Runway excursions have led to the installation of Engineered Material Arresting Systems (EMASs). An EMAS is a passive arresting system designed to decelerate an aircraft by dissipating its energy when it skids past the runway during the landing and takeoff flight phases. This study presents an overview of EMAS technology, its constructability, installation considerations, material composition, mechanical behavior, and energy absorption mechanism. Additionally, the data-driven performance prediction of the aircraft stopping distance on the EMAS bed from 109 data points was analyzed using four machine-learning models: Ridge Regression, Support Vector Regression, Categorical Boosting, and Adaptive Boosting. The model performances were evaluated using the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). The Categorical Boosting model exhibited the best predictive performance, with the highest test R2 value of 0.903 and the lowest test RMSE and MAE values of 11.954 and 7.774, respectively. The interpretability technique revealed simulated aircraft mass as the most dominant feature in predicting the aircraft stopping distance, followed by crushing stress and aircraft entry speed. The study explores the potential of a data-driven framework for predicting aircraft stopping distance, highlighting opportunities for further development of predictive modeling approaches for runway safety applications.
