Nonstationary time series prediction by incorporating external forces
Nonstationary time series prediction by incorporating external forces
复制标题
DOI：
10.1007/s00376-013-2134-z
复制
发表时间：
2013-01
影响因子：
5.8
通讯作者：
Geli Wang;Peicai Yang;Xiuji Zhou
中科院分区：
文献类型：
--
作者：
Geli Wang;Peicai Yang;Xiuji Zhou
由于观测系统的外力作用，几乎所有的气候时间序列都具有一定程度的非平稳性。因此，在重建气候动力学时应考虑这些外力。本文提出了一种新的预测非平稳时间序列的技术。这种新技术与以前的一些方法的主要区别在于，它将驱动力纳入预测模型中。为了评估其有效性，进行了三个预测实验，使用的数据产生的一些已知的经典动力学模式和气候模式与多个外力。实验结果表明，该方法能够有效地提高预测能力。
Almost all climate time series have some degree of nonstationarity due to external forces of the observed system. Therefore, these external forces should be taken into account when reconstructing the climate dynamics. This paper presents a novel technique in predicting nonstationary time series. The main difference of this new technique from some previous methods is that it incorporates the driving forces in the prediction model. To appraise its effectiveness, three prediction experiments were carried out using the data generated from some known classical dynamical models and a climate model with multiple external forces. Experimental results indicate that this technique is able to improve the prediction skill effectively.