AI-Enhanced Digital Twin Framework for Humanitarian Logistics: a Decision Support Approach for Crisis Response

Purpose: This study aims to develop an AI-enhanced Digital Twin framework (HLDT) for humanitarian logistics, addressing the research question: How can AI-driven Digital Twins improve decision-making and efficiency in crisis response? The scope focuses on optimizing operations, resource allocation, and transparency in disaster scenarios. Methodology: A qualitative approach was employed, conducting semi-structured interviews with 15 humanitarian logistics experts to identify challenges and inform the design of the DSA-HLDT model. The framework integrates real-time data, AI analytics, and simulation, validated using real-world datasets from organizations like the United Nations and Red Cross. Findings: The HLDT framework significantly reduced response times, optimized resource allocation, and improved multi-agency coordination. Blockchain and IoT integration enhanced operational transparency, ensuring efficient aid distribution. Originality: This research pioneers a federated AI-driven Digital Twin model for humanitarian logistics, enabling collaborative, data-driven crisis management with innovative hybrid modeling techniques.