Research on a Deep Learning-Based Congestion Detection and Optimization Method for Army Tactical Airspace

To address the congestion issue in tactical airspace management, this paper proposes a deep learning-based method for airspace congestion detection and traffic optimization. The method first utilizes a three-dimension Convolutional Neural Network (3D CNN) to construct a congestion detection model, enabling real-time prediction of congestion conditions within the tactical airspace. Subsequently, Particle Swarm Optimization (PSO) is applied to automatically regulate airspace traffic, reducing the risk of airspace conflicts. Experimental results demonstrate that the proposed method significantly outperforms traditional approaches in both congestion detection accuracy and traffic regulation effectiveness, providing an efficient solution for airspace management.