Aircraft Trajectory Dataset Augmentation in Latent Space

2025-06-09

AI Summary

To address the scarcity and severe class imbalance of aircraft trajectory data in air traffic management, this paper proposes ATRADA—a novel trajectory data augmentation framework. First, a Transformer encoder learns latent representations of trajectories. Second, in the dimensionality-reduced latent space, Principal Component Analysis (PCA) and Gaussian Mixture Models (GMM) are jointly applied to model the underlying trajectory distribution. Finally, a differentiable MLP decoder synthesizes semantically consistent and geometrically plausible trajectories. ATRADA is the first method to integrate latent-space modeling, PCA-GMM-based joint distribution fitting, and differentiable decoding for aviation trajectory augmentation. Experiments on conflict detection and landing time prediction demonstrate that ATRADA significantly outperforms baseline methods—including SMOTE, GANs, and VAEs—yielding substantial improvements in downstream model robustness and generalization performance.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Aircraft trajectory modeling plays a crucial role in Air Traffic Management (ATM) and is important for various downstream tasks, including conflict detection and landing time prediction. Dataset augmentation through the addition of synthetically generated trajectory data is necessary to develop a more robust aircraft trajectory model and ensure that the trajectory dataset is sufficient and balanced. In this work, we propose a novel framework called ATRADA for aircraft trajectory dataset augmentation. In the proposed framework, a Transformer encoder learns the underlying patterns in the original trajectory dataset and converts each data point into a context vector in the learned latent space. The converted dataset in the latent space is projected into reduced dimensions using principal component analysis (PCA), and a Gaussian mixture model (GMM) is applied to fit the probability distribution of the data points in the reduced-dimensional space. Finally, new samples are drawn from the fitted GMM, the dimension of the samples is reverted to the original dimension, and they are decoded with a Multi-Layer Perceptron (MLP). Several experiments demonstrate that the framework effectively generates new, high-quality synthetic aircraft trajectory data, which were compared to the results of several baselines.

Problem

• Enhancing aircraft trajectory dataset robustness via synthetic data
• Learning latent space patterns for trajectory augmentation
• Generating high-quality synthetic trajectories using GMM and MLP

Innovation

• Transformer encoder learns trajectory patterns
• PCA and GMM model latent space distribution
• MLP decodes synthetic high-quality trajectory data