From Continuous Deployment to Queryable Dataset: Terabyte-Scale AIS-Aligned Passive Acoustic Labelling

2026-07-15

AI Summary

This study addresses the challenge of analyzing long-term passive acoustic recordings, which often lack critical metadata such as source distance due to limited integration with vessel trajectories. To overcome this limitation, the authors propose a database-native workflow that aligns fixed-duration acoustic recording windows with Automatic Identification System (AIS) position reports through spatiotemporal indexing. By replacing memory-intensive nested loops with scalable set-based operations, the method efficiently processes approximately 950,000 recording windows against 6.9 million AIS messages. The resulting structured, spatially indexed dataset resolves acoustic signals by distance and encompasses non-contact, single-contact, and dual-contact scenarios. This enables the characterization of distance-dependent attenuation of weak signals in noise-dominated environments and establishes a scalable data foundation for GeoAI and machine learning applications.

Abstract

Long-duration passive acoustic deployments produce large archives of recordings that are not linked to vessel tracks or encounter structure, leaving range and contact conditions unavailable as variables and requiring manual selection for analysis. To address this limitation, we propose a database-native workflow that aligns hydrophone recordings with Automatic Identification System (AIS) position reports to produce distance-resolved data. Fixed-duration recording windows and AIS messages are stored as persistent geospatial tables and associated through an indexed spatiotemporal join, replacing in-memory nested iteration with a single scalable set-based database process capable of handling continuous, multi-year, million-window archival deployments without exhausting available memory. In this study, the approach processes approximately 9.5x10e5 recording windows and 6.9x10e6 AIS position reports, producing a structured table that separates no-contact, single-contact, and two-contact windows, with the closest point of approach computed directly where applicable and background conditions characterized via deterministic spectral ranking. This formulