AI-Powered Satellite Imagery Processing for Global Air Traffic Surveillance

The increasing complexity of global air traffic management requires innovative surveillance solutions beyond traditional radar. This chapter explores the integration of artificial intelligence (AI) and machine learning (ML) in satellite imagery processing for enhanced air traffic surveillance. The proposed AI framework utilizes satellite remote sensing, computer vision algorithms, and geo-stamped aircraft data to improve real-time detection and classification. It addresses limitations in conventional systems, particularly in areas lacking radar coverage. The study outlines a three-phase approach: extracting radar coverage from satellite imagery, labeling data with geo-stamped aircraft locations, and applying deep learning models for classification. YOLO and Faster R-CNN models distinguish aircraft from other objects with high accuracy. Experimental trials demonstrate AI-enhanced satellite monitoring's feasibility, achieving improved detection in high-traffic zones. The system enhances situational awareness, optimizes flight planning, reduces airspace congestion, and strengthens security. It also aids disaster response by enabling rapid search-and-rescue missions. Challenges like adverse weather and nighttime monitoring remain, requiring infrared sensors and radar-based techniques. By combining big data analytics, cloud computing, and satellite monitoring, the study offers a scalable, cost-effective solution for future air traffic management. Future research will refine models and expand predictive analytics for autonomous surveillance, revolutionizing aviation safety and operational intelligence.