Improving Public Health Disaster Response through Data Analytics by Addressing Gaps in Technology and Resource Allocation

Natural disasters, including earthquakes, tsunamis, and volcanic eruptions, pose significant and recurrent threats to public health in Indonesia, one of the world's most disaster-prone regions. While conventional disaster management primarily focuses on emergency response, the growing scale and frequency of these events demand a shift towards proactive preparedness using advanced technology. This study addresses a critical gap in Indonesian disaster preparedness: the underutilization of data analytics for enhancing public health response and resource allocation during disasters. By developing an innovative data-driven framework that integrates real-time surveillance, predictive modeling, and machine learning, this research introduces a novel approach to improving disaster preparedness. The proposed framework empowers decision-makers to forecast healthcare needs, optimize resource allocation, and deploy early warning systems with precision. Results demonstrate that predictive modeling achieves up to a 40% improvement in resource allocation efficiency, particularly within the vital first 72 hours post-disaster, where rapid response can significantly reduce mortality and prevent disease outbreaks. This paper highlights the transformative potential of data analytics for disaster resilience, advocating for its integration into Indonesia's public health infrastructure to build a robust and adaptive disaster response system.