Elenna Dugundji, PhD
Director, Deep Knowledge Lab for Supply Chain and Logistics | Research Scientist MIT Center for Transportation & Logistics
- Cambridge MA
Dr. Dugundji shapes supply chain futures by bringing expertise in demand forecasting, machine learning and AI.
MIT Center for Transportation & Logistics
View more experts managed by MIT Center for Transportation & Logistics
Social
Biography
• Network analytics - impact of planned road disruption on feeder highways to airports and maritime ports and evaluation of public works maintenance schemes
• Optimization of operational processes - improvement of import and export processes, involving warehousing, airside and landside transport, via information sharing and collaborative planning
• Tactical planning - evaluation of routing and packaging decisions for cold chain logistics of special air cargo (Pharma, Fresh) in the context of economic and environmental sustainability
• Strategic asset management - strategic decisions in airports and maritime ports related to maintenance of assets and construction of facilities
Research Focus
Future Logistics & Infrastructure Systems
Shaping freight, mobility, and infrastructure systems that enable global supply networks.
Intelligent & Autonomous Supply Chains
AI-driven, data-centric, and increasingly autonomous decision systems for supply chain planning and execution.
Critical Systems & Supply Network Resilience
Ensuring continuity, preparedness, and mission assurance under disruption and geopolitical volatility.
Areas of Expertise
Education
University of Amsterdam
PhD
Environmental Sciences (Ruimtelijke Wetenschappen)
University of Amsterdam
MSc
Urban and Regional Planning (Planologie)
Massachusetts Institute of Technology
BS
Mathematics
Affiliations
- Deep Knowledge Lab for Supply Chain and Logistics : Director
Languages
- Dutch
- English
Media Appearances
Beyond the Hype: Decoding AI in Supply Chains
MIT Supply Chain Frontiers Podcast online
2026-01-20
Artificial Intelligence is frequently hailed as a transformative force for global supply chains, yet the gap between technological promise and operational reality remains a central challenge for industry leaders. In this episode, host Dr. Matthias Winkenbach, Director of Research at MIT CTL, leads a nuanced discussion on the transition from AI hype to the implementation of functional "decision technology."
Speaking Engagements/Featured Conversations
Supply Chain Futures by Bringing Expertise in Demand Forecasting, Machine Learning and AI to Research in Port Logistics.
Presenter: Elenna Dugundji, Research Scientist, Massachusetts Institute of Technology (MIT) (Live) Watch full presentation: https://www.maritimetv.com/Events/DigiMariner-X/VideoId/4968/UseHtml5/True
Garbage In, AI Out: Why Data Discipline Drives Supply Chain Optimization
In this webinar, Elenna Dugundji, Director, Deep Knowledge Lab for Supply Chain and Logistics Research Scientist with MIT explores why data discipline remains the foundational driver of supply chain optimization. Our discussion will examine the critical role of data quality, governance, system integration, and process alignment in enabling meaningful AI outcomes. Watch the full webinar here: https://www.scmr.com/article/garbage-in-ai-out-why-data-discipline-drives-supply-chain-optimization/resources
Research Papers
An effective aggregation heuristic for Capacitated Facility Location Problems with many demand points
Computers & Operations ResearchRJW Buijs, RD van der Mei, ER Dugundji, Sandjai Bhulai
2025-11-01
In location analysis, the effects of demand aggregation have been the subject of many studies. This body of literature is mainly focused on p-median and p-center problems. Relatively few papers in the literature on aggregation explicitly concern the Capacitated Facility Location Problem (CFLP). Our work examines the beneficial use of aggregation in the context of the CFLP. We focus on problems where there are significantly more demand points than potential facility locations, since this is where aggregation is most applicable in reducing complexity. We examine ways to obtain an aggregation at a fixed resolution, that is likely to perform well for a given instance of the problem. These aggregation techniques will form the core of a broader algorithmic framework, which contributes to the literature concerning heuristics for CFLPs.
From Dock to Destination: Toward an End-to-End Simulation Study
Procedia Computer ScienceKevin Power, Yassine Lahlou-Kamal, Nikolay Aristov, Elenna Dugundji, Thomas Koch
2025-01-01
This study uses a discrete-event simulation model, built with open-source software, to analyze import container flows at the Port of New York/New Jersey. The model integrates input and parameter distributions derived from extensive data analysis of publicly available import records, enhanced by machine learning techniques, including Natural Language Processing for commodity classification using unstructured shipping manifest product descriptions. Initial results demonstrate the effectiveness of Gaussian Kernel Density Estimate (KDE) and Fourier models in representing container dwell times, reducing mean absolute error compared to normal distribution by up to 39.5% for dry containers and 24.8% for reefers. A fine-tuned BERT model achieves over 80% accuracy in commodity classification to the four-digit HS code level, enabling improved input data structuring for simulation.
Forecasting traffic flow by vehicle category on a major highway impacted by road maintenance works
Transportation Research ProcediaEline A Belt, Lili Yao, Xiaoyue Li, Nan Wang, Varun Shekhar, Thomas Koch, Elena R Dugundji
2025-01-01
In this paper we look at the forecasting of traffic flow on a major highway in the Netherlands impacted by road maintenance works, examining the effects of lane closures on intensities per vehicle category. We apply several forecasting methodologies such as Prophet, Harmonic Regression, Seasonal Autoregressive (SAR), and Seasonal Autoregressive Integrated Moving Average (SARIMA) and compare them against a seasonal naive baseline model. We observe that SARIMA performs better than other models across all forecasting metrics for all sensors. This is mainly because of its capability of capturing linear trends and seasonality. There is also an opportunity to further improve the forecast accuracy of the SARIMA model by incorporating holiday information as seen in the Prophet model.
