Toward Knowledge-Enhanced Geohazard Intelligence: A Review of Knowledge Graphs and Large Language Models

Geohazards such as landslides, earthquakes, debris flows, and floods are governed by complex interactions among geological, hydrological, and human processes. Traditional data-driven models have improved hazard prediction but often lack interpretability and adaptability. This review examines the evolution of knowledge-guided approaches in geohazard research, highlighting how knowledge representation and artificial intelligence have progressively converged to enhance understanding, reasoning, and model transparency. A bibliometric analysis of 1410 publications indexed in the Web of Science reveals an evolution from early ontology-based knowledge engineering for expert reasoning to knowledge graphs (KG), frameworks enabling multi-source data integration and relational inference, and more recently, to large language model (LLM), augmented systems for automated knowledge extraction and cognitive geoscience. This review synthesizes advances in knowledge representation, knowledge graphs, and LLM-based reasoning, demonstrating how hybrid models that embed physical laws and expert knowledge can improve the interpretability and generalization of machine learning. These developments enable new forms of knowledge-driven geohazard intelligence and support applications in hazard monitoring, early warning, and risk communication. There are challenges we still face, including semantic fragmentation, limited causal reasoning, and sparse data for extreme events. Future directions require unified knowledge–data–mechanism architectures, causality-aware modeling, and interoperable standards to advance trustworthy and explainable geohazard intelligence.