计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (18): 237-240.

• 工程与应用 • 上一篇    下一篇

基于GA-NN的碳通量预测因素选择

薛月菊1,刘曙光2,胡月明3,刘国瑛1,陈 强1   

  1. 1.华南农业大学 工程学院,广州 510642
    2.美国地质勘探局地球资源观测和科学数据中心,美国 南达科他州 57198
    3.华南农业大学 信息学院,广州 510642
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-06-21 发布日期:2011-06-21

Factors selection for prediction of carbon flux based on Genetic Algorithm—Neural Network

XUE Yueju1,LIU Shuguang2,HU Yueming3,LIU Guoying1,CHEN Qiang1   

  1. 1.College of Engineering,South China Agricultural University,Guangzhou 510642,China
    2.US Geological Survey Earth Resources Observation and Science Center,SD 57198,USA
    3.College of Information,South China Agricultural University,Guangzhou 510642,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-06-21 Published:2011-06-21

摘要: 研究和选择碳循环的影响因素是预测碳通量的重要环节,也是研究碳循环机理的重要步骤。然而从众多的影响因素中选择重要的因素,依然存在着困难。提出利用相关分析、遗传算法和神经网络进行碳通量预测的主要因素选择的方法,首先用相关分析去处冗余的因素;然后利用遗传算法,以选择最小数目的因素时,最大碳通量的观测值和用神经网络预测值的相关系数为准则,来搜寻最优的影响因素。实验证明该方法能在不影响(或尽量小地影响)预测精度的前提下,有效地选择出碳通量预测的重要因素。

关键词: 因素选择, 遗传算法, 神经网络, 碳通量预测

Abstract: Selecting the driving factors for carbon cycle is critical step prior predicting carbon dioxide(CO2) flux and it also is the important step to study the machines of carbon cycle.But,how to select the driving factors among the plenty of factors is still a challenge problem.This paper proposes a method of driving factors selection based on correlation analysis,Genetic Algorithm(GA)—Neural Network(NN).The redundant factors are reduced using correlation analysis firstly.And then,GA is used to select the driving factors according the criteria that maximizes the correlation coefficient between the Net Ecosystem Exchange(NEE) observed and the NEE predicted using Radial Basis Function Neural Network(RBFNN) as well as minimizes the number of driving factors.To evaluate the validity of the proposed method,it is used to select the driving factors in predicting CO2 flux of Duke Forest.The experimental results illustrate that the method can mine the main driving factors for predictive CO2 flux effectively without loss of precision.

Key words: factors selection, Genetic Algorithm(GA), Neural Network(NN), prediction of carbon flux