Survey on Disaster Management Datasets for Remote Sensing Based Emergency Applications

TL;DR

This survey reviews publicly available remote sensing datasets crucial for developing machine learning and deep learning solutions in disaster management across all disaster phases.

Contribution

It provides a comprehensive overview of high-quality datasets supporting computer vision and remote sensing tasks for disaster management.

Findings

Highlights datasets supporting all disaster phases from pre- to post-disaster.

Emphasizes the importance of high-resolution imagery for rapid detection and assessment.

Serves as a centralized reference for researchers and practitioners.

Abstract

Recent natural disasters have highlighted the urgent need for efficient data-driven approaches to disaster management. Machine learning (ML) and deep learning (DL) techniques have shown considerable promise in enhancing the key phases of disaster management including mitigation, preparedness, detection, response, and recovery. A critical enabler of successful ML or DL based applications in remote sensing, however, is the accessibility and quality of annotated datasets. With the growing availability of high-resolution imagery from unmanned aerial vehicles (UAVs) and satellites, computer vision and remote sensing algorithms have become essential tools for rapid detection, situational assessment, and decision-making in disaster scenarios. This survey provides a comprehensive overview of publicly available image-based datasets relevant to ML/DL-based disaster management pipelines. Emphasis is placed on datasets that support computer vision and remote sensing tasks across all phases of disaster events including pre-disaster, during, and post-disaster. The goal of this work is to serve as a centralized reference for researchers and practitioners seeking high-quality datasets for rapid development and deployment of remote sensing-driven disaster response solutions.