基于最小二乘支持向量机的灌区粮食产量预测研究  

Grain Yield Prediction for Irrigation District Based on Least Squares Support Vector Machine

作　　者：宰松梅[1,2] 贾艳辉[1] 丁铁山 温季[1] 郭冬冬[1] 

机构地区：[1]中国农业科学院农田灌溉研究所,河南新乡453003 [2]西北农林科技大学,陕西杨凌712100 [3]黑山县农业综合开发办公室,辽宁黑山121400

出　　处：《安徽农业科学》2010年第1期98-100,共3页Journal of Anhui Agricultural Sciences

基　　金：国家863计划项目(2006AA100213);国家科技支撑计划项目(2007BAD38B04)

摘　　要：对常用作物产量预测模型进行了简要评述,建立了基于最小二乘支持向量机的灌区产量预测模型。对灌区作物产量进行模拟计算,并用检验样本与灰色预测和神经网络模型的预测结果进行了比较。结果表明,最小二乘支持向量机预测的最大误差7.12%,平均误差4.81%。最小二乘支持向量机模型有较高的预测精度和良好的推广能力,可做为灌区粮食产量预测的一种新方法。Commonly used grain yield forecasting models were briefly reviewed, and a yield prediction model of irrigation district was established based on least squares support vector machines. The grain yield in irrigation district was analog calculated. And the test samples were used to compare with gray prediction, and neural network model. The maximum predicted error of least squares SVM was 7.12% , with an average error of 4.81%. The resuhs showed that least squares support vector machine model has high prediction accuracy and strong generalization ability. So it could be used as a new method for irrigation district yield prediction.

关 键 词：产量 预测 最小二乘支持向量机 模型 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]