Performance of Multilayer Perceptron Neural Network Models and Radial-Based Functions in Estimation of Sugar-cane Crop Yield

Document Type : Research Paper

Authors

Abstract

Background and objective: According to the high importance of sustainable crop production in the agro-industry units, intelligent systems such as artificial neural networks should be used to manage farm units.Therefore, the main purpose of this study was to compare the performance of MLP (Multi-Layer Perceptron) and RBF (Radial Basis Functions) neural network models in order to modeling and estimating of the sugarcane crop yield and investigate the factors affecting it.
 
Materials and Methods: The study was analytical and its database contained of a matrix  elements. Required data for this research were obtained from the Debel Khazaei sugar cane agro-industry farm during the years 2016 to 2019. The input variables and their units were soil electrical conductivity (dS.m-1), Phosphate and Nitrogen chemical fertilizer (kg.ha-1), water consumption (m3.ha-1), also, irrigation times, month of harvest, age of crop, sugarcane variety, soil texture (non-dimensional), respectively. The analysis was performed by MATLAB 2017 software.
 
Results: By comparing the error parameters of RMSE (Root Mean Square Error) and the MAPE (Mean Absolute Percentage Error), and according to indexes of R2 (coefficient of determination) and the EF (Model Efficiency) and, in the validation phase the RBF model was the best model with 0.064494 (%), 0.037686, 0.7576 and 0.800409 (non-dimensional) respectively. Also, the RBF model indicated that the sugarcane variety and soil electrical conductivity were the most important factors affecting the sugar-cane yield.
 
Conclusion: By selecting the appropriate variety of sugarcane and controlling the amount of electrical conductivity of the soil, the yield per unit area can be increased, resulting in greater productivity of the inputs and more sustainable production.
 

