AI-Enabled Resilient Freight Optimization and Responsive Network for Hazardous and Time-Sensitive Materials
Project Description
The United States urgently needs a transformational capability for the safe, efficient, and resilient movement of hazardous and time-critical materials. These commodities, ranging from nuclear medicine and fuels to humanitarian aid and defense-critical components, are the lifeblood of both daily operations and emergency response. Yet today’s systems are slow to adapt, fragmented, and reactive, leaving the nation vulnerable to cascading failures in times of crisis.
We aim to deliver an AI-driven, cyber-physical freight optimization framework and digital infrastructure platform designed specifically for the safe, efficient, and resilient movement of hazardous or time-sensitive commodities, such as medical supplies, nuclear or chemical materials, fuels, and humanitarian aid, during both routine operations and emergency scenarios where the environment and infrastructure have drastic changes..
The system will integrate digital twins, edge–cloud AI analytics, and real-time risk monitoring to dynamically orchestrate routes, monitor hazards, and enable rapid response during disruptions or disasters. By moving beyond static planning, the platform will enable a scalable national capability for adaptive, risk-informed logistics, protecting communities while ensuring critical materials always arrive on time and safely.
Start Date
Spring, Summer or Fall 2026
Postdoc Qualifications
Desired postdoctoral candidates for this project will bring a strong interdisciplinary background in artificial intelligence, data science, operations research, transportation, logistics engineering, or a closely related field. Applicants should possess deep expertise in AI/ML/Statistics methods (such as predictive modeling, reinforcement learning, or large-scale optimization), digital twin modeling, and the integration of complex real-time sensor data. Excellence in programming (Python, Julia, C++, or similar languages) and advanced analytics, with demonstrated experience applying these skills to large, real-world datasets in domains such as logistics, cyber-physical systems, or supply chain management, is preferred.
Ideal candidates will have a track record of creative problem solving, strong quantitative skills, and the ability to design and implement novel algorithms for risk-informed decision-making, network optimization, or adaptive control of multimodal systems. Experience with edge-cloud computing architectures, IoT data fusion, or privacy-by-design data sharing frameworks will be highly valued. Given the project’s emphasis on rapid prototyping and practical impact, outstanding communication skills, the ability to work as part of a diverse interdisciplinary team, and demonstrated initiative in leading collaborative research are also highly desirable. Applicants should hold a PhD in a relevant discipline at the time of appointment and have a publication record indicative of impactful, innovative research.
Co-advisors
Yuehwern Yih, Ph.D., Tompkins Professor, Edwardson School of Industrial Engineering, https://engineering.purdue.edu/SOS/research
Ziran Wang, Ph.D., Assistant Professor, Lyles School of Civil and Construction Engineering, https://engineering.purdue.edu/ICON
Stephan Biller, Ph.D., Harold T. Amrine Distinguished Professor, Edwardson School of Industrial Engineering and the Mitch Daniels School of Business. https://business.purdue.edu/centers/dcmme/
Bibliography
- He, H., Brush, T., Cai, H., Thakkar, D., Dunlop, S., & Biller, S. (2025). Developing a strategic supply chain resiliency index: an assessment of the global lithium supply for U.S. automotive EV battery production. International Journal of Production Research. doi:10.1080/00207543.2025.2534842
- Biller, B., Yi, J., & Biller, S. (2023). A Practitioner’s Guide to Digital Twin Development. In Tutorials in Operations Research: Advancing the Frontiers of OR/MS: From Methodologies to Applications (pp. 198-227). Institute for Operations Research and the Management Sciences (INFORMS). doi:10.1287/educ.2023.0263
- Biller, B., & Biller, S. (2023). Implementing Digital Twins That Learn: AI and Simulation Are at the Core. Machines, 11(4). doi:10.3390/machines11040425
- Z. Wang et al., "Mobility Digital Twin: Concept, Architecture, Case Study, and Future Challenges," in IEEE Internet of Things Journal, vol. 9, no. 18, pp. 17452-17467, 15 Sept.15, 2022, doi: 10.1109/JIOT.2022.3156028
- 122. Salama M., LeeG MK., Yih Y. “Welfare-oriented and Public Health-aware Disaster Sheltering Network Design”, International Journal of Production Research, 2025, 1-27, 10.1080/00207543.2025.2453648