Probabilistic Modeling versus Robust Optimization: A tutorial based on a humanitarian logistics use case

TL;DR

This tutorial compares probabilistic modeling and robust optimization in humanitarian logistics, demonstrating their application in supply chain decision-making under natural and human disruptions through a Typhoon Noru case study.

Contribution

It introduces a two-step workflow for dispatch planning and a robust routing method for last-mile delivery, integrating probabilistic and robust approaches in humanitarian logistics.

Findings

Optimal dispatch time identified for Typhoon Noru case

Robust routing enhances last-mile delivery resilience

Combined approach balances lead time and disruption risks

Abstract

This tutorial contrasts probabilistic modeling and robust optimization to determine decisions in humanitarian logistics, specifically supply chains subject to adversarial (natural and human) disruptions. Natural disruptions induce dispatch of long-haul relief supply movement as storm forecasts evolve. A two-step workflow: (i) computes an initial pre-staging plan from the most likely forecast, and (ii) evaluates that fixed plan across plausible deviations in the eventual landfall location. In this way, dispatch decisions balance lead time and improved forecast information. For last-mile distribution, we propose deliveries when transportation networks must be protected against the worst case. We apply an iterative robust routing method that detects high-concentration links and increases their effective cost to promote route diversification. A case study based on Typhoon Noru (2022) shows how the combined approach identifies an optimal dispatch time and then protects last-mile delivery from difficult-to-predict network disruptions that could jeopardize the entire supply-chain operation.