Predictive Intelligent Climatology Analyzer and Information System for Airport Meteorological Center

Abstract

This study Presents a data-approach to predict the impact of weather on airport on airport performance using machine learning models. By employing recurrent and convolutional neural networks, the proposed system analyzes meteorological and operational data to improve airport decision-making. The framework achieved over 90% prediction accuracy, demonstrating its potential to enhance airport efficiency and mitigate weather-induced delays. The framework integers both historical and real-time meteorological data to identify weather patterns influencing flight schedules. This approach enhances the reliability of predictions by combining multiple data sources such as METAR and TAF reports. Furthermore, the System supports dynamic forecasting, enabling airports to adapt operations proactively. The study concludes that implementing such models can improve the sustainability and safety of air transportation systems.