Aircraft takeoff speed prediction with machine learning: parameter analysis and model development

Abstract With developing technology, the usage areas of aircraft are constantly expanded. In aircraft designed for different missions, it is an important issue to evaluate many design possibilities and make optimum designs by taking into account many parameters that are not directly connected to each other with equal importance. In this context, issues such as safety and performance come to the fore in aircraft designs. One of the critical situations affecting flight safety is the takeoff and landing phases of the aircraft. The speed changes that occur in these stages are an important issue. In this study, takeoff speed was predicted with different machine learning algorithms using takeoff speed data of the Boeing B-737-300 type aircraft. Linear regression, support vector regression, classification and regression trees, random forest regression, Extreme Gradient Boosting algorithms were selected from machine learning algorithms for takeoff speed prediction. Base models were created with these selected algorithms and the takeoff speed was predicted by training the data. Considering the obtained results, feature engineered was applied to minimise the error values of the proposed base models. In models developed by applying feature engineered, error values were reduced and better performance was observed in takeoff speed prediction. Takeoff speed values obtained with the developed models and actual flight speed values are presented comparatively for the first time in the literature. The simulation results emphasise that the developed models can be used as an effective and alternative method for takeoff speed prediction.