The recognition of aircraft wake vortex can provide an indicator of early warning for civil aviation transportation safety. In this paper, several wake vortex recognition models based on deep learning and traditional machine learning were presented. Nonetheless, these models are not completely suitable owing to their dependence on the visualization of LiDAR data that yields the information loss of in reconstructing the behavior patterns of wake vortex. To tackle this problem, we proposed a lightweight deep learning framework to recognize aircraft wake vortex in the wind field of Shenzhen Baoan Airport’s arrival and departure routes. The nature of the introduced model is geared towards three aspects. First, the dilation patch embedding module is used as the input representation of the framework, attaining additional rich semantics information over long distances while maintaining parameters. Second, we combined a separable convolution module with a hybrid attention mechanism, increasing the model’s attention to the space position of wake vortex core. Third, environmental factors that affect the vortex behavior of the aircraft’s wake were encoded into the model. Experiments were conducted on a Doppler LiDAR acquisition dataset to validate the effectiveness of the proposed model. The results show that the proposed network has an accuracy of 0.9963 and a recognition speed at 100 frames per second was achieved on an experimental device with 0.51 M parameters.

This study adopts the calculation method of reducing pollutant emission during flight based on the flight record data from Nantong to Chengdu. More accurate flight record data can be obtained by interpolating, filtering, and weighting QAR (airborne quick access recorder) data in order to recover specific flight conditions. BMMF2 and P3‐T3 flow correction method are used to correct the fuel flow value in the QAR data and analyze the exact consumption time of each phase of the LTO (landing take‐off cycle) based on the key parameter. The actual pollutant emission results calculated using QAR data are compared with the reference data of International Civil Aviation Organization under the same conditions, and then changes of pollutant emission in each flight stage are analyzed. The results show that in the four modes of approach, taxi, take‐off, and climb of standard landing and take‐off (LTO) cycle, the pollutants emitted in the taxi section account for about 60% of the whole cycle, the taxi time is reduced by 6.78 min, the total emission is reduced by 11.4%, and the fuel consumption is reduced by 11.96%. The estimated nitrogen oxide emissions of LTO in stages using the QAR measured data after accurately dividing the flight phase, which is over 28% different from the original estimation method. The QAR data can analyze the pollutant emissions of aircraft in different stages. Methods for calculating the engine emissions of the LTO phase can provide a more accurate reference for assessing pollution of near‐ground aircraft and airports in different regions.

Due to the various meteorological conditions encountered in the flight process, the uncertainty of FT will change. In order to obtain the FT error, the secondary surveillance radar and aviation weather forecast data are used for analysis. According to the propagation mechanism of uncertainty, an adaptive prediction model of FT uncertainty is established. The input parameters of the adaptive model include Mach number, flight distance, vector wind and temperature. Cluster analysis and linear regression analysis are used to analyze the accuracy of the model. Compared with the static time-of-flight prediction model, the dynamic time-of-flight prediction model can accurately predict the FT even if the weather conditions are very bad. The dynamic time-of-flight prediction model is applied to air traffic management to further test the accuracy of the model. The results show that the adaptive time-of-flight prediction model based on meteorological conditions can accurately predict the arrival time of a flight to a certain waypoint.

During the final approach, the headwind leads to a reduction of landing rate, which affects the achieved capacity and the predictability of operation, time, fuel efficiency, and environmental pollution. Under headwind conditions, ground speed decrease results in increased flight time. Time-based separation (TBS) changes the separation rule of the final approach, which changes the distance separation between two aircrafts into a time separation. This paper introduces the time-based separation (TBS) based on the distance-based separation (DBS). According to the aircraft landing schedule of each airport, the ICAO (International Civil Aviation Organization) aircraft engine emission database, Boeing Fuel Flow Method 2 (BFFM2), and meteorological data of Pu-dong airport, this study uses the modified P3-T3 aviation pollutant emission model to calculate, respectively, the fuel consumption and pollutant emissions based on distance separation mode and time separation mode. According to the calculation results, TBS operation mode can save 32.52%, 19.12%, and 30.41% fuel, reduce 28.93%, 17.9%, and 29.29% CO, 31.02%, 19.36%, and 33.78% HC, 30.85%, 16.42%, and 28.67% NOx, respectively, compared with the DBS operation mode at three stages of the day. It ends that TBS has an obvious optimization effect on fuel consumption and pollutant emission compared with DBS from data.