A flexible framework to coordinate debris clearance and relief distribution operations: A robust machine learning approach

Abstract

This study aims to offer an integrated, flexible action plan to bridge two vital operations in the response phase of disaster management, namely debris clearance and relief items distribution. On this subject, a broad range of associated decisions, including location-allocation, inventory, scheduling, and routing, are reflected in a multi-period environment. Also, so as to provide a pliable decision chain, two substantial kinds of flexibility are considered, including network design and due dates. So, a new bi-objective mathematical model is proposed, where the first objective minimizes the total cost, and the second one minimizes the total operation time. Since travel time information accuracy has an undeniable influence on system performance, a new two-phase data-driven methodology, including a hybrid machine learning model and the distributionally robust optimization with φ- divergence, is offered to estimate reliable travel time and tackle its uncertainty. Additionally, the application and validation of the recommended model and solution methodology are investigated in a real case study. What is more, in order to explain the superiority of the proposed solution approach concerning robustness solution, various simulation experiments are executed. Ultimately, several numerical experiments are implemented, and captured results manifest that the proposed framework can enhance the system’s performance. The obtained results reveal that considering the flexibility in network design and delivery date reduces the total costs and operation time by 7 and 6 percent.