A Prediction of Grain Yield Based on Hybrid Intelligent Algorithm

Abstract

The prediction is most important goals in economic quantitative studies, it basis in design and plan future economic policies properly process over forecasting accuracy. This paper is aiming at the problem salp swarm algorithm (SSA) for predicting grain yield is prone to fall into the local optimal problem. An improved SSA is proposed with combine with back propagation neural network. Using the different advantages of SSA algorithm in global search capabilities, combining the two for further optimize the weight, improve the accuracy and robustness of the grain yield prediction model. The specific implementation is selected from 1963 to 2013.These methods are used to define agricultural datasets that supports crop growth decision for grain product and its influencing factors were tested as a data set.The results show that, the improved salp swarm optimization can be classified as a good predict tool for the domestic food production trend in recent years compared with the SSA. This paper briefly introduces three artificial methods BP neural networks, SSA and improved SSA optimization algorithm. The natural behavior of salp, barrel-shaped plankton that are mostly water by weight optimization and combined with mixed-group of intelligent algorithm are simulated. The simulation results of grain production prediction illustrate that the predict precision of the improved SSA is much higher than of both conventional BPNN and SSA techniques and it’s very efficient and practicable.