Machine Learning Optimization Algorithms for Clustering Regions and Emergency Management: A Review.

Problem: Disasters, public health emergencies, and allied humanitarian logistical problems have continued to plague humans for years. In recent years, however, there has been a tremendous increase in the frequency of occurrence of these events. The depot location-allocation problem is vital to ensuring an effective pre-disaster management plan, and techniques for efficiently solving it are of utmost importance to public health emergency planners. Methods: Previously, traditional logistical optimization models and spatial allocation algorithms have been used to provide multi-faceted approaches and solutions to these problems. Machine learning models and related approaches have been suggested as alternative methods for addressing these problems. Results: This paper presents a review of these attempts from disparate sources, incorporating modern methods of decision-making improvement in dynamic environments through machine learning applications. Conclusion: A review of existing algorithms for clustering disaster-prone regions and managing rapidly changing disasters was conducted, with a view to developing an updated model to achieve these tasks.