Identifying Incident Causal Factors to Improve Aviation Transportation Safety: Proposing a Deep Learning Approach

Table 3

There are sixteen primary causal factors identified by the human experts in the database.

Primary casual factor	Count	Percentage in all incidents
Human factors	112,305	58.6%
Aircraft	43,119	22.5%
Company policy	7,676	4.0%
Procedure	7,626	4.0%
Weather	6,450	3.4%
Airport	4,475	2.3%
ATC equipment/buildings	2,803	1.5%
Chart or publication	2,519	1.3%
Environment, non-weather-related	2,180	1.1%
Airspace structure	1,163	0.6%
Equipment/tooling	465	0.2%
Manuals	338	0.2%
Staffing	238	0.1%
MEL	211	0.1%
Incorrect/unavailable part	154	0.1%
Logbook entry	32	0

The distribution of causal factors is highly unbalanced. Extant research primarily focus on the identification of the first two factors and ignore others. This study addresses the six most frequent factors, which account for as much as 95% of all incidents. Therefore, our solution is more applicable and feasible, because it can handle more factors, and is not targeting all factors, which causes the prediction performance to be worse due to the data unbalance.