Objectives With the drastic changes in the global climate, it is increasingly likely that the Arctic Passage will become fully navigable. However, current research on the navigability assessment of Arctic Passage faces the following challenges: Fragmented navigability assessment, difficulties in integrating multi-source heterogeneous data, as well as the lack of a systematic indicator system for complex influencing factors. Therefore, a knowledge graph chain rule and reasoning model for summer navigability decision-making is explored, and a knowledge graph construction method is proposed, thereby providing reliable and effective decision support for navigability assessment.

Methods First, multimodal and multi-source data are preprocessed based on the relevant ontology model of Arctic Passage knowledge graph. Retrieval augmented generation technology combined with a large language model is used for ontology-guided data cleaning and verification. Entities and relationships are subsequently extracted to obtain high-confidence triples. Then, knowledge graph chain rules and reasoning models that meet decision-making needs are constructed, and the graph chain system is stored and managed using the Neo4j graph database. Finally, by incorporating the relevant rules and knowledge provided by experts in the polar field to query the knowledge graph library, the calculation and reasoning of the summer navigability of Arctic Passage are achieved.

Results The experimental verification is carried out on the example of the Northeast Passage from 2017 to 2021 and the international ship trajectory data in 2021.

Conclusions The results show that the proposed method can achieve reliable transformation from multi-source and multimodal data to decision-oriented summer navigability assessment knowledge.