Enhancing agricultural aviation safety analysis: a knowledge graph and ontology-based approach to systemic accident pattern detection

Abstract Brazilian agricultural aviation combines one of the world’s largest fleets with a rising accident rate, yet existing safety analyses remain predominantly descriptive and single-event in scope. This paper proposes and demonstrates a knowledge graph and ontology-based framework for the systemic investigation of agricultural aviation accidents, using final investigation reports published by the Brazilian Centre for Investigation and Prevention of Aeronautical Accidents (CENIPA) between 2017 and 2024. A domain ontology formalised in OWL 2 (Web Ontology Language) and aligned with the ICAO ADREP taxonomy and the Human–Aircraft–Environment–Management (HAEM) framework was instantiated as a Neo4j property graph over 16 final reports, yielding 67 weighted event–factor relationships across 20 causal factors. Weighted degree, betweenness and closeness centrality, Louvain community detection, and semantic inference rules were applied to identify systemic patterns invisible to retrospective single-event analysis. Community detection converged at modularity Q = 0.207, producing three risk clusters—Powerplant Failure Syndrome, Organisational Deficiency Cascade, and Low-Altitude Control Loss—confirmed by independent qualitative content analysis. Betweenness centrality confirmed that latent conditions—maintenance deficiency and supervisory failure—function as causal bridges, outranking all active failures and validating Reason’s accident causation model at the network level. The network-derived priority order redirects regulatory focus from pilot-centred interventions towards upstream maintenance oversight and operational supervision adequacy. The study delivers the first machine-readable ontology for Brazilian agricultural aviation accident causation and a replicable graph-based analytical pipeline extensible to other specialised aviation segments.