投影寻踪门限自回归模型在海洋冰情预测中的应用

APPLICATION OF PROJECTION PURSUIT THRESHOLD AUTO-REGRESSIVE MODEL TO PREDICTING SEA ICE CONDITIONS

为预测海洋冰情时序这类非线性动力系统,提出了投影寻踪门限自回归（PPTAR）模型。用自相关分析技术确定预测因于,构造了新的投影指标函数,用门限回归（TR）模型描述投影值与预测对象间的非线性关系,并用实码加速遗传算法优化投影指标函数和 TR模型参数。实例的计算结果表明,用PPTAR模型预测海洋冰情时序是可行和有效的。PPTAR模型简便、适用性强,克服了目前投影寻踪方法计算量大、编程实现困难的缺点,有助于投影寻踪方法的推广应用,为解抉非线性时序复杂殒测问题提供了新的途径。

In order to predict the nonlinear dynamic systems such as the sea ice conditionstime series, a new model-projection pursuit threshold auto-regressive (PPTAR) model is presented. A scheme of PPTAR modeling is also given to reduce the computational amount. The predicting factors can be determined with the technique of auto-correlation analysis, a new function of projection indexes is constructed, the nonlinear relation of projection value and predicted object can be described with threshold regressive (TR) model, and it is suggested that both the function of projection indexes and the parameters of TR model can be optimized by using a real coding based genetic algorithm. The example of predicting sea ice condition time series shows that the scheme is practical and effective. PPTAR model is simple and general, which overcomes the shortcomings of large computation amount and difficulty of computer programming in traditional projection pursuit methods, benefits the more applications of projection pursuit, and gives a new approach to resolving the complex predictive problems of the nonlinear time series.