A Hybrid Framework for Explainable Aviation Risk: Causal Chain Extraction from Safety Reports with Physics-Based Failure Quantification and Interventional Analysis
Abstract
Aviation authorities hold decades of accident reports whose narratives record how investigators reconstructed each accident. Computational work on these archives has mostly sorted reports into fixed taxonomies. In this work, we propose a hybrid framework in which a text-based corpus identifies the leading factors of a failure mode. Physics-based models then quantify how likely that failure is at a stated operating point. Ordered causal chains extracted from 56{,}202 American accident reports with a local large language model aggregate into a causation knowledge graph. On an evaluation sample of 2{,}000 reports, the chains recover 90.8\% of investigator-flagged causes. Each physical factor whose drivers the record carries receives an occurrence model calibrated to the accident population. A leaky noisy-OR fitted to the corpus combines the factors into a failure mode probability that supports intervention. For engine power loss, the carburetor icing model separates 1{,}205 icing accidents from other accidents using temperature and dewpoint alone, reaching 0.61 in area under the receiver operating characteristic curve against a density ratio ceiling of 0.64. Routine weather hours give no valid control, because flying concentrates in fair weather. On later years the physics adds 0.03 to that area for occurrence and nothing for severity, so its value lies in interpretability. On four named accidents, abduction gives a probability of necessity of 0.29 to 0.50 for the heat omission, under monotonicity. The Fast Causal Inference algorithm does not license the largest backdoor adjustment on the learned networks.
Related
- An integrated explainable AI framework with counterfactual optimization for decision support
- Explainable computational framework for subtype classification and biomarker identification in head and neck squamous cell carcinoma using machine learning
- A Hybrid Structural Modelling and Explainable Machine Learning Framework for Human–AI Strategic Decision Support Systems
- An Explainable Multi-Criteria Decision-Making Framework for Evaluating Malware Detection Models Across Heterogeneous Datasets
- Explainable machine learning framework with Granger-based temporal predictive validation for monitoring fiscal risk in national health insurance expenditure
BibTeX
@misc{pang2026hybrid,
title = {{A Hybrid Framework for Explainable Aviation Risk: Causal Chain Extraction from Safety Reports with Physics-Based Failure Quantification and Interventional Analysis}},
author = {Yutian Pang and Yifang Tian and Xinyu Zhao and Jueming Hu and John-Paul Clarke and Hans-Arno Jacobsen},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2610.35658},
eprint = {2610.35658},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.35658},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - A Hybrid Framework for Explainable Aviation Risk: Causal Chain Extraction from Safety Reports with Physics-Based Failure Quantification and Interventional Analysis
AU - Yutian Pang
AU - Yifang Tian
AU - Xinyu Zhao
AU - Jueming Hu
AU - John-Paul Clarke
AU - Hans-Arno Jacobsen
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2610.35658
UR - https://arxiv.org/abs/2610.35658
AB - Aviation authorities hold decades of accident reports whose narratives record how investigators reconstructed each accident. Computational work on these archives has mostly sorted reports into fixed taxonomies. In this work, we propose a hybrid framework in which a text-based corpus identifies the leading factors of a failure mode. Physics-based models then quantify how likely that failure is at a stated operating point. Ordered causal chains extracted from 56{,}202 American accident reports with a local large language model aggregate into a causation knowledge graph. On an evaluation sample of 2{,}000 reports, the chains recover 90.8\% of investigator-flagged causes. Each physical factor whose drivers the record carries receives an occurrence model calibrated to the accident population. A leaky noisy-OR fitted to the corpus combines the factors into a failure mode probability that supports intervention. For engine power loss, the carburetor icing model separates 1{,}205 icing accidents from other accidents using temperature and dewpoint alone, reaching 0.61 in area under the receiver operating characteristic curve against a density ratio ceiling of 0.64. Routine weather hours give no valid control, because flying concentrates in fair weather. On later years the physics adds 0.03 to that area for occurrence and nothing for severity, so its value lies in interpretability. On four named accidents, abduction gives a probability of necessity of 0.29 to 0.50 for the heat omission, under monotonicity. The Fast Causal Inference algorithm does not license the largest backdoor adjustment on the learned networks.
ER -