Research paper accepted by Decision Support Systems
Safety, as the most important concern in civil aviation, needs to be maintained at an acceptable level at all times in the air transportation system. This paper aims to increase en-route flight safety through the development of deep learning models for trajectory prediction, where model prediction uncertainty is characterized following a Bayesian approach. The proposed methodology consists of four steps. In the first step, a large volume of raw messages in Flight Information Exchange Model (FIXM) format streamed from Federal Aviation Administration are processed with a distributed computing engine Apache Spark to extract trajectory information in an efficient manner. In the second step, two types of deep learning models are trained to predict flight trajectory from different perspectives. Specifically, deep feedforward neural networks (DNN) are trained to make a one-step-ahead prediction on the deviation along latitude and longitude between the actual flight trajectory and target flight trajectory. In parallel, deep Long Short-Term Memory (LSTM) neural networks are trained to make longer-term predictions on the flight trajectory over several subsequent time instants. The DNN model is more accurate but has a single-step prediction horizon, whereas the LSTM model is less accurate but longer prediction horizon. Therefore, in the third step, the two different types of deep learning models are blended together to create a multi-fidelity prediction. After quantifying the discrepancy between the two model predictions in the current time instant, the DNN prediction is used to correct the LSTM prediction of flight trajectory along subsequent time instants accordingly. The multi-fidelity approach is expanded to multiple flights, and is then used to assess safety based on horizontal and vertical separation distance between two flights. Computational results illustrate the promising performance of the blended model in predicting the flight trajectory and assessing en-route flight safety.
Research paper published in Decision Support Systems
We facilitate the “proactive safety” paradigm to increase system safety with a focus on predicting the severity of abnormal aviation events in terms of their risk levels. To accomplish this goal, a predictive model needs to be developed to examine a wide variety of possible cases and quantify the risk associated with the possible outcome. By utilizing the incident reports available in the Aviation Safety Reporting System (ASRS), we build a hybrid model consisting of support vector machine and an ensemble of deep neural networks to quantify the risk associated with the consequence of each hazardous cause. The proposed methodology is developed in four steps. First, we categorize all the events, based on the level of risk associated with the event consequence, into five groups: high risk, moderately high risk, medium risk, moderately medium risk, and low risk. Secondly, a support vector machine model is used to discover the relationships between the event synopsis in text format and event consequence. In parallel, an ensemble of deep neural networks is trained to model the intricate associations between event contextual features and event outcomes. Thirdly, an innovative fusion rule is developed to blend the prediction results from the two types of trained machine learning models, thereby improving the prediction. Finally, the prediction on risk level categorization is extended to event-level outcomes through a probabilistic decision tree. By comparing the performance of the developed hybrid model against another three individual models with ten-fold cross-validation and statistical tests, we demonstrate the effectiveness of hybrid model in quantifying the risk related to the consequences of hazardous events.
Research paper published in Risk Analysis
We develop a bi-level mathematical optimization model to maximize the transportation system resilience and restore its performance through two network reconfiguration schemes: contraflow (also referred to as lane reversal), and crossing elimination at intersections. Mathematical models are developed to represent the two reconfiguration schemes and characterize the interactions between traffic operators and passengers. Specifically, traffic operators act as leaders to determine the optimal system reconfiguration to minimize the total travel time for all the users (both evacuees and regular commuters), while passengers act as followers by freely choosing the path with the minimum travel time, which eventually converges to a user equilibrium state. For each given network reconfiguration, the lower level problem is formulated as a traffic assignment problem (TAP) where each user tries to minimize his/her own travel time. To tackle the lower-level optimization problem, a gradient projection method is leveraged to shift the flow from other non-shortest paths to the shortest path between each origin-destination pair, eventually converging to the user equilibrium traffic assignment. The upper-level problem is formulated as a constrained discrete optimization problem, and a probabilistic solution discovery algorithm is used to obtain the near-optimal solution. Two numerical examples are used to demonstrate the effectiveness of the proposed method in restoring the traffic system performance.
