Planning Disaster Recovery Under Uncertain Funding: Prioritization Strategies for Irreversible Decisions
讲座通知 2026 年 6 月 16 日（星期二）， 上午 10:00 - 11:30 信息管理与工程学院102室 上海市杨浦区武东路100号 主题 Planning Disaster Recovery Under Uncertain Funding: Prioritization Strategies for Irreversible Decisions 主讲人 Chung Piaw TEO National University of Singapore Chung Piaw TEO is Provost’s Chair Professor and Executive Director of the Institute of Operations Research and Analytics (IORA) in the National University of Singapore. Prior to the current appointments, he was Head of Department, Acting Deputy Dean, Vice-Dean of the Research & Ph.D. Program as well as Chair of the Ph.D. Committee in the NUS Business School. He was a fellow in the Singapore-MIT Alliance Program, an Eschbach Scholar in Northwestern University (US), Professor in Sungkyunkwan Graduate School of Business (Korea), and a Distinguished Visiting Professor in YuanZe University (Taiwan). He was elected INFORMS Fellow in 2019. 讲座简介 Following a major disaster, agencies must act quickly to restore critical infrastructure and allocate scarce recovery resources. Yet many of the most important decisions—such as repairing roads, restoring network connectivity, or locating emergency facilities—must be made before the timing and magnitude of external funding become known. This creates a fundamental planning challenge: how should recovery actions be prioritized when budgets are uncertain and early decisions cannot be reversed? In this talk, I will present a new optimization framework that enables decision makers to construct a fixed, actionable priority list of recovery projects that can be implemented immediately and continued as funding arrives over time. Rather than optimizing for a single budget scenario, the approach identifies actions that perform well across a wide range of possible funding trajectories while preserving flexibility for future investments. The resulting model is formulated as a multi-scenario mixed-integer optimization problem with consistency constraints that enforce a common prioritization across scenarios. To solve this challenging problem efficiently, we develop a novel pegging-based heuristic that combines scenario-specific optimization with linear programming relaxations, producing robust and interpretable recovery plans. We also establish theoretical guarantees that quantify the value of committing to a single priority list before funding uncertainty is resolved. Under mild conditions, the performance loss relative to an ideal planner with perfect foresight is provably small, and our solution approach admits approximation guarantees. Using both synthetic test instances and a real-world application involving the Manhattan road network, we demonstrate that the proposed method consistently outperforms conventional prioritization rules and closely matches the performance of a full-information benchmark. The results provide new insights into how organizations can make timely, resilient, and high-quality recovery decisions in the face of uncertainty, offering practical guidance for disaster management agencies, infrastructure operators, and public-sector planners.
上海财经大学（武东路校区）
