Data-Driven Trajectory Imputation for Vessel Mobility Analysis

TL;DR

This paper tackles the challenge of missing AIS-based vessel trajectories by introducing HABIT, a lightweight, data-driven imputation framework that leverages an H3 hex grid to learn area-specific movement patterns from historical AIS data. HABIT builds a four-stage pipeline (preprocessing, graph generation, trajectory imputation, and trajectory simplification) that maps gaps to a navigable path via A* on a data-driven maritime network and reconciles coordinates through median-based inverse projection. The approach achieves comparable or better accuracy than state-of-the-art baselines while offering sub-second latency and lower memory requirements, demonstrating strong scalability across diverse datasets and gap sizes. The work has practical implications for maritime traffic analytics, safety, and environmental monitoring, enabling higher-quality trajectory reconstructions without heavy computational demands.

Abstract

Modeling vessel activity at sea is critical for a wide range of applications, including route planning, transportation logistics, maritime safety, and environmental monitoring. Over the past two decades, the Automatic Identification System (AIS) has enabled real-time monitoring of hundreds of thousands of vessels, generating huge amounts of data daily. One major challenge in using AIS data is the presence of large gaps in vessel trajectories, often caused by coverage limitations or intentional transmission interruptions. These gaps can significantly degrade data quality, resulting in inaccurate or incomplete analysis. State-of-the-art imputation approaches have mainly been devised to tackle gaps in vehicle trajectories, even when the underlying road network is not considered. But the motion patterns of sailing vessels differ substantially, e.g., smooth turns, maneuvering near ports, or navigating in adverse weather conditions. In this application paper, we propose HABIT, a lightweight, configurable H3 Aggregation-Based Imputation framework for vessel Trajectories. This data-driven framework provides a valuable means to impute missing trajectory segments by extracting, analyzing, and indexing motion patterns from historical AIS data. Our empirical study over AIS data across various timeframes, densities, and vessel types reveals that HABIT produces maritime trajectory imputations performing comparably to baseline methods in terms of accuracy, while performing better in terms of latency while accounting for vessel characteristics and their motion patterns.

Figures (7)

• Figure 1: Imputing a gap along a vessel trajectory.
• Figure 2: Inverse projection of the imputed path cell sequence back to real-world coordinates using (a) cell centers [red]; and (b) a data-driven (median) method [purple].
• Figure 3: HABIT accuracy (DTW) at different H3 resolutions and $p$ options (H3 cell center / Data median) [DAN Dataset].
• Figure 4: HABIT accuracy (DTW) for different simplification tolerances ${t=\{0, 100, 250, 500, 1000\}}$, and resolutions $r=\{9, 10\}$ [DAN Dataset].
• Figure 5: Sensitivity analysis on accuracy (mean & median DTW) of the imputed paths with varying parameterizations for GTI ($rm$, $rd$) and HABIT ($r$, $t$) [KIEL & SAR Dataset].