AIS-CycleGen: A CycleGAN-Based Framework for High-Fidelity Synthetic AIS Data Generation and Augmentation

TL;DR

AISCycleGen employs CycleGAN to generate high-fidelity synthetic AIS data, effectively addressing data scarcity and domain shifts, thereby improving maritime predictive models with realistic augmented data.

Contribution

This paper introduces AISCycleGen, a novel CycleGAN-based framework for unpaired, high-quality AIS data augmentation tailored for maritime applications.

Findings

Outperforms existing GAN-based augmentation methods

Achieves PSNR of 30.5 and FID of 38.9

Enhances predictive model performance in maritime domains

Abstract

Automatic Identification System (AIS) data are vital for maritime domain awareness, yet they often suffer from domain shifts, data sparsity, and class imbalance, which hinder the performance of predictive models. In this paper, we propose a robust data augmentation method, AISCycleGen, based on Cycle-Consistent Generative Adversarial Networks (CycleGAN), which is tailored for AIS datasets. Unlike traditional methods, AISCycleGen leverages unpaired domain translation to generate high-fidelity synthetic AIS data sequences without requiring paired source-target data. The framework employs a 1D convolutional generator with adaptive noise injection to preserve the spatiotemporal structure of AIS trajectories, enhancing the diversity and realism of the generated data. To demonstrate its efficacy, we apply AISCycleGen to several baseline regression models, showing improvements in performance across various maritime domains. The results indicate that AISCycleGen outperforms contemporary GAN-based augmentation techniques, achieving a PSNR value of 30.5 and an FID score of 38.9. These findings underscore AISCycleGen's potential as an effective and generalizable solution for augmenting AIS datasets, improving downstream model performance in real-world maritime intelligence applications.