This study proposes an integrated framework for identifying weather-disruption indicators by news intelligence in maritime transportation systems and ascertaining their impact on a port's operation. Port performance can be affected by many external and operational factors, including labor disputes, geopolitical tensions, infrastructure constraints, economic disruptions, and extreme weather conditions. This paper focuses on weather-related disruptions and examines how such events can be detected in unstructured news sources and their impact on port reliability performance. The framework combines keyword-based retrieval, large language model (LLM) classification, structured event extraction, and temporal reconstruction to convert online news into interpretable disruption indicators capturing event occurrence, type, impact, and timing. The impact of these indicators is then determined on a port's monthly reliability measures derived from vessel stay-duration records. The findings provide evidence that news-derived weather indicators can support the contextual interpretation of port reliability changes.

Today, logistic systems face many issues. Logistics terminals increasingly suffer from congestion, long waiting times and inefficient truck scheduling. To overcome this limitations this paper proposes a closed loop framework combining Machine Learning (ML)-based Estimated Time of Arrival (ETA) prediction with dynamic dock scheduling and rescheduling at logistics terminals under truck arrival uncertainty. Three prediction models namely an Artificial Neural Network (ANN), a Random Forest (RF), and XGBoost are tested on a dataset from the U.S. Bureau of Transportation Statistics (BTS) adapted to a freight logistics. Among the three tested models, XGBoost achieves the best performance with a Mean Absolute Error (MAE) of 6.35 minutes and an R2 of0.9768,andisselectedas an inputto MixedIntegerLinearProgramming (MILP) formulations models: an initial scheduling model minimizing makespan based on predicted ETAs, and a dynamic rescheduling model that adjusts assignments based on Actual Time of Arrivals (ATAs). Validated on five days from the test set with 6 docks. These Results demonstrate that tightly coupling data-driven ETA prediction with proactive scheduling decisions significantly reduces terminal disruption.

With growing sustainability and environmental concerns, the maritime shipping route selection process has become more complex, involving simultaneous optimisations across multiple criteria. This paper proposes a user-driven Software-as-a-Service (SaaS) application platform as a decision-support tool for freight forwarders, shippers, and customers, assisting them in optimising route and carrier selection within multimodal transport networks. While traditional approaches, such as multi-criteria decision-making (MCDM) methods have addressed similar decision-making problems in which users can adjust decisions based on their preferences to identify trade-offs, they have largely relied on explicit weight schemes for a fixed set of predefined criteria. In practice, these weights are often challenging to determine, especially in maritime logistics, where each criterion is governed by multiple different stakeholders with conflicting interests. Furthermore, even though customers may prefer different preference elicitation methods, existing application systems in the maritime sector often cannot incorporate diverse user inputs (e.g., weights or aspiration levels). To address these limitations, we propose a Customer-Driven Unified Goal Programming (CD-UGP)-based SaaS application framework that allows decision-makers to express preferences either through aspiration levels or using a weight scheme. The proposed framework is evaluated and validated with multiple real-life scenarios using two case studies focused on optimal container shipping route selection: (i) from Canberra to Colombo, and (ii) from Tokyo to Los Angeles. Results demonstrate that the proposed CD-UGP-based SaaS framework effectively produces more customised and practically relevant routing solutions compared to existing methods.