基于最小二乘支持向量机的灌区粮食产量预测研究

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。最小二乘支持向量机,采用二次规划方法代替传统的支持向量机来解决函数估计问题。最小二乘支持向量机在利用结构风险原则时,在优化目标中选取了不同的损失函数,即误差ξ_i（允许错分的松弛变量）的二范数。这使得最小二乘向量机的优化问题为：min（1/2）‖w‖^2＋C（1/2）sum from i=1 to 1ξi~2（ξi是松驰变量;C为正则化参数）。用于函数估计的最小二乘SVM为：y（x）=sum from k=1 to Nαk K（x,xk）＋b。采用等式约束可以将求解的优化问题转化成线性方程,大大减少算法的复杂性,另外,采用径向基核函数的最小二乘SVM仅需确定γ、σ2个参数（γ为可调参数,σ为核函数宽度系数）,参数的搜索空间由标准SVM的三维降低到二维,极大地加快了建模速度。对γ,σ2个参数通过模型评估来确定参数最优值,大大提高了预测的精度。对河南省人民胜利渠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SVM预测的最大误差7.12%,平均误差4.81%;灰色理论预测的最大误差38.36%,平均误差17.52%;神经网络预测的最大误差10.40%,平均误差6.80%。可见,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,预测结果优于灰色预测理论和人工神经网络,可作为灌区粮食产量预测的一种新方法。

Grain Yield Prediction for Irrigation District Based on LS-SVM

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 （LS-SVM）. 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 results showed that LS-SVM model has high prediction accuracy and strong generalization ability. So it could be used as a new method for irrigation district yield prediction