Sameer Alam’s research while affiliated with Nanyang Normal University and other places

This study proposes an autonomous aircraft taxi agent that can be used to recommend the pilot the optimal speed profile to achieve optimal fuel burn and to arrive on time at the target position on the taxiway while considering potential interactions with surrounding traffic. The problem is modeled as a control decision problem that is solved by training the agent under a Deep Reinforcement Learning (DRL) mechanism using the Proximal Policy Optimization (PPO) algorithm. The reward function is designed to consider the fuel burn, taxi time, and delay time. Accordingly, the trained agent will learn to taxi the aircraft between any pair of locations on the airport surface in a timely manner while maintaining safety and efficiency. As a result, in more than 97.8% of the evaluated sessions, the controlled aircraft reached the target position with a time difference falling within the range of −20 to 5 s. Moreover, compared to actual fuel burn, the proposed autonomous taxi agent demonstrated a reduction of 29.5%, equivalent to reducing 13.9 kg of fuel consumption per aircraft. This benefit in fuel burn reduction can complement the emission reductions achieved by solving other sub-problems, such as pushback control and taxi-route assignments, to achieve much higher performance.

With the advancement of Communication, Navigation and Surveillance (CNS) technologies such as space-based Automatic Dependent Surveillance-Broadcast/Contract (ADS-B/C), large separation minima may be reduced in procedural airspaces. It is of great significance to know the upper limit of the Reduced Separation Minima (RSM) for a procedural airspace and the corresponding consequences on collision risk with specifics of the advanced ADS-B and control intervention model. In this work, an interactive software is first developed for collision risk estimation. This software integrates the International Civil Aviation Organization (ICAO) collision risk models for lateral and longitudinal collision risk calculation for the Singapore procedural airspace. Results demonstrate that the lateral and longitudinal collision risk of Singapore procedural airspace with respect to current control procedures meets the ICAO Target Level of Safety (TLS) standard. Moreover, the feasibility of reducing the horizontal separations implemented in the Singapore procedural airspace with respect to advanced CNS techniques is investigated. It is found that if advanced CNS technologies are applied, then the current 50-NM lateral and longitudinal separation standards can be reduced to 22 NM (1 NM=1.825 km) and 20 NM, respectively, to meet the TLS standards based on current demand. A method is then devised to expand the traffic demand by p% for p∈[10, 200]. It is found that the minimum lateral and longitudinal separations can be reduced from 50 NM to be within the range of [23, 31] NM, and 20 NM, respectively, for p∈[10, 200], while the collision risk still meets the TLS standards.

Aircraft trajectory prediction is a challenging problem in air traffic control, especially for conflict detection. Traditional trajectory predictors require a variety of inputs such as flight-plans, aircraft performance models, meteorological forecasts, etc. Many of these data are subjected to environmental uncertainties. Further, limited information about such inputs, especially the lack of aircraft tactical intent, makes trajectory prediction a challenging task. In this work, we propose a deep learning model that performs trajectory prediction by modeling and incorporating aircraft tactical intent. The proposed model adopts the encoder-decoder architecture and makes use of the convolutional layer as well as Gated Recurrent Units (GRUs). The proposed model does not require explicit information about aircraft performance and wind data. Results demonstrate that the provision of enriched aircraft intent, together with appropriate model design, could improve the prediction error up to 30% at a prediction horizon of 10 minutes (from 4.9 nautical miles to 3.4 nautical miles). The model also guarantees the mean error growth rate with increasing look-ahead time to be lower than 0.2 nautical miles per minute. In addition, the model offers a very low variance in the prediction, which satisfies the variance-standard specified by EUROCONTROL (EU Organization for Safety and Navigation of Air Traffic) for trajectory predictors. The proposed model also outperforms the state-of-the-art trajectory prediction model, where the Root Mean Square Error (RMSE) is reduced from 0.0203 to 0.0018 for latitude prediction, and from 0.0482 to 0.0021 for longitude prediction in a single prediction step of 15 seconds look-ahead. We showed that the pre-trained model on ADS-B data maintains its high performance, in terms of cross-track and along-track errors, when being validated in the Bluesky Air Traffic Simulator. The proposed model would significantly improve the performance of conflict detection systems where such trajectory prediction models are needed.

