A Meta-Learning Approach for Aircraft Trajectory Prediction

The aviation industry has seen significant advancements in safety procedures over the past few decades, resulting in a steady decline in aviation deaths worldwide. However, the safety standards in General Aviation (GA) are still lower compared to those in commercial aviation. With the anticipated growth in air travel, there is an imminent need to improve operational safety in GA. One way to improve aircraft and operational safety is through trajectory prediction. Trajectory prediction plays a key role in optimizing air traffic control and improving overall flight safety. This paper proposes a meta-learning approach to predict short- to mid-term trajectories of aircraft using historical real flight data collected from multiple GA aircraft. The proposed solution brings together multiple models to improve prediction accuracy. In this paper, we are combining two models, Random Forest Regression (RFR) and Long Short-term Memory (LSTM), using k-Nearest Neighbors (k-NN), to output the final prediction based on the combined output of the individual models. This approach gives our model an edge over single-model predictions. We present the results of our meta-learner and evaluate its performance against individual models using the Mean Absolute Error (MAE), Absolute Altitude Error (AAE), and Root Mean Squared Error (RMSE) evaluation metrics. The proposed methodology for aircraft trajectory forecasting is discussed in detail, accompanied by a literature review and an overview of the data preprocessing techniques used. The results demonstrate that the proposed meta-learner outperforms individual models in terms of accuracy, providing a more robust and proactive approach to improve operational safety in GA.

Investigating the influence of segmentation in estimating safety performance functions for roadway sections

Safety performance functions（SPFs） are crucial to science-based road safety management.Success in developing and applying SPFs, apart data quality and availability, depends fundamentally on two key factors： the validity of the statistical inferences for the available data and on how well the data can be organized into distinct homogeneous entities. The latter aspect plays a key role in the identification and treatment of road sections or corridors with problems related to safety. Indeed, the segmentation of a road network could be especially critical in the development of SPFs that could be used in safety management for roadway types, such as motorways（freeways in North America）, which have a large number of variables that could result in very short segments if these are desired to be homogeneous. This consequence, from an analytical point of view, can be a problem when the location of crashes is not precise and when there is an overabundance of segments with zero crashes. Lengthening the segments for developing and applying SPFs can mitigate this problem, but at a sacrifice of homogeneity. This paper seeks to address this dilemma by investigating four approaches for segmentation for motorways, using sample data from Italy. The best results were obtained for the segmentation based on two curves and two tangents within a segment and with fixed length segments. The segmentation characterized by a constant value of all original variables inside each segment was the poorest approach by all measures.