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

Lan Wu, Xuebin Wang, Ruijuan Chu, Guangyi Liu, Jing Zhang, Linyu Wang
Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, PMLR 286:4618-4635, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v286-wu25c, title = {FlightPatchNet: Multi-Scale Patch Network with Differential Coding for Short-Term Flight Trajectory Prediction}, author = {Wu, Lan and Wang, Xuebin and Chu, Ruijuan and Liu, Guangyi and Zhang, Jing and Wang, Linyu}, booktitle = {Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence}, pages = {4618--4635}, year = {2025}, editor = {Chiappa, Silvia and Magliacane, Sara}, volume = {286}, series = {Proceedings of Machine Learning Research}, month = {21--25 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v286/main/assets/wu25c/wu25c.pdf}, url = {https://proceedings.mlr.press/v286/wu25c.html}, 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.} }
Endnote
%0 Conference Paper %T FlightPatchNet: Multi-Scale Patch Network with Differential Coding for Short-Term Flight Trajectory Prediction %A Lan Wu %A Xuebin Wang %A Ruijuan Chu %A Guangyi Liu %A Jing Zhang %A Linyu Wang %B Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2025 %E Silvia Chiappa %E Sara Magliacane %F pmlr-v286-wu25c %I PMLR %P 4618--4635 %U https://proceedings.mlr.press/v286/wu25c.html %V 286 %X 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.
APA
Wu, L., Wang, X., Chu, R., Liu, G., Zhang, J. & Wang, L.. (2025). FlightPatchNet: Multi-Scale Patch Network with Differential Coding for Short-Term Flight Trajectory Prediction. Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 286:4618-4635 Available from https://proceedings.mlr.press/v286/wu25c.html.

Related Material