相关向量回归模型在径流预报不确定性中的研究
|
摘要
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.
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.
引文
[1]仕玉治,彭勇,周惠成.基于相关向量机的中长期径流预报模型研究[J].大连理工大学学报,2012(1):79-84.
[2]徐莹,王嘉阳,苏华英.基于遗传算法的支持向量机在径流中长期预报中的应用[J].水利与建筑工程学报,2014(5):42-45,72.
[3]李继伟,纪昌明,张新明,等.基于支持向量机的水电站中长期径流组合预报[J].水电能源科学,2013(11):13-16.
[4]ZHENG J,SONG Z,GE Z.Probabilistic learning of partial least squares regression model:Theory and industrial applications[J].Chemometrics and Intelligent Laboratory Systems,2016,158:80-90.
[5]CORDIOLI M,PIRONI C,DE MUNARI E,et al.Combining land use regression models and fixed site monitoring to reconstruct spatiotemporal variability of NO 2 concentrations over a wide geographical area[J].Science of The Total Environment,2017,574:1075-1084.
[6]YABUUCHI Y,KAWURA T,WATADA J.Analysis of the relation between health statistics and eating habits in Japanese prefectures using fuzzy robust regression model[J].Computers in Biology and Medicine,2016,72:256-262.
[2]徐莹,王嘉阳,苏华英.基于遗传算法的支持向量机在径流中长期预报中的应用[J].水利与建筑工程学报,2014(5):42-45,72.
[3]李继伟,纪昌明,张新明,等.基于支持向量机的水电站中长期径流组合预报[J].水电能源科学,2013(11):13-16.
[4]ZHENG J,SONG Z,GE Z.Probabilistic learning of partial least squares regression model:Theory and industrial applications[J].Chemometrics and Intelligent Laboratory Systems,2016,158:80-90.
[5]CORDIOLI M,PIRONI C,DE MUNARI E,et al.Combining land use regression models and fixed site monitoring to reconstruct spatiotemporal variability of NO 2 concentrations over a wide geographical area[J].Science of The Total Environment,2017,574:1075-1084.
[6]YABUUCHI Y,KAWURA T,WATADA J.Analysis of the relation between health statistics and eating habits in Japanese prefectures using fuzzy robust regression model[J].Computers in Biology and Medicine,2016,72:256-262.