Abstract
In modern applications, Unmanned Aerial Vehicles (UAVs) are widely used in various industries such as logistics, agriculture, environmental monitoring, and emergency services. However, their operation is highly dependent on weather conditions, including wind speed, temperature, precipitation, and atmospheric pressure. The unpredictability of meteorological factors poses significant risks to the safety and efficiency of UAV flights. This study proposes an intelligent weather prediction system for UAV flight planning, based on big data and machine learning technologies. The research examines modern methods of meteorological data processing, incorporating satellite imagery, IoT sensors, and historical records. To predict key weather parameters, advanced deep learning algorithms such as Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) are utilized. The developed system achieves a forecast accuracy of up to 92%, reducing flight planning time by 30% and enhancing overall operational safety. The integration of machine learning into UAV weather prediction systems ensures adaptability and enables rapid responses to changing climatic conditions. The obtained results highlight the significance of artificial intelligence and big data analytics in aviation. Additionally, this work suggests future research directions, including the consideration of additional environmental factors such as air quality and solar radiation, as well as the potential integration with autonomous flight management systems.