相关向量回归模型在径流预报不确定性中的研究

Research on uncertainty of runoff forecast by correlation vector regression model

全球气候变暖,各种水域的径流变化也变得更加难以预测,而径流的变化对船舶的航行安全有着非常大的影响。因此,为了满足航运业对航道径流预测的需求,本文提出了基于相关向量回归模型的预测算法,通过先进的计算机建模技术,实现了对径流向量的自回归模型的建立与仿真。文中重点研究了在复杂的水域环境下,如何建立一个相对稳定的径流变化模型,同时设置了冲击函数,对此预测模型的不确定行为进行验证,此模型中采用了卡尔曼滤波算法,以达到良好的预测效果。

With the warming of global climate, the variation of runoff in various waters becomes more unpredictable,and the change of runoff has a great influence on the safety of navigation. Therefore, in order to meet the demand of the shipping industry for the runoff forecasting, this paper proposes a prediction algorithm based on the correlation vector regression model. Through the advanced computer modeling technology, the establishment and simulation of the runoff vector autoregressive model is realized. In this paper, we focus on the study of how to establish a relatively stable model of runoff variation in a complex water environment, and set up a shock function to validate the uncertain behavior of this model. In this model, Kalman filter algorithm is used to achieve Good predictive effect.