A Learning-Based Robust Optimization Framework for Resilient and Sustainable Synchromodal Freight Transportation Under Uncertainty
Bibliographic record
Abstract
Synchromodal freight transport is an advanced logistics approach that allows for the seam- less integration and dynamic interchange between transport modes—such as road, rail, and maritime transport. The increasing complexity of global logistics and the dynamic nature of synchromodal transport necessitate innovative solutions for optimal decision-making under real-world uncertainties and disruptions. This research presents a learning-based robust opti- mization framework that integrates Machine Learning (ML), Operations Research (OR), and uncertainty analysis to address the challenges of synchromodal transportation, aiming to derive data-driven, explainable decisions that enhance system performance and resilience. The proposed approach employs a predict-then-optimize framework, combining Bayesian Neural Networks with uncertainty quantification and dynamic robust optimization modules to solve the shipment matching problem within a synchromodal framework This integration is achieved through scenario-based adjustable uncertainty sets, enabling the framework to generate flexible plans. Decision-makers can evaluate trade-offs across various scenarios, improving the adaptability and robustness of logistics operations. In addition, this study incorporates disruption management to identify unexpected events impacting transportation networks and dynamically re-plan to mitigate disruptions by proposing Reassign with Delay Buffer and (De)consolidation strategies. Implemented for the Great Lakes region with nine intermodal terminals and real-world data, the framework demonstrates its efficacy in handling large-scale demand instances (up to 700 shipment requests). A heuristic- based pre-processing algorithm for feasible path generation ensures timely solutions, further enhancing computational efficiency. Numerical experiments reveal that the integration of upstream ML-based prediction with downstream optimization provides a range of optimal solutions instead of a single solution, particularly focusing on variations in road travel times, transshipment operations, and storage costs. By seamlessly merging the predictive capabilities of ML with the prescriptive strengths of OR, the framework optimizes resource utilization, reduces operational costs, and lowers en- vironmental impact, advancing synchromodal freight transport with a sustainable and resilient approach. This research aims to contribute to the field of synchromodal transportation by providing a novel framework that integrates OR and ML techniques, offering practical solutions to enhance logistics efficiency and reduce costs. By addressing the challenges and opportunities presented by the digital transformation of transportation networks, this study seeks to pave the way for more sustainable and resilient logistics systems in the future.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".