Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{194937,
        author = {Sundhara Murthy Sreelohith and Latheef Ahmed A and MADHAN SAI C R and Jagath Abhijit K},
        title = {Ethical Multi-Agent Disaster Resource Allocation and Management System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {5855-5865},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194937},
        abstract = {Natural disasters and large-scale crises require rapid, equitable, and efficient allocation of critical resources across multiple administrative levels. Traditional disaster response mechanisms often rely on fragmented data and manual decision-making, which is prone to delays, misallocation, and limited situational awareness during rapidly escalating emergencies. This paper presents a comprehensive, AI-driven multi-role disaster management framework that dynamically forecasts demand and optimizes resource allocation across district, state, and national jurisdictions. The proposed system integrates a high-performance FastAPI backend for real-time scenario orchestration with role-specific dashboards to provide real-time operational visibility. A novel hybrid decision-support architecture is introduced, combining AI/ML predictive pipelines which estimate localized demand, event severity, and regional vulnerability with a rigorous PuLP-based Linear Programming (LP) optimization engine. This core solver automatically generates optimal resource distribution strategies that maximize aid effectiveness while strictly adhering to supply constraints and fairness mandates. To ensure reliability in high-stress environments, the framework incorporates extensive operational certification, automated scenario auditing, and bias-state evaluation pipelines that stabilize supply chains under duress. Experimental results from extensive simulated disaster scenarios demonstrate that the proposed approach achieves highly efficient, equitable, and resilient real-time resource distribution, highlighting the effectiveness of integrating predictive machine learning with operations research for intelligent disaster management systems.},
        keywords = {Disaster management, AI-driven resource allocation, linear programming optimization, predictive vulnerability modeling, multi-echelon coordination, intelligent decision support systems},
        month = {March},
        }