The terminal airspace that surrounds an airport is the area with high flight density and complex structure. Aircraft are asked to follow the standard arrival and departure routes in terminal airspace, yet the actual trajectories may deviate due to air traffic control (ATC) instructions, pilots' decisions, surveillance and flying performance variations, etc. Predicting aircraft trajectories considering such uncertainties plays a crucial role in evaluating a redesign of the standard routes. Traditional simulation approaches for generating aircraft trajectories in a terminal airspace are cumbersome to use as it requires a detailed setup for each new scenario, while most existing data-driven methods can only be used in an airspace with historical trajectories, not applicable to new structure designs or other terminal areas. To fill in gap, in this paper, we develop a new model based on Multilayer Perceptron Neural Network (MLPNN) to predict aircraft trajectories with uncertainties for terminal airspace design evaluations. A key feature of the proposed model is that it is trained on existing standard routes yet it can be applied to new standard routes to generate trajectories. The enabler of the model's transferability is a novel input-and-output construction method for feature representations of raw trajectory data based on domain knowledge, including trajectory reconstruction, feature engineering, and output designing. After the input-and-output construction, a supervised learning model based on MLPNN is built to predict the standard deviations from the extracted features using historical trajectory data of existing standard routes. Once the model is built, trajectories with uncertainty can be simulated, through applying Gaussian distribution and exponential moving average algorithms, even on newly designed standard routes, where no aircraft have flown yet. Subsequently, new terminal airspace designs could be evaluated for their safety, efficiency, and environmental implications based on the simulated trajectories. The proposed model was tested on real-world operational data. Results showed that the model can quantify the characteristics of aircraft trajectories that are transferable across standard routes, and generate trajectories for new standard routes. We also demonstrated the proposed model on evaluating deficiencies on fuel consumption of actual arrival trajectories compared with the designed arrival routes. The generated trajectories showed 23%–37% more fuel consumption on average than the standard arrival routes in the terminal airspace of Hong Kong International Airport, which was validated with actual flight data.

Short-term forecasting of passenger flow is critical for transit management and crowd regulation. Spatial dependencies, temporal dependencies, inter-station correlations driven by other latent factors, and exogenous factors bring challenges to the short-term forecasts of passenger flow of urban rail transit networks. An innovative deep learning approach, Multi-Graph Convolutional-Recurrent Neural Network (MGC-RNN) is proposed to forecast passenger flow in urban rail transit systems to incorporate these complex factors. We propose to use multiple graphs to encode the spatial and other heterogenous inter-station correlations. The temporal dynamics of the inter-station correlations are also modeled via the proposed multi-graph convolutional-recurrent neural network structure. Inflow and outflow of all stations can be collectively predicted with multiple time steps ahead via a sequence to sequence(seq2seq) architecture. The proposed method is applied to the short-term forecasts of passenger flow in Shenzhen Metro, China. The experimental results show that MGC-RNN outperforms the benchmark algorithms in terms of forecasting accuracy. Besides, it is found that the inter-station driven by network distance, network structure, and recent flow patterns are significant factors for passenger flow forecasting. Moreover, the architecture of LSTM-encoder-decoder can capture the temporal dependencies well. In general, the proposed framework could provide multiple views of passenger flow dynamics for fine prediction and exhibit a possibility for multi-source heterogeneous data fusion in the spatiotemporal forecast tasks.

Under increasing economic and environmental pressure, airlines are constantly seeking new technologies and optimizing flight operations to reduce fuel consumption. However, the current practice on fuel loading, which has a significant impact on aircraft weight and fuel consumption, has yet to be thoroughly addressed by existing studies. Excess fuel is loaded by dispatchers and (or) pilots to handle fuel consumption uncertainties, primarily caused by flight time uncertainties, which cannot be predicted by current Flight Planning Systems (FPS). In this paper, we develop a novel spatial weighted recurrent neural network model to provide better flight time predictions by capturing air traffic information at a national scale based on multiple data sources, including Automatic Dependent Surveillance - Broadcast (ADS-B), Meteorological Aerodrome Reports (METAR), and airline records. In this model, a spatial weighted layer is designed to extract spatial dependences among network delay states (i.e. average flight delay at each airport and average flight delay of each Origin-Destination (OD) pair for a specific time interval). Then, a new training procedure associated with the spatial weighted layer is introduced to extract OD-specific spatial weights and then integrate into one model for a nationwide air traffic network. Long short-term memory (LSTM) networks are used after the spatial weighted layer to extract the temporal behavior patterns of network delay states. Finally, features from delays, weather, and flight schedules are fed into a fully connected neural network to predict the flight time of a particular flight. The proposed model was evaluated using one year of historical data from an airline's real operations. Results show that our model can provide a more accurate flight time predictions than baseline methods, especially for flights with extreme delays. We also show that, with the improved flight time prediction, fuel loading can be optimized and resulting reduced fuel consumption by 0.016%–1.915% without increasing the fuel depletion risk.