FlightPatchNet: Multi-Scale Patch Network with Differential Coding for Flight Trajectory Prediction

TL;DR

FlightPatchNet introduces a multi-scale patch network with differential coding and attention mechanisms to improve multi-step flight trajectory prediction, effectively capturing complex temporal dependencies and diverse patterns.

Contribution

The paper presents a novel multi-scale patch network with differential coding and ensemble predictors, enhancing flight trajectory prediction accuracy over existing methods.

Findings

Outperforms baseline models on ADS-B datasets

Effectively captures multi-scale temporal dependencies

Improves prediction accuracy in air traffic control scenarios

Abstract

Accurate multi-step flight trajectory prediction plays an important role in Air Traffic Control, which can ensure the safety of air transportation. Two main issues limit the flight trajectory prediction performance of existing works. The first issue is the negative impact on prediction accuracy caused by the significant differences in data range. The second issue is that real-world flight trajectories involve underlying temporal dependencies, and most existing methods fail to reveal the hidden complex temporal variations and extract features from one single time scale. To address the above issues, we propose FlightPatchNet, a multi-scale patch network with differential coding for flight trajectory prediction. Specifically, FlightPatchNet first utilizes differential coding to encode the original values of longitude and latitude into first-order differences and generates embeddings for all variables at each time step. Then, global temporal attention is introduced to explore the dependencies between different time steps. To fully explore the diverse temporal patterns in flight trajectories, a multi-scale patch network is delicately designed to serve as the backbone. The multi-scale patch network exploits stacked patch mixer blocks to capture inter- and intra-patch dependencies under different time scales, and further integrates multi-scale temporal features across different scales and variables. Finally, FlightPatchNet ensembles multiple predictors to make direct multi-step prediction. Extensive experiments on ADS-B datasets demonstrate that our model outperforms the competitive baselines.