Implementation of machine learning methods for air traffic management

Despite significant technological advancements, various factors continue to affect the safety and efficiency of multiple industries, including air transportation. One of the critical challenges in this field remains flight delays, which not only generate substantial economic costs but also pose potential risks to operational safety. This paper explores the application of machine learning methods for delay prediction and airport capacity modeling. Regression algorithms, decision trees, and reinforcement learning techniques were employed to analyze operational data. The study findings indicate that implementing machine learning models enables more precise delay forecasting, supporting decision-making processes and optimizing air traffic management.