School of Management, China University of Mining and Technology, Xuzhou, 221116, PR China.
School of Economics and Management, Beihang University, Beijing, 100083, PR China.
J Environ Manage. 2020 May 15;262:110382. doi: 10.1016/j.jenvman.2020.110382. Epub 2020 Mar 6.
Environmental emergencies are characterized by high uncertainty, complex evolution, and potential for serious damage, thus posing enormous pressure and difficulties to the emergency responses of enterprises and governments. Improving the efficiency and quality of emergency decision-making constitutes the primary focus of today's research in this field. This study systematically analyzes the scenario evolution mechanism of environmental emergencies with a multi-dimensional scenario space method, and key scenario factors are identified from disaster-inducing factors, disaster-bearing factors, disaster-pregnant environments, and emergency actions. Based on these, an emergency decision-making model for environmental emergencies (EEEDM) is constructed based on case-based reasoning (CBR). First, different matching algorithms are designed for accurate numerical data, fuzzy semantic data, and symbolic data. The similarity between the target scenario and the historical scenario is calculated, and the historical scenario similarity set is built according to the given threshold value. Finally, the emergency action plan of the scenario is modified with its utility value evaluated. A solution that applies to the target scenario is then obtained. Additionally, the decision-making model proposed in this paper is validated by an example of environmental emergencies. The results show that this model is scientific and reasonable, and it can better realize the multi-dimensional expression and fast matching of the scenarios and meet the decision requirements of "scenario-response". In practice, the model is capable of providing support for relevant departments' emergency decision-making.
环境突发事件具有高度不确定性、复杂演化和潜在严重损害的特点，因此给企业和政府的应急响应带来了巨大的压力和困难。提高应急决策的效率和质量是当前该领域研究的重点。本研究采用多维情景空间方法系统地分析了环境突发事件的情景演化机制，从致灾因子、承灾载体、孕灾环境和应急行动四个方面识别出关键情景因素。在此基础上，构建了基于案例推理（CBR）的环境突发事件应急决策模型（EEEDM）。首先，针对精确数值数据、模糊语义数据和符号数据设计了不同的匹配算法，计算目标情景与历史情景之间的相似度，并根据给定的阈值构建历史情景相似度集。最后，根据情景的效用值对情景的应急行动计划进行修正，从而得到适用于目标情景的解决方案。此外，通过环境突发事件的实例验证了本文提出的决策模型的科学性和合理性，该模型能够更好地实现情景的多维表达和快速匹配，满足“情景-响应”的决策要求。在实际应用中，该模型能够为相关部门的应急决策提供支持。
