计算机与现代化

• 人工智能 • 上一篇    下一篇

基于PSO与LS-SVM的作物需水量预测

  

  1. (盐城工学院电气工程学院,江苏盐城224051)
  • 收稿日期:2018-04-24 出版日期:2018-10-26 发布日期:2018-10-26
  • 作者简介:商志根(1979-),男,江苏盐都人,盐城工学院电气工程学院副教授,博士,研究方向:进化算法,智能预测; 段小汇(1982-),男,江苏射阳人,讲师,硕士,研究方向:系统辨识。
  • 基金资助:
    盐城市农业科技指导性计划项目(YKN2014012)

Predicting Crop Water Requirements Based on Particle Swarm Optimization #br# and Least Square Support Vector Machine

  1. (School of Electrical Engineering, Yancheng Institute of Technology, Yancheng〖KG*3〗 224051, China)
  • Received:2018-04-24 Online:2018-10-26 Published:2018-10-26

摘要: 为了提高作物需水量预测精度,提出基于粒子群优化算法(PSO)优化最小二乘支持向量机(LS-SVM)的预测模型。该模型以空气湿度、温度、太阳辐射以及风速为输入,利用多项式核函数和径向基核函数的非负线性组合构造核函数,将粒子群优化算法(PSO)与交叉验证方法用于确定模型参数。实验结果表明与神经网络和随机森林相比,PSO优化的LS-SVM可获得更好的预测精度和泛化能力,可用于节水灌溉,具有较高的应用价值。

关键词: 作物需水量, 支持向量机, 粒子群优化, 核函数

Abstract: To improve the accuracy of crop water requirement prediction, a model based on Least Square Support Vector Machine (LS-SVM) optimized by Particle Swarm Optimization (PSO) is put forward. Relative humidity, air temperature,  solar radiation and wind speed are considered as input variables. A nonnegative linear combination of polynomial kernel function and radial basis kernel function is used as the kernel function of LS-SVM. PSO and cross validation are applied to optimize the parameters of LS-SVM. Experimental results indicate that LS-SVM optimized by PSO outperforms neural network and random forest. It can be used for water-saving irrigation, and has good application value.

Key words: crop water requirements, support vector machine, particle swarm optimization, kernel function

中图分类号: