Climb Performance Prediction in High Drag Configuration Middle-Class Transportation Aircraft: An Ensemble Learning Approach

Abstract

This study addresses the application of machine learning and artificial neural network models for predicting the climb speed of the C-130H military transport aircraft. Random Forest, Neural Network, and Ensemble models were developed to overcome limitations of traditional chart reading and interpolation methods. Models were trained on flight manual data, considering factors such as gross weight, pressure altitude, drag index, temperature deviation, and engine efficiency. Comparative analysis revealed the Ensemble approach, combining Random Forest and Neural Network techniques, provided the highest accuracy (R² ≈ 0.4532), followed by Random Forest (R² ≈ 0.4303) and Neural Network (R² ≈ 0.3765) models. All significantly outperformed the traditional Young Method (R² = -1.2673). Feature importance analysis identified pressure altitude, gross weight, and engine efficiency as critical factors influencing climb speed. The ensemble approach demonstrated more reliable and accurate results in predicting C-130H climb rates, reducing risks associated with single-model reliance. This research highlights the potential of machine learning in aircraft performance prediction, offering possibilities for improving pre-flight preparation, reducing workload, and enhancing flight safety. Implications for the aviation industry and future research directions are discussed, emphasizing the role of advanced predictive models in shaping future flight operations and aircraft performance management.