Integrating Machine Learning and Remote Sensing in Disaster Management: A Decadal Review of Post-Disaster Building Damage Assessment

Abstract

Natural disasters pose significant threats to human life and property, exacerbated by their sudden onset and increasing frequency. This paper conducts a comprehensive bibliometric review to explore robust methodologies for post-disaster building damage assessment and reconnaissance, focusing on the integration of advanced data collection technologies and computational techniques. The objectives of this study were to assess the current landscape of methodologies, highlight technological advancements, and identify significant trends and gaps in the literature. Using a structured approach for data collection, this review analyzed 370 journal articles from the Scopus database from 2014 to 2024, emphasizing recent developments in remote sensing, including satellite and UAV technologies, and the application of machine learning and deep learning for damage detection and analysis. Our findings reveal substantial advancements in data collection and analysis techniques, underscoring the critical role of machine learning and remote sensing in enhancing disaster damage assessments. The results are significant as they highlight areas requiring further research and development, particularly in data fusion techniques, real-time processing capabilities, model generalization, UAV technology enhancements, and training for the rescue team. These areas are crucial for improving disaster management practices and enhancing community resilience. The application of our research is particularly relevant in developing more effective emergency response strategies and in informing policy-making for disaster-prepared social infrastructure planning. Future research should focus on closing the identified gaps and leveraging cutting-edge technologies to advance the field of disaster management.