Researchers propose a new method combining LLMs with Temporal Graph Attention Networks for port congestion prediction.
The approach enhances explainability by grounding predictions in interpretable LLM-generated insights.
Temporal Graph Attention Networks model dynamic port network interactions over time.
The hybrid model aims to improve both accuracy and transparency in maritime logistics forecasting.
📖 Full Retelling
arXiv:2603.04818v1 Announce Type: new
Abstract: Port congestion at major maritime hubs disrupts global supply chains, yet existing prediction systems typically prioritize forecasting accuracy without providing operationally interpretable explanations. This paper proposes AIS-TGNN, an evidence-grounded framework that jointly performs congestion-escalation prediction and faithful natural-language explanation by coupling a Temporal Graph Attention Network (TGAT) with a structured large language mo
# Artificial Intelligence (AI)
**Artificial Intelligence (AI)** is a specialized field of computer science dedicated to the development and study of computational systems capable of performing tasks typically associated with human intelligence. These tasks include learning, reasoning, problem-solvi...
A large language model (LLM) is a language model trained with self-supervised machine learning on a vast amount of text, designed for natural language processing tasks, especially language generation. The largest and most capable LLMs are generative pre-trained transformers (GPTs) that provide the c...
--> Computer Science > Artificial Intelligence arXiv:2603.04818 [Submitted on 5 Mar 2026] Title: LLM-Grounded Explainability for Port Congestion Prediction via Temporal Graph Attention Networks Authors: Zhiming Xue , Yujue Wang View a PDF of the paper titled LLM-Grounded Explainability for Port Congestion Prediction via Temporal Graph Attention Networks, by Zhiming Xue and 1 other authors View PDF HTML Abstract: Port congestion at major maritime hubs disrupts global supply chains, yet existing prediction systems typically prioritize forecasting accuracy without providing operationally interpretable explanations. This paper proposes AIS-TGNN, an evidence-grounded framework that jointly performs congestion-escalation prediction and faithful natural-language explanation by coupling a Temporal Graph Attention Network with a structured large language model reasoning module. Daily spatial graphs are constructed from Automatic Identification System broadcasts, where each grid cell represents localized vessel activity and inter-cell interactions are modeled through attention-based message passing. The TGAT predictor captures spatiotemporal congestion dynamics, while model-internal evidence, including feature z-scores and attention-derived neighbor influence, is transformed into structured prompts that constrain LLM reasoning to verifiable model outputs. To evaluate explanatory reliability, we introduce a directional-consistency validation protocol that quantitatively measures agreement between generated narratives and underlying statistical evidence. Experiments on six months of AIS data from the Port of Los Angeles and Long Beach demonstrate that the proposed framework outperforms both LR and GCN baselines, achieving a test AUC of 0.761, AP of 0.344, and recall of 0.504 under a strict chronological split while producing explanations with 99.6% directional consistency. Results show that grounding LLM generation in graph-model evidence enables interpretable and auditable ris...
