Geometry-Informed Adaptive Time-Series Fusion of ADS-B Sensor Data for Short-Term Aircraft Trajectory Prediction.

Accurate short-term aircraft trajectory prediction is critical for modern air traffic management and collision avoidance systems. This research direction explores the integration of Automatic Dependent Surveillance-Broadcast (ADS-B) sensor data using a geometry-informed adaptive time-series fusion methodology. Traditional trajectory prediction models often struggle with sensor noise, latency, and geometric dilution of precision inherent in multi-station ADS-B reception. To address these limitations, this framework provides guidance on structuring an adaptive fusion algorithm that dynamically weights incoming time-series data based on the spatial geometry of the receiving network and the aircraft's instantaneous flight state. By incorporating geometric constraints directly into the state estimation process, the proposed simulation model aims to minimize tracking errors

during highly dynamic maneuvers. The project development support focuses on establishing a robust mathematical formulation for the adaptive fusion filter, followed by validation against simulated or historical flight trajectories. Through systematic evaluation of prediction horizons and error metrics, this research assists in refining sensor fusion architectures for next-generation guidance, navigation, and control systems, offering a structured approach to analyzing trajectory prediction accuracy under varying environmental and geometric configurations.

Message: Hi FE, I need help with “Geometry-Informed Adaptive Time-Series Fusion of ADS-B Sensor Data for Short-Term Aircraft Trajectory Prediction.” in “Aerospace Engineering”