Wind Limitations at Madeira International Airport: A Deep Learning Prediction Approach

Abstract

The unique geographical and topographical features of Madeira International Airport in Portugal significantly influence flight safety, primarily due to variable wind patterns. In this study, a machine learning approach is developed to predict runway operational statuses at Madeira International Airport, focusing on addressing wind-related challenges. To tackle this issue, a Deep Learning model is utilized. This model undergoes a particle swarm optimization process, resulting in one optimized model for each timestep, to provide minute-resolution predictions within a 20-minute timeframe. The training, validation, and testing phases for the optimized models were conducted using high-frequency wind data from Madeira International Airport. The main objective is to accurately predict the runway operational statuses, specifically whether the airport is open or closed for landing, take-off, or both. The models exhibit high performance, particularly in identifying operational conditions, reaching 99.93% precision, and a top accuracy of 94.35% predicting all runway status, underscoring their potential to enhance decision-making processes and operational efficiency under challenging weather conditions.

Keywords

• Machine learning
• aviation meteorology
• runway operations
• Madeira Airport
• flight safety