投影寻踪自回归模型在长江径流量预测中的应用

Application of projection pursuit auto regression model in predicting runoff of Yangtze River

为准确预测长江径流量,引入投影寻踪自回归模型,用自相关分析技术确定预测因子,构造了新的投影指标函数,并用基于实数编码的加速遗传算法优化投影指标函数,建立了投影寻踪自回归流量预测模型.将该模型应用于长江径流量的预测,结果表明用该模型预测长江流量时序是可行和有效的.

In order to accurately predict the runoff of the Yangtze River, a new model--the projection pursuit auto regression mode is introduced. The prediction factors were determined using of the auto-correlation analysis technique. A new function of projection indices was established and optimized using a real coded accelerating genetic algorithm. A projection pursuit auto regression model was established and applied in the predication of the runoff of the Yangtze River. The calculated results show that the time series of the predicted runoff of the Yangtze River by means of the present model is feasible and effective.