Turkish Journal of Agriculture and Forestry




The yield of energy crops has been widely questioned by the public, but few researchers have analyzed the yield prediction of these crops, which has greatly limited their distribution and use. Based on this, in this study, a machine learning algorithm was used to design an energy crop yield simulation and prediction system, and this system was used to analyze the yields of four common energy crops. First the factors that affect the yield of energy crops are discussed, and then, the analysis of the machine learning algorithm and its application in the yield prediction of energy crops is presented, followed by an introduction to the framework of the energy crop yield simulation and prediction system. At the end of this paper, the effect of the energy crop yield simulation and prediction system was analyzed, and the feasibility conclusion was finally reached. The energy crop yield simulation and prediction system designed in this paper can greatly improve the accuracy of yield prediction when forecasting and analyzing energy crop yields. The sugarcane yield measured by the back propagation (BP) neural network model was 8694 kg/hm2, with a relative deviation of 0.86% from the actual. The BP neural network algorithm is widely used in energy crop yield prediction, and can greatly improve the accuracy. In the future, with the maturity and development of a BP neural network algorithm, it would promote the development of crop yield prediction.


Energy crops, machine learning algorithms, BP neural network, yield prediction

First Page


Last Page