This study presents a combined Long Short-Term Memory and Extreme Gradient Boosting (LSTM-XGBoost) method for flight arrival flow prediction at the airport. Correlation analysis is conducted between the historic arrival flow and input features. The XGBoost method is applied to identify the relative importance of various variables. The historic time-series data of airport arrival flow and selected features are taken as input variables, and the subsequent flight arrival flow is the output variable. The model parameters are sequentially updated based on the recently collected data and the new predicting results. It is found that the prediction accuracy is greatly improved by incorporating the meteorological features. The data analysis results indicate that the developed method can characterize well the dynamics of the airport arrival flow, thereby providing satisfactory prediction results. The prediction performance is compared with benchmark methods including backpropagation neural network, LSTM neural network, support vector machine, gradient boosting regression tree, and XGBoost. The results show that the proposed LSTM-XGBoost model outperforms baseline and state-of-the-art neural network models.

In this study, a compound method using modified Boeing Fuel Flow Method 2 (BFFM2) and an updated First Order Approximation V3.0 (FOA3.0) method deploying the ICAO Time-in-Mode (TIM) was used to produce a more reliable aircraft emission inventory for the Guangdong–Hong Kong–Macao Greater Bay Area (GBA). The results show that compared with the International Standard Atmosphere (ISA) conditions, the total emission of nitrogen oxides(NOx) decreased by 17.7%, while carbon monoxide(CO) and hydrocarbons(HC) emissions increased by 11.2%. We confirmed that taxiing is the phase in which an aircraft emits the most pollutants. These pollutant emissions will decrease by 0.3% to 3.9% if the taxiing time is reduced by 1 minute. Furthermore, the impact of reducing taxi-out time on emissions is more significant than that of reducing the taxi-in time. Taking the total aircraft emission factors as the main performance indicators, Hong Kong International Airport (VHHH) contributes the most to the total emissions of the GBA, while the Zhuhai airport(ZGSD) contributes the least. The contribution of an individual airport to the total emissions of the GBA is mainly determined by the proportion of Boeing B77L, B77W, and B744.

Requirements of digitization, intellectualization, and integration for the programming and management of air transportation have been recommended as information technology booms. A variety of single ground movement optimization problems have been discussed with few taking the impact of other segments into account. In this research, bilevel programming is applied to simultaneously consider three problems including the gate assignment, taxi path scheduling, and pushback time delay. For evaluating the strategy of gate assignment and measuring its connection with taxiing comprehensively, an auxiliary variable and the matching degree of gate and aircraft are introduced. In addition, an algorithm incorporating the genetic algorithm and routing algorithm is designed to obtain a solution with satisfactory performance in both taxi time and conflict risk. The scheme obtained also assigns aircraft to gates more appropriately and maintains the characteristics of environmental protection as well as high efficiency, showing considerable reliability in practice.

The increasing availability of high-resolution gridded meteorological data poses significant challenges for efficient storage and rapid data access. This study proposes an adaptive variable-resolution storage (AVRS) strategy for gridded meteorological datasets, in which the spatial resolution of data blocks is dynamically adjusted according to local feature characteristics. Composite radar reflectivity (CREF) data are employed as a representative case to evaluate the performance of the proposed method. The AVRS approach partitions the data into fixed-size spatial blocks and assigns multiple resolution levels based on block-level statistical properties, enabling high-resolution preservation in feature-intensive regions while applying coarser resolution in spatially homogeneous areas. Experimental results indicate that the proposed strategy achieves effective storage reduction, with compression ratios ranging from 11.60% to 14.44% of the original data volume. Despite the substantial reduction in storage size, high reconstruction accuracy is maintained. The MSE ranges from 0.74 to 1.54, with RMSE values between 0.86 and 1.24, while the MAE remains low (0.10–0.22). The PSNR consistently exceeds 34.90 dB, with an average value above 37 dB, demonstrating limited information loss and good structural preservation. In addition, the AVRS strategy significantly improves query efficiency, reducing the average query time from 0.5 s for fixed-resolution storage to 0.2 s. Overall, the proposed method provides a practical and efficient solution for managing large-scale gridded meteorological data in atmospheric research and operational applications.

To address the inefficiencies of traditional numerical simulations and the high cost of experimental validation in the aerodynamic–stealth integrated design of S-shaped inlets for aero-engines, this study proposes a novel parameter prediction model based on a fuzzy C-means (FCM) clustering and nonlinear dynamic adaptive particle swarm optimization-enhanced radial basis function neural network (NDAPSO-RBFNN). The FCM algorithm is applied to reduce the feature dimensionality of aerodynamic parameters and determine the optimal hidden layer structure of the RBF network using clustering validity indices. Meanwhile, the NDAPSO algorithm introduces a three-stage adaptive inertia weight mechanism to balance global exploration and local exploitation effectively. Simulation results demonstrate that the proposed model significantly improves training efficiency and generalization capability. Specifically, the model achieves a root mean square error (RMSE) of $3.81\times {10}^{-8}$ on the training set and $8.26\times {10}^{-8}$ on the test set, demonstrating robust predictive accuracy. Furthermore, $98.3\%$ of the predicted values fall within the $y=x\pm 3\beta$ confidence interval ($\beta =1.2\times {10}^{-7}$). Compared with traditional PSO-RBF models, the number of iterations of NDAPSO-RBF network is lower, the single prediction time of NDAPSO-RBF network is shorter, and the number of calls to the standard deviation of the NDAPSO-RBF network is lower. These results indicate that the proposed model not only provides a reliable and efficient surrogate modeling method for complex inlet flow fields but also offers a promising approach for real-time multi-objective aerodynamic–stealth optimization in aerospace applications.