Search papers, labs, and topics across Lattice.
This paper introduces an AI-assisted method for generating operational hazard scenarios in aviation by leveraging data from NASA's Aviation Safety Reporting System (ASRS). The approach focuses on producing structured hypotheses and narrative scenarios that reflect complex interactions among various aviation factors, while also providing a plausibility score based on historical data. A hybrid variant enhances scenario correctness and reduces variability by conditioning narrative generation on structured hypotheses derived through evolutionary abduction, demonstrating significant improvements in the realism and validity of the generated scenarios across multiple large language models.
AI-generated hazard scenarios can now be traced back to real-world ASRS reports, enhancing operational safety analysis in aviation.
Operational hazard analysis of aviation system operations must consider interactions among weather, ATC actions, airspace constraints, aircraft operations, and human factors - distinct from the functional hazard assessment applied at the aircraft-system level. We present an AI-assisted approach that generates candidate hazard scenarios from NASA's Aviation Safety Reporting System (ASRS). Given a target adverse outcome, it produces a structured hypothesis as categorical factors and a narrative scenario describing an operational event sequence consistent with the structure. Each scenario includes by a plausibility score from historical co-occurrence evidence and traceability to the most similar held-out ASRS reports. We then propose a hybrid variant, conditioning narrative generation on a structured hypothesis produced via evolutionary abduction, improving correctness and reducing variability. We evaluate multiple large language models, zero-shot versus few-shot prompting, and optional fine-tuning, measuring how prompting and model choice affect the validity and realism of the generated structures and narratives.
