安徽农业科学2013，Vol.41Issue(6)：2775-2777,2781,4.
基于REMCC-BPNN的粮食产量预测研究
Study on Prediction for Grain Yield Based on REMCC-BPNN
摘要
Abstract
Accurate prediction of grain yield has a great significance for food safety and social stability. An improved Back-propagation Neural Network (BPNN) model named REMCC-BPNN for time series forecasting was proposed. REMCC-BPNN optimizes the training model for BPNN based on the minimum correlation coefficient of the absolute value of the K nearest neighbor training samples' fitting relative error and the K training samples' time order. Two real-world datasels, the grain yield from 1985 to 2011 in China and the grain yield from 1995 to 2010 in Hunan, China, was used to test the effectiveness of REMCC-BPNN. The results showed that the prediction accuracy of REMCC-BPNN is better than that of several frequently-used prediction models for time series, such as BPNN, SVR, ARIMA and GM( 1 ,N). The REMCC-BPNN prediction model is faster and more stable.关键词
BP神经网络/时间序列/粮食产量/预测Key words
Back-propagation neural network/Time series/Grain yield/Prediction分类
农业科技引用本文复制引用
谢元瑰,张红燕,陈玉峰..基于REMCC-BPNN的粮食产量预测研究[J].安徽农业科学,2013,41(6):2775-2777,2781,4.基金项目
国家科技支撑计划重大项目(农村物联网基础平台共性关键技术研究)(2012BAD35B05) （农村物联网基础平台共性关键技术研究）
湖南省研究生科研创新项目(时间序列分析方法在农业虫害预测中的应用研究)(CX2012B307) （时间序列分析方法在农业虫害预测中的应用研究）
湖南农业大学科技创新基金项目(2012ZK63). （2012ZK63）
