信息不完全下极端气象灾害态势感知建模优化-《计算机技术与发展》

文章信息/Info

Title:: Situation Awareness Modeling and Optimization of Extreme Meteorological Disasters Based on Incomplete Information

作者:: 杨继君¹ ; 曾子轩²; 3; 1. 广东财经大学,广东广州 510320;?
2. 上海交通大学,上海 200030;?
3. 广西财经学院跨境电商智能信息处理重点实验室,广西南宁 530003

Author(s):: YANG Ji-jun¹ ; ZENG Zi-xuan²; 3; 1. Guangdong University of Finance & Economics,Guangzhou 510320,China;
2. Shanghai Jiaotong University,Shanghai 200030,China;
3.?Guangxi Key Laboratory Cultivation Base of Cross-border E-commerce Intelligent Information Processing, Guangxi University of Finance & Economics,Nanning 530003,China

Keywords:: incomplete information; hidden Markov chain; extreme meteorological disasters; situation awareness; modeling and optimizing

摘要:: 极端气象灾害事件态势演化问题是应急决策者关心的首要问题,因为它是制定应急处置与救援措施的前提和依据。鉴于整个极端气象灾害的态势演化过程类似于一个隐马尔可夫状态转移过程,为此首先设计了极端气象灾害事件态势演化框架模型,在此基础上构建基于隐马尔可夫状态转移的极端气象灾害态势感知模型及其求解算法,实现对极端气象灾害的态势进行实时精准感知,以便为应急决策者提供决策支持。鉴于极端气象灾害相关信息的不完全性,致使极端气象灾害态势感知模型中部分参数的初始值选择存在不足,为此引入贝叶斯方法对其进行修正,很好地克服了上述问题。最后通过实例分析说明该方法的应用过程和实际意义。此外,该方法也为极端气象灾害态势演化规律的探索提供了新的思路和途径。

Abstract:: Situation evolution of extreme meteorological disasters is the primary problem that the emergency decision makers care about, because it’s the premise and basis for emergency response and rescue measures. In view of the fact that the evolution process? ? ?of extreme meteorological disasters is similar to a hidden Markov state transition process, a framework model for the evolution of extreme meteorological disasters is constructed. Then situation awareness model and its solution algorithm of extreme meteorolo-gical disasters based on hidden Markov chain are designed to accurately perceive the situation of extreme meteorological disasters and provide decision support for emergency decision - makers. Due to incomplete information of extreme meteorological disasters, the Bayesian method is applied to modify the initial values in this model, which overcomes above problems effectively. Finally, the application process and practical significance of this method are illustrated by an example. In addition,this method also provides a new idea and way to explore the evolution law of extreme meteorological disaster.