Remote tower technology is an important development direction for air traffic control to reduce the construction and operation costs of small or remote airports. However, its digital and virtualized working environment poses new challenges to controllers’ situational awareness (SA). In this study, a dataset is constructed by collecting eye-tracking (ET) and heart rate variability (HRV) data from participants in a remote tower simulation control experiment. At the same time, probe questions are designed that correspond to the SA hierarchy in conjunction with the remote tower control task flow, and the dataset is annotated using the scenario presentation assessment method (SPAM). The annotated dataset containing 25 ET and HRV features is trained using the LightGBM model optimized by a Tree-structured Parzen Estimator, and feature selection and model interpretation are performed using the SHapley Additive exPlanations (SHAP) analysis. The results show that the TPE-LightGBM model exhibits excellent prediction capability, obtaining an RMSE, MAE and adjusted R² of 0.0909, 0.0730 and 0.7845, respectively. This study presents an effective method for assessing and predicting controllers’ SA in remote tower environments. It further provides a theoretical basis for understanding the effect of the physiological state of remote tower controllers on their SA.

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.