X-VORTEX: Spatio-Temporal Contrastive Learning for Wake Vortex Trajectory Forecasting

TL;DR

X-VORTEX introduces a contrastive learning framework that leverages unlabeled LiDAR data to improve wake vortex trajectory forecasting, addressing challenges of data sparsity and dynamic vortex behavior.

Contribution

It presents a novel spatio-temporal contrastive learning approach that learns physics-aware representations from unlabeled data for vortex tracking and forecasting.

Findings

Achieves superior vortex localization with only 1% labeled data

Supports accurate trajectory forecasting from learned representations

Outperforms existing supervised methods on real-world data

Abstract

Wake vortices are strong, coherent air turbulences created by aircraft, and they pose a major safety and capacity challenge for air traffic management. Tracking how vortices move, weaken, and dissipate over time from LiDAR measurements is still difficult because scans are sparse, vortex signatures fade as the flow breaks down under atmospheric turbulence and instabilities, and point-wise annotation is prohibitively expensive. Existing approaches largely treat each scan as an independent, fully supervised segmentation problem, which overlooks temporal structure and does not scale to the vast unlabeled archives collected in practice. We present X-VORTEX, a spatio-temporal contrastive learning framework grounded in Augmentation Overlap Theory that learns physics-aware representations from unlabeled LiDAR point cloud sequences. X-VORTEX addresses two core challenges: sensor sparsity and time-varying vortex dynamics. It constructs paired inputs from the same underlying flight event by combining a weakly perturbed sequence with a strongly augmented counterpart produced via temporal subsampling and spatial masking, encouraging the model to align representations across missing frames and partial observations. Architecturally, a time-distributed geometric encoder extracts per-scan features and a sequential aggregator models the evolving vortex state across variable-length sequences. We evaluate on a real-world dataset of over one million LiDAR scans. X-VORTEX achieves superior vortex center localization while using only 1% of the labeled data required by supervised baselines, and the learned representations support accurate trajectory forecasting.