Floods, earthquakes, storm surges and other natural disasters severely affect the communication infrastructure and thus compromise the effectiveness of communications dependent rescue and warning services. In this paper, a user centric approach is proposed to establish communications in disaster affected and communication outage areas. The proposed scheme forms ad hoc clusters to facilitate emergency communications and connect end-users/ User Equipment (UE) to the core network. A novel cluster formation with single and multi-hop communication framework is proposed. The overall throughput in the formed clusters is maximized using convex optimization. In addition, an intelligent system is designed to label different clusters and their localities into affected and non-affected areas. As a proof of concept, the labeling is achieved on flooding dataset where region specific social media information is used in proposed machine learning techniques to classify the disaster-prone areas as flooded or unflooded. The suitable results of the proposed machine learning schemes suggest its use along with proposed clustering techniques to revive communications in disaster affected areas and to classify the impact of disaster for different locations in disaster-prone areas.

洪水，地震，风暴潮和其他自然灾害严重影响通信基础设施，从而损害了依赖通信的救援和预警服务的有效性。在本文中，提出了一种以用户为中心的方法来在受灾和通信中断的地区建立通信。所提出的方案形成了临时集群，以促进紧急通信并将最终用户/用户设备（UE）连接到核心网络。提出了一种具有单跳和多跳通信框架的新型集群形成方法。使用凸优化可最大程度地提高形成的群集中的总体吞吐量。此外，还设计了一个智能系统，以将不同的群集及其位置标记为受影响和不受影响的区域。作为概念证明，标记是在洪水数据集上实现的，其中在建议的机器学习技术中使用特定于区域的社交媒体信息将易受灾地区分类为洪水还是未洪水。拟议的机器学习方案的适当结果表明，将其与拟议的聚类技术一起使用，可以恢复受灾地区的通信，并对易受灾地区不同地点的灾难影响进行分类。