计算机工程与应用2009，Vol.45Issue(21)：235-238,4.DOI:10.3778/j.issn.1002-8331.2009.21.068
支持向量机回归的碳通量预测
Research of predicting methods for carbon flux based on support vector regression
摘要
Abstract
Precisely predicting the carbon flux through impact factors has auracted many ecologists' interest.However,there is still no perfect method to predict carbon flux effectively.In this paper,ε-support vector regression(ε-SVR) is used to predict carbon flux,and the results of ε-SVR and BP neural network(BPNN) for the prediction of carbon flux are compared.ε-SVR with differ-ent kernel functions and parameters and BPNN with different numbers of the neurons in hidden layer are analyzod.The experi-ment results show that the correlation between the carbon flux predicted by ε-SVR and BPNN and the observation values is high,However,ε-SVR converges global optimal more easily than BPNN.And the ε-SVR predicts more accurately than BPNN.关键词
ε-支持向量回归/反向传播神经网络/碳通量/预测精度Key words
ε-support vector regression/Back Propagation(BP) neural network/carben flux/predicting分类
信息技术与安全科学引用本文复制引用
陈强,吴慕春,薛月菊,杨敬锋,刘国瑛..支持向量机回归的碳通量预测[J].计算机工程与应用,2009,45(21):235-238,4.基金项目
国家科技攻关计划项目(the Key Technologies R&D Program of China under Grant No.2002BA516A08) （the Key Technologies R&D Program of China under Grant No.2002BA516A08）
国家星火计划项目(No. 2006EA780057) （No. 2006EA780057）
广东省自然科学基金(the Natural Science Foundation of Guangdong Province of ChiIla under Grant No.04300504,No. 05006623) （the Natural Science Foundation of Guangdong Province of ChiIla under Grant No.04300504,No. 05006623）
广东省科技攻关计划(the Key Technologies R&D Program of Guangdong Province,China under Grant No.2005820701008.No.2005B10101028,No.2004B20701006). （the Key Technologies R&D Program of Guangdong Province,China under Grant No.2005820701008.No.2005B10101028,No.2004B20701006）