Safety is a top priority for civil aviation. Data mining in digital Flight Data Recorder (FDR) or Quick Access Recorder (QAR) data, commonly referred to as black box data on aircraft, has gained interest for proactive safety management. New anomaly detection methods, primarily clustering methods, have been developed to monitor pilot operations and detect any risks from such flight data. However, all existing anomaly detection methods are offline learning — the models are trained once using historical data and used for all future predictions. In practice, new flight data are accumulated continuously and analyzed every month at airlines. Clustering such dynamically growing data is challenging for an offline method because it is memory and time intensive to re-train the model every time new data come in. If the model is not re-trained, false alarms or missed detections may increase since the model cannot reflect changes in data patterns. To address this problem, we propose a novel incremental anomaly detection method based on Gaussian Mixture Model (GMM) to identify common patterns and detect outliers in flight operations from digital flight data. It is a probabilistic clustering model of flight operations that can incrementally update its clusters based on new data rather than to re-cluster all data from scratch. It trains an initial GMM model based on historical offline data. Then, it continuously adapts to new incoming data points via an expectation–maximization (EM) algorithm. To track changes in flight operation patterns, only model parameters need to be saved, not the raw flight data. The proposed method was tested on three sets of simulation data and two sets of real-world flight data. Compared with the traditional offline GMM method, the proposed method can generate similar clustering results with significantly reduced processing time (57 %–99 % time reduction in testing sets) and memory usage (91 %–95 % memory usage reduction in testing sets). Preliminary results indicate that the incremental learning scheme is effective in dealing with dynamically growing data in flight data analytics.

Air passenger forecasting provides important insights for both Governments and Aerospace industries to plan their for their future activities. Google Trends can provide a large database of historical search query frequency which can be used as explanatory variables for air passenger forecasting. This paper explores the use of a Neural Granger Causality model to select the best search query that can forecast arrival air passengers in Singapore Changi Airport. Neural Granger Causality models are an extension of the original Granger Causality model that uses neural networks instead of Linear Vector Auto-Regressive (VAR) models to capture non-linear relations between the targets and the tested explanatory variables. In this paper, 1317 Google Trends search queries are tested for Neural Granger Causality of which 171 queries are deemed as Neural Granger Causal for forecasting Singapore Changi Airport monthly arrival passengers. The model that used all 171 Neural Granger Queries achieved the highest R2 value (R2=0.919) with the lowest Standard Deviation (SD=0.363) compared to the other models which was not filtered for Neural Granger Causality. The 171 queries found are search terms that reflects a unidirectional neural granger causal relationship with the number of arrival air passengers at Changi Airport.

Air travelers’ behavior is closely related to the operational performance of any airport terminal. Much of previous research has focused on how airport operators balance the number of facilities in a terminal and the Level of Service (LOS), while the behavior of passengers is less considered. Not much is known, however, about passenger’s behavior during the entire departure process in an airport. In this study, we analyze empirical departure passenger’s data to gain an insight into the regular patterns of their activities in an airport. We find that there exist two distinguished temporal patterns during two discretionary periods— post check-in and pre-security check, post security check and pre-boarding. The time that departure passengers spend in these two periods is well approximated by a double power-law distribution and an exponential truncated power-law distribution respectively. The two distinguished distributions suggest that there may be different mechanisms underlying passengers’ behavior as indicated by previous studies on human mobility. We introduce a stochastic model that considers traveling experience and time pressure to capture the decision dynamics of human behavior. Simulation results suggest that traveling experience and time pressure dominate passenger’s decisions before and after security respectively. Our findings contribute to a better understanding of human dynamics, and also offer the potential for optimizing and simulation of airport terminal operation.

Safety is a top priority for civil aviation. Data mining in digital Flight Data Recorder (FDR) or Quick Access Recorder (QAR) data, commonly referred as black box data on aircraft, has gained interest from researchers, airlines, and aviation regulation agencies for safety management. New anomaly detection methods based on supervised or unsupervised learning have been developed to monitor pilot operations and detect any risks from onboard digital flight data recorder data. However, all existing anomaly detection methods are offline learning - the models are trained once using historical data and used for all future predictions. In practice, new QAR data are generated by every flight and collected by airlines whenever a datalink is available. Offline methods cannot respond to new data in time. Though these offline models can be updated by being re-trained after adding new data to the original training set, it is time-consuming and computational costly to train a new model every time new data come in. To address this problem, we propose a novel incremental anomaly detection method to identify common patterns and detect outliers in flight operations from FDR data. The proposed method is based on Gaussian Mixture Model (GMM). An initial GMM cluster model is trained on historical offline data. Then, it continuously adapts to new incoming data points via an expectation-maximization (EM) algorithm. To track changes in flight operation patterns, only model parameters need to be saved, not the raw flight data. The proposed method was tested on two sets of simulation data. Comparable results were found from the proposed online method and a classic offline model. A real-world application of the proposed method is demonstrated using FDR data from daily operations of an airline. Results are presented and future challenges of using online learning scheme for flight data analytics are discussed.