In recent years, there have been an increasing number of extreme weather events that have had major impacts on the built environment and particularly on people living in urban areas. As the frequency and intensity of such events are predicted to increase in the future, innovative response strategies to cope with potential emergency conditions, particularly evacuation planning and management, are becoming more important. Although mass transit evacuation of populations at risk is recognized to play a potentially important role in reducing injury and mortality rates, there is relatively little research in this area. In answering the need for more research in this increasingly important and relatively new field of research, this study proposes a hybrid simulation–optimization approach to maximize the number of evacuees moved from disaster-affected zones to safe locations. In order to improve the efficiency of the proposed optimization approach, a novel multipopulation differential evolution approach based on an opposition-based learning concept is developed. The results indicate that even for large populations the proposed approach can produce high-quality options for decision makers in reasonable computational times. The proposed approach enables emergency decision makers to apply the procedure in practice to find the best strategies for evacuation, even when the time for decision making is severely limited.

中文翻译：

---

使用公共交通系统增强对极端天气灾害的疏散反应：一种新颖的模拟方法

近年来，越来越多的极端天气事件对建筑环境，特别是对居住在城市地区的人们产生了重大影响。随着预计此类事件的频率和强度在未来会增加，应对潜在紧急情况（尤其是疏散计划和管理）的创新应对策略变得越来越重要。尽管人们公认危险人群的大众运输疏散在降低伤害和死亡率方面可能发挥重要作用，但在这一领域的研究相对较少。在回答这一日益重要和相对较新的研究领域中的更多研究需求时，这项研究提出了一种混合模拟-优化方法，以使从受灾地区转移到安全地点的撤离人员数量最大化。为了提高所提出的优化方法的效率，开发了一种基于对立的学习概念的新颖的多种群差分进化方法。结果表明，即使对于大量人口，所提出的方法也可以在合理的计算时间内为决策者提供高质量的选择。所提出的方法使紧急决策者能够在实践中应用该程序，以找到最佳的疏散策略，即使在决策时间受到严重限制的情况下。提出了一种基于对立的学习理念的新型多种群差异进化方法。结果表明，即使对于大量人口，所提出的方法也可以在合理的计算时间内为决策者提供高质量的选择。所提出的方法使紧急决策者能够在实践中应用该程序，以找到最佳的疏散策略，即使在决策时间受到严重限制的情况下。提出了一种基于对立的学习理念的新型多种群差异进化方法。结果表明，即使对于大量人口，所提出的方法也可以在合理的计算时间内为决策者提供高质量的选择。所提出的方法使紧急决策者能够在实践中应用该程序，以找到最佳的疏散策略，即使在决策时间受到严重限制的情况下。