A Multi-Scale Deep Network for Aircraft Wake Vortex Recognition Using Lidar Radial Velocity Fields

Aircraft wake vortices pose significant threats to following aircraft during takeoff and landing phases. Coherent Doppler lidar provides an effective remote sensing technique for wake vortex monitoring through radial velocity measurements. However, reliable identification of wake vortices from lidar observations remains challenging due to noise and the complex multi-scale evolution of vortex structures. In this study, we propose a physics-guided multi-scale deep network (HMNet) for aircraft wake vortex identification. First, we propose a denoising module (DE) to suppress noise in radial velocity fields. Subsequently, we design a hybrid multi-scale backbone network containing a hybrid multi-scale feature extraction module (HMFE) to capture vortex structures at different spatial scales. Furthermore, we propose a feature gradient guidance module (FGGM) to incorporate physically meaningful gradient cues and enhance vortex-sensitive features. HMNet is evaluated and tested on 1401 radial velocity field data samples collected on the runway at Shenzhen Bao’an Airport. The experimental results show that HMNet achieves 97.15% accuracy, 95.83% recall, and 96.84% F1 score. Compared with the baseline VGG16 and Random Forest, HMNet improves accuracy by 6.18% and 11.88%, respectively. These results demonstrate that HMNet provides an effective solution for lidar-based wake vortex identification and can support the development of intelligent air traffic management.