FiReS: A semantic model for advanced querying and prediction analysis for first responders in post-disaster response plans

Abstract

Natural disasters have emerged as a recurring and severe menace to the sustainability of countries, resulting in compromised environmental and infrastructural integrity, human fatalities, and significant economic repercussions. Prompt and effective response by first responders is essential in Disaster Risk Management (DRM) to reduce individuals' vulnerability and minimize environmental and infrastructural damages. However, disaster-related information is often generated by heterogeneous sources, making the first responders’ decision-making process complex and time-consuming. To address these challenges, a common conceptual model is imperative to improve interoperability among diverse organizations and software systems, enabling effective collaboration. Semantic Web technologies offer a promising solution for integrating heterogeneous data and providing well-defined meaning in the representation and exchange of DRM-related knowledge. In this context, this study introduces FiReS (First Responders System), an ontological model designed to enhance data interoperability among first responders in post-disaster response plans for advanced data analysis and machine learning prediction. The validation of FiReS is conducted through a series of case studies exploring various aspects of disaster response, such as the response time of emergency services and the volume and classification of emergency calls. This approach facilitates streamlined access, thorough analysis, and seamless exchange of information, empowering stakeholders to strengthen their disaster response strategies and foster resilience within communities.