From Learning to Optimization in Intelligent Logistics Systems

Call for Papers – From Learning to Optimization in Intelligent Logistics Systems

Journal: Transportation Research Part E: Logistics and Transportation Review
Publisher: Elsevier
Submission deadline: 30 October 2026

This special issue focuses on the integration of machine learning and intelligent optimization to tackle emerging challenges in modern logistics and transportation systems. It targets high‑quality, method‑driven research that bridges operations research and machine learning, using learned solution approaches to improve planning, routing, and decision‑making in freight, transport, and city‑logistics networks.

Why this issue matters

• Logistics systems are rapidly becoming “intelligent,” powered by digitalisation, automation, real‑time tracking, and data‑driven platforms, but their increasing complexity demands more adaptive and robust optimization methods.

• Traditional OR methods often struggle with uncertainty, dynamic inputs, and large‑scale problem structures, while machine learning can help learn better inputs, models, and heuristics, or even embed optimization directly into learning frameworks (e.g., predict‑then‑optimize, end‑to‑end learning, and sequential learning).

• This SI encourages work that closes the gap between mathematical modelling and empirical reality, producing actionable, data‑driven, and operationally relevant methods for logistics and transport.

Key objectives and scope

Papers should clearly demonstrate how learning mechanisms (e.g., ML models, reinforcement learning, meta‑learning) strengthen optimization processes in intelligent logistics and transport systems. The SI focuses on, but is not limited to:

• Integrating operations research and machine learning to develop novel optimization methods that exploit learning to find high‑quality solutions.

• Generating practical, operations‑level insights that improve efficiency, sustainability, and robustness in logistics.

• Supporting data‑driven decision‑making under uncertainty and dynamic conditions.

Topics and application areas

Contributions are welcome from both theoretical and applied work, including conference‑based follow‑up studies from ICCL & EUROMAR 2025 and original papers not presented at conferences.

Methodological topics

• Machine learning‑based pre‑processing, parameter tuning, or feature learning for optimization algorithms.

• End‑to‑end or sequential learning frameworks that embed optimization within the learning pipeline.

• Learning‑based robust and stochastic optimization for logistics under uncertainty.

• Hybrid approaches (e.g., ML‑enhanced heuristics, matheuristics, learning‑augmented exact methods).

Application areas

• Freight, road, rail, maritime, and intermodal logistics

• Urban / city logistics and last‑mile delivery

• Routing and vehicle‑routing problems (including crowdsourced logistics)

• Collaborative and green logistics (e.g., collaborative transport, low‑emission zones, renewable‑energy‑integrated supply chains)

• Reverse logistics and circular‑economy‑oriented networks

• Shipping, port operations, and port‑call optimization

• IoT‑enabled smart logistics and autonomous‑system‑based transport

Guest editors

• Çağatay Iris, University of Liverpool Management School, UK

• Alice E. Smith, University of Alabama, USA

• Frederik Schulte, Delft University of Technology, Netherlands

• Jiangang Jin, Shanghai Jiao Tong University, China

• Rosa G. González‑Ramírez, Universidad de los Andes, Chile

Submission information

• Submission portal:
  https://www.editorialmanager.com/tre

• When submitting, select article type:
  “VSI: LearnOptLogis_Hans”

• Submission deadline: 30 October 2026

• All manuscripts must conform to the journal’s Guide for Authors:
  https://www.elsevier.com/journals/transportation‑research‑part‑e‑logistics‑and‑transportation‑review/1366‑5545/guide‑for‑authors

Papers should be original, technically sound, and clearly demonstrate how learning‑based optimization improves real‑world logistics and transportation problems, with practical implications for planners, operators, and policymakers.

ServiceSetu Academics — Premier Platform for Academic Opportunities & Research Collaboration

Visit official website of the publisher