Aircraft Landing Distance Prediction: A Multistep Long Short-Term Memory Approach

Abstract

Aircraft landing is one of the riskiest phases of flight with multiple possible adversities, such as sudden gust, misalignment, ground vehicle incursion, hard landing, and runway overrun. A long landing distance increases the risk of landing overrun, which appears frequently in landing accidents. In this paper, we develop a landing distance prediction approach using DASHlink data. Time dependence in the time series flight data is captured by a long short-term memory neural network model. A multistep rolling prediction strategy is developed to predict the landing distance, which captures the temporal variation of flight parameters better compared to a single-step prediction. The methodology is accompanied by several preprocessing steps, such as upsampling/downsampling, data smoothing, removal of outliers, and standardization. Several different modeling options within the overall methodology are investigated to identify the best performing model. The proposed methodology is illustrated with landing data at the Detroit Metropolitan Wayne County Airport (KDTW), and the performances of several modeling options are compared with each other as well as with several other well-established modeling methods.