Keywords

References

Afsharnia F, and Marzban A. 2019. Risk analysis of sugarcane stem transportation operation delays using the FMEA-ANP hybrid approach. Journal of Agricultural Machinery, 9(2): 455-467. (In Persian).
Amid S, Mesri Gunddoshmian T, and Shahghgoli. 2016. Comparison of MLP and RBF neural networks performance for estimation of broiler output energy. Iranian Journal of Biosystems Engineering, 47(2): 319-328. (In Persian).
Ayoubi S, and Lal Sahrawat K. 2011. Comparing multivariate regression and artificial neural network to predict barley production from soil characteristics in northern Iran. Archives of Agronomy and Soil Science, 57(5): 549-565.
Bahrami M, Amiri MJ, Rezaei Maharluei F, and Ghaffari KA. 2017. Data pre-processing effects on the artificial neural network performance to predict monthly rainfall (Case study: Abadeh county). Iranian Journal of Ecohydrology, 4(1): 29-37. (In Persian).
Bigdeli Z, and Yousef Aghli N. 2005. Investigating the motivations of the goals and database used by the experts of the sugar cane development company and the related industries of Khuzestan province and investigation of their problems for accessing their required information. Journal of Education, 12 (2): 91-112. (In Persian).
Bocca FF, and Rodrigues LHA. 2016. The effect of tuning, feature engineering, and feature selection in data mining applied to rainfed sugarcane yield modelling. Computers and Elctronics in Agriculture, 128, 67-76.
Bugate O, and Seresangtakul P. 2013. Sugarcane production forecasting model of the northeastern by artificial neural network. Khon Kaen Univresity Science Journal, 41(1): 213-225.
Coelho AP, Bettiol JVT, Dalri AB, Fischer Filho JA, Faria RTD, and Palaretti, LF. 2019. Application of artificial neural networks in the prediction of sugarcane juice Pol. Brazilian Journal of Agricultural and Environmental Engineering Open Access, 23, 9-15.
Dayani M, Jafari S, Khalilmoghadam B, and Dehghani AA. 2011. Saline and sodic mapping using geostatistics theory (A case study in western Karoon river land of Khozestan). Watershed Management Research (Pajouhesh & Sazandegi). 94, 86-95. (In Persian).
Ghaderpour O, Rafiee S, and Sharifi M. 2017. Life cycle assessment of alfalfa production and prediction of emissions using multi-layer adaptive neuro-fuzzy inference system in Bukan township. Journal of Agricultural Machinery, 8(1): 119-136. (In Persian).
Haghverdi A, Cornelis WM, and Ghahraman B. 2012. A pseudo-continuous neural network approach for developing water retention pedotransfer functions with limited data. Journal of Hydrology, 442, 46-54.
Hashemi Fath A, Madanifar F, and Abbasi M. 2018. Implementation of multilayer perceptron (MLP) and radial basis function (RBF) neural networks to predict solution gas-oil ratio of crude oil systems. Petroleum. In Press, Corrected Proof.
Jafari M, Vafakhah M, and Abghari H. 2013. Performance comparison of two activation functions namely Sigmoid and Hyperbolic Tangent in Artificial Neural Networks for storm runoff coefficient forecasting(Case Study: Barariyeh Watershed, Neishabour). Journal of Water and Soil Conservation, 20(2): 85-104. (In Persian).
Kumar S, Kumar V, and Sharma RK. 2015. Sugarcane yield forecasting using artificial neural network models.  International Journal of Artificial Intelligence & Applications, 6(5): 51-68.
Marashi F, Jafarzadeh Haghighi fard N, Khorasani N, and Monavari S. 2019. Life cycle assessment of the sugar industry: A Case study of Amir Kabir sugar cane industry. Iranian Journal of Biosystems Engineering, 49(4): 597-608. (In Persian).
Markopoulos AP, Georgiopoulos S, and Manolakos DE. 2016. On the use of back propagation and radial basis function neural networks in surface roughness prediction. Journal of Industrial Engineering International, 12, 389-400.
Mekparyup J, and Saithanu K. 2019. Forecasting sugar cane yield in the eastern area of Thailand with ANN technique. Australian Journal of Basic and Applied Sciences, 13(1): 112-116.
Narimany R, Hakimipour, AllahRezaee A. 2013. An application of value at risk based on artificial neural networks and hetroscecasdicity models. Quarterly Journal of Financial Economics (Financial Economics and Development), 7(24): 101-137. (In Persian).
Nemati Z, Hemmat A, and Mosaddeghi M R. 2017. Effect of adding sugarcane bagasse and filter cake and wetting and drying cycles on pre-compaction stress of soil. Journal of Agricultural Machinery, 8(1): 55-66. (In Persian).
Norouzian Azizi Z, Ghajar Sepanlou M, Emadi S, and Sadeqzade F. 2017. Evaluation of regression and artificial neural network models to estimate the saturated hydraulic conductivity in Mazandaran province. Iranian Journal of Soil Research, 31(1): 75-87. (In Persian).
Obe OO, and Shangodoyin DK. 2010. Artificial neural network based model for forecasting sugar cane production. Journal of Computer Science, 6(4): 439-445.
Osama K, Mishra BN, and Somvanshi P. 2015. Machine learning techniques in plant biology. Pp. 731-754. In: Barh D, Sarwar Khan M, Davies E.(eds). PlantOmics: The Omics of plant science. Springer- New Delhi, India.
Patan K. 2019. Neural Networks. Pp. 9-58. In: Patan, K. (eds). Neural Networks Robust and Fault-Tolerant Control Neural-Network-Based Solutions. Springer- Cham, Switzerland.
Peyman L, Mahmoudi A, Abdollahpor S, Moghaddam M, and Ranabonab B. 2012. Controlling spray particle size using artificial neural networks. Journal of Agricultural Science and Sustainable Production, 21(4): 75-84. (In Persian).
Ribeiro CO, and Oliveira S. 2011. A hybrid commodity price-forecasting model applied to the sugar-alcohol sector. Australian Journal of Agricultural and Resource Economics, 55(2): 180-198.
Sarparandeh M, and Hezarkhani A. 2017. Studying distribution of rare earth elements by classifiers, Se-Chahun iron ore, Central Iran. Acta Geochim, 36, 232-239.
Sayyadi H, Oladghaffari A, Faalian A, and Sadraddini A. 2009. Comparison of RBF and MLP neural networks performance for estimation of reference crop evapotranspiration. Water and Soil Science, 19(1): 1-12. (In Persian).
Sedehi M, Mehrabi Y, Kazemnejad A, Hadaegh F. 2009. Comparison of artificial neural network, logistic regression and discriminant analysis methods in prediction of metabolic syndrome. Iranian Journal of Endocrinology and Metabolism, 11(6): 638-646. (In Persian).
Sefeedpari P, Rafiee S, and Akram A. 2013. Application of artificial neural network to model the energy output of dairy farms in Iran. International Journal of Energy Technology and Policy, 9(1): 82-91.
Sifaoui A, Abdelkrim A, Alouane S, and Benrejeb M. 2009. On new RBF neural network construction algorithm for classification. Studies in Informatics and Control, 18(2): 103-110.
Silva N, Siqueira I, Okida S, Steven SL, and Siqueira H. 2019. Neural nework for predicting prices of sugarcane derivatives. Sugar Technology, 21(3): 514-523.
Sundermeyer M, Oparin I, Gauvain JL, Freiberg B, Schlüter R, and Ney H. 2013. Comparison of feedforward and recurrent neural network language models. Proceedings of38th IEEE International Conference on Acoustics, Speech and Signal Processing. May, Vancouver, BC, Canada .Pp. 8430-8434.
Taherei Ghazvinei P, Hassanpour Darvishi H, Mosavi A, Yusof K b W, Alizamir M, Shamshirband S, and Chau K-w. 2018. Sugarcane growth prediction based on meteorological parameters using extreme learning machine and artificial neural network. Engineering Applications of Computational Fluid Mechanics, 12(1): 738-749.
Taherpoor H, Shahnoushi N, Danshvar M, and Mohebi M. 2009. Investigation on technical efficiency of agronomy and horticulture sub sectors products in Khorasan Razavi province: Application of integrated neural network and fuzzy clustering approach. Journal of Agricultural Science and Sustainable Production, 20(4): 37-51. (In Persian).
Taki M, Ajabshirchi Y, Ranjbar SF, Rohani A, Matloobi M. 2016. Modeling and experimental validation of heat transfer and energy consumption in an innovative. Information Processing in Agriculture,
3(3): 157-174.
Taki M, Rohani A, Soheili-Fard F, and Abdeshahi A. 2018. Assessment of energy consumption and modeling of output energy for wheat production by neural network (MLP and RBF) and Gaussian process regression (GPR) models. Journal of Cleaner Production, 172, 3028-3041.
Thuankaewsing S, khmjan S, Piewthongngam K, Pathumnakul S. 2015. Harvest scheduling algorithm to equalize supplier benefits: a case study from the Thai sugar cane industry. Computers and Elctronics in Agriculture, 110, 42-55.
Veisitabar A, Hemmat A, and Mosaddeghi MR. 2015. Soil compaction assessment in sugarcane fields under different planting conditions using soil bulk density, relative bulk density and cone index. Quarterly Water and Soil Science (Journal of Science and Technology of Agriculture and Natural Resources),
19 (72): 93-106. (In Persian).
Wang X, Xia A, and Wang J. 2010. Determination of brix and POL in sugar cane juice by using near infrared spectroscopy coupled with BP-ANN. Spectroscopy and Spectral Analysis, 30, 1759-1762.
Wu Y, Wang H, Zhang B, and Du K-L. 2012. Using Radial Basis Function Networks for Function Approximation and Classification. International Scholarly Research Notices Applied Mathematics, 1-34.
Zaki dizaji H, Monjezi N, and Sheikhdavoodi J. 2018. Investigating effective factors on sugarcane production performance to increase the production of sugarcane using data mining. Iranian Journal of Biosystems Engineering, 49(3): 501-511. (In Persian).
 
JOURNAL OF AGRICULTURAL SCIENCE AND SUSTAINABLE PRODUCTION
Volume 30, Issue 4
January 2021
Pages 213-228

Files

Share

How to cite

Statistics