<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T02:18:06Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/30901" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/30901</identifier><datestamp>2026-09-24T07:45:06Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Razavi, Saiedeh</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Filom, Siyavash</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Civil Engineering</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2025-01-21T16:58:57Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2025-01-21T16:58:57Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2024</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/30901</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/23295</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Synchromodal freight transport is an advanced logistics approach that allows for the seam-&#xd;
less integration and dynamic interchange between transport modes—such as road, rail, and&#xd;
maritime transport. The increasing complexity of global logistics and the dynamic nature&#xd;
of synchromodal transport necessitate innovative solutions for optimal decision-making under&#xd;
real-world uncertainties and disruptions. This research presents a learning-based robust opti-&#xd;
mization framework that integrates Machine Learning (ML), Operations Research (OR), and&#xd;
uncertainty analysis to address the challenges of synchromodal transportation, aiming to derive&#xd;
data-driven, explainable decisions that enhance system performance and resilience.&#xd;
The proposed approach employs a predict-then-optimize framework, combining Bayesian&#xd;
Neural Networks with uncertainty quantification and dynamic robust optimization modules&#xd;
to solve the shipment matching problem within a synchromodal framework This integration is&#xd;
achieved through scenario-based adjustable uncertainty sets, enabling the framework to generate&#xd;
flexible plans. Decision-makers can evaluate trade-offs across various scenarios, improving the&#xd;
adaptability and robustness of logistics operations.&#xd;
In addition, this study incorporates disruption management to identify unexpected events&#xd;
impacting transportation networks and dynamically re-plan to mitigate disruptions by proposing&#xd;
Reassign with Delay Buffer and (De)consolidation strategies. Implemented for the Great Lakes&#xd;
region with nine intermodal terminals and real-world data, the framework demonstrates its&#xd;
efficacy in handling large-scale demand instances (up to 700 shipment requests). A heuristic-&#xd;
based pre-processing algorithm for feasible path generation ensures timely solutions, further&#xd;
enhancing computational efficiency.&#xd;
Numerical experiments reveal that the integration of upstream ML-based prediction with&#xd;
downstream optimization provides a range of optimal solutions instead of a single solution,&#xd;
particularly focusing on variations in road travel times, transshipment operations, and storage&#xd;
costs. By seamlessly merging the predictive capabilities of ML with the prescriptive strengths&#xd;
of OR, the framework optimizes resource utilization, reduces operational costs, and lowers en-&#xd;
vironmental impact, advancing synchromodal freight transport with a sustainable and resilient&#xd;
approach.&#xd;
This research aims to contribute to the field of synchromodal transportation by providing a&#xd;
novel framework that integrates OR and ML techniques, offering practical solutions to enhance&#xd;
logistics efficiency and reduce costs. By addressing the challenges and opportunities presented&#xd;
by the digital transformation of transportation networks, this study seeks to pave the way for&#xd;
more sustainable and resilient logistics systems in the future.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree" lang="en_US">Doctor of Philosophy (PhD)</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="layabstract" lang="en_US">This research aims to enhance the efficiency and resilience of freight transportation through a&#xd;
flexible framework known as synchromodal freight transport. Synchromodality enables dynamic&#xd;
switching between different transportation methods—such as road, rail, and maritime—based on&#xd;
real-time conditions. With increasing complexity in supply chains and transportation networks,&#xd;
decision-making becomes particularly challenging when faced with disruptions and uncertain-&#xd;
ties, such as road traffic congestions or unforeseen events.&#xd;
To address these challenges, this thesis integrates machine learning, optimization, and uncer-&#xd;
tainty analytic techniques to develop a predictive system capable of anticipating uncertainties in&#xd;
delays and demand and adapting transportation plans accordingly. By using advanced methods&#xd;
to account for uncertainties, this system helps logistics planners make better, more reliable de-&#xd;
cisions that save time, reduce costs, and lower environmental impact. Tested in the Great Lakes&#xd;
region, this approach shows promise in making freight transport more resilient and sustainable,&#xd;
ultimately improving efficiency and reducing disruptions across complex logistics networks.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en_US">en</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Freight transportation</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Logistics</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Synchromodality</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Physical internet</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Learning-based optimization</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Uncertainty quantification</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Disruption management</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Consolidation</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">A Learning-Based Robust Optimization Framework for Resilient and Sustainable Synchromodal Freight Transportation Under Uncertainty</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>