This paper proposes a hybrid deep learning network architecture (Inception-VGG16) to address the challenge of accurate aircraft wake vortex identification. The model first employs a Feature0 module for preliminary feature extraction of two-dimensional Doppler radar radial velocity data. This module comprises convolution, batch normalization, ReLU activation, and max pooling operations. Subsequently, improved InceptionB and InceptionC modules are utilized for parallel extraction of multi-scale features. The InceptionB former module adopts two parallel branches, combining 1 × 1 and 3 × 3 convolutions, and outputting 64-channel feature maps, while the InceptionC latter module expands the number of channels number to 128, enhancing the model’s feature representation capability. The backend employs the VGG16’s hierarchical structure, performing deep feature extraction through multiple convolution and pooling operations, and ultimately achieving wake vortex classification through fully connected layers. Experimental validation based on 3530 wind field samples collected at the Chengdu Shuangliu Airport demonstrates that compared to traditional methods (SVM, KNN, RF) and single deep networks (VGG16), the proposed hybrid model achieves a classification accuracy of 98.8%, significantly outperforming comparative traditional methods (SVM, KNN, RF) and single deep networks (VGG16). The model not only overcomes the limitations of single networks in processing multi-scale wake features but also enhances the model’s ability to identify wake vortices in complex backgrounds through deep feature hierarchies, providing a new technical solution for aviation safety monitoring systems based on deep learning.

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.