Operacional 27 (2): 235–246.
Moraes, M.L., and M.R.P. Bacchi. 2015. Ethanol: fromthe start to the final stages of production, In Portuguese: “Etanol: do início às fases finais de produção”. Revista de Politica Agricola 4: 5–22.
Nahvi, B., J. Habibi, K. Mohammadi, S. Shamshirband, and O.S. Al Razgan. 2016. Using self-adaptive evolutionary algorithm to improve the performance of an extreme learning machine for estimating soil temperature. Computers and Electronics in Agriculture 124: 150–160.
Neves, M.F., A.W. Gray, and B.A. Bourquard. 2016. Copersucar: A world leader in sugar and ethanol. International Food and Agribusiness Management Review 19 (2): 207–240.
Obe, O., and D.K. Shangodoyin. 2010. Artificial neural network based model for forecasting sugar cane production. Journal of Computer Science 6 (4): 439–445.
Oliveira, S.M., C.O. Ribeiro, and M.P.V. Cicogna. 2018. Uncertainty effects on production mix and on hedging decisions: The case of Brazilian ethanol and sugar. Energy Economics 70: 516–524.
Polezer, G., Y.S. Tadano, H.V. Siqueira, A.F.L. Godoi, C.I. Yamamoto, P.A. André, T. Pauliquevis, M.F. Andrade, A. Oliveira, P.H.N. Saldiva, P.E. Taylor and R.H.M. Godoi. 2018. Assessing the impact of PM 2.5 on respiratory disease using artificial neural networks. Environmental Pollution 235: 394–403.
Rezende, M., and J.W. Richardson. 2015. Economic feasibility of sugar and ethanol production in Brazil under alternative future prices outlook. Agricultural Systems 138: 77–87.
Ribeiro, C., and O. Oliveira. 2011. A hybrid commodity price-forecasting model applied to the sugar-alcohol sector. Australian Journal of Agricultural and Resource Economics 55 (2): 180–198.
Rumelhart, D.E., R.J. Williams, and G. Hinton. 1986. Learning representations by backpropagation errors. Nature 323: 533–538.
Santos, E. P. and F. J. Von Zuben. 1999. Improved second-order training algorithms for globally and partially recurrent neural networks. In IEEE proceedings of international joint conference neural networks, vol. 3, 1501–1506.
Schaefer, A.M., and H. Zimmermann. 2007. Recurrent neural networks are universal approximators. International Journalof Neural Systems 17 (4): 253–263.
Schlindwein, M. M., and A. L. Kassouf. 2007. Changes in the pattern of consumption of time-intensive food sand time-saving foods, by region in Brazil, In Portuguese “Mudanças no padrão de consumo de alimentos tempo-intensivos e de alimentos poupadores de tempo, por região no Brasil”, In: Siveira, F. G.; Servo, L. M. S.; Meneszes, T., Piola, S. F. (Org.). Gasto e consumo das famílias brasileiras contemporâneas 2. Brasília: IPEA – Institute of Applied Economic Research (Instituto de Pesquisa Econômica Aplicada), 423–462.
Siqueira, H., L. Boccato, R. Attux, and C. Lyra. 2012. Echo state networks and extreme learning machines: A comparative study on seasonal streamflow series prediction. Lecture Notes in Computer Science 7664 (2): 491–500.
Siqueira, H., L. Boccato, R. Attux, and C. Lyra. 2014. Unorganized machines for seasonal streamflow series forecasting. International Journal of Neural Systems 24: 1430009–1430016.
Siqueira, H., L. Boccato, I. Luna, R. Attux, and C. Lyra. 2018. Performance analysis of unorganized machines in streamflow forecasting of Brazilian plants. Applied Soft Computing 68: 494–506.
Soliani, R.D., and A.R.T.T. Argoud. 2015. Analysis of the logistics infrastructure of the sugar bulk produced to export in the Brazilian State of São Paulo. European Journal of Business and Social Sciences 4 (6): 100–113.
Sorjamaa, A., J. Hao, N. Reyhani, Y. Ji, and A. Lendasse. 2007. Methodology for long-term prediction of time series. Neurocomputing 70: 2861–2869.
Souza, M.J.P., P.R. Oliveira, and H.L. Burnquist. 2013. Home, sweet home: an analysis of the consumption of sugar and related products in Brazil, In Portuguese: “Lar ‘Doce’ Lar: uma análise do consumo de açúcar e de produtos relacionados no Brasil”. Revista de Economia e Sociologia Rural 51: 785–796.
Statista, The Statistics Portal. 2017. Available in www.statista.com/statistics/249604/sugar-cane-production-worldwide/. Accessed 1 April 2017.
Suresh, K.K., and S.R.K. Priya. 2011. Forecasting sugarcane yield of Tamilnadu using ARIMA models. Sugar Tech 13 (1): 23–26.
Todde, G., L. Murgia, M. Caria and A. Pazzona. 2017. Dairy energy prediction (DEP) model: A tool for predicting energy use and related emissions and costs in dairy farms. Computers and Electronics in Agriculture 135: 216–221.
Xiong, T., C. Li, and Y. Bao. 2018. Seasonal forecasting of agricultural commodity price using a hybrid STL and ELM method: Evidence from the vegetable market in China. Neurocomputing 275: 2831–2844.
Xu, Y., S. Shen, and Z. Chen. 2009. Research on forecast of sugar price based on improved neural network. In Annals of the second international symposium on intelligent information technology and security informatics (IITSI’09), 12–15.
Yildiz, I.B., H. Jaeger, and S.J. Kiebel. 2012. Re-visiting the echo state property. Neural Networks 35: 1–9.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Silva, N., Siqueira, I., Okida, S. et al. Neural Networks for Predicting Prices of Sugarcane Derivatives. Sugar Tech 21, 514–523 (2019). https://doi.org/10.1007/s12355-018-0648-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12355-018-0648-5