Risk assessments in airline operations are mostly qualitative, despite abundant data from programmes such as flight data monitoring (FDM) and flight operations quality assurance (FOQA). In this paper, features relating to runway excursion causal factors are extracted from flight data from over 310,448 flights from Airbus A320 series aircraft flown on a European network. The data is combined with meteorological data to provide additional features.

Bayesian networks are then learnt from the feature set, and two network learning algorithms are compared, Bayesian Search and Greedy Thick Thinning (GTT). Cross-validation of the resulting networks shows both algorithms produce similarly performing networks, and a subjective analysis concludes that the GTT algorithm is marginally preferred.

The resulting networks produce relative probabilities, which airlines can use to quantitatively assess runway veer-off risk under different scenarios, such as different meteorological conditions and unstable approaches.

This paper's main finding is that by utilising existing data sources, such as FDM and weather databases, airlines can create and use Bayesian networks alongside their existing qualitative risk assessment methods to provide quantitative risk assessment and understand the effect of different conditions on those risks. This is not possible with current methods in use by airlines.

The method described can be extended to other operational safety risks, such as runway overrun.

尽管来自航班数据监控（FDM）和航班运营质量保证（FOQA）等计划的大量数据，但航空公司运营中的风险评估大多是定性的。在本文中，从欧洲网络上空客A320系列飞机的310,448多次航班的飞行数据中提取了与跑道偏移因果因素有关的特征。该数据与气象数据相结合以提供其他功能。

然后从特征集中学习贝叶斯网络，并比较了两种网络学习算法，即贝叶斯搜索和贪婪厚度细化（GTT）。对生成的网络进行交叉验证表明，两种算法均会产生性能相似的网络，而主观分析得出的结论是，GTT算法在边缘上是首选。

由此产生的网络会产生相对概率，航空公司可以将其用于定量评估在不同情况下（例如，不同的气象条件和不稳定的进近情况）的跑道转向风险。

本文的主要发现是，通过利用FDM和天气数据库等现有数据源，航空公司可以创建和使用贝叶斯网络以及其现有的定性风险评估方法来提供定量风险评估，并了解不同条件对这些风险的影响。对于航空公司当前使用的方法，这是不可能的。

所描述的方法可以扩展到其他运行安全风险，例如跑道超限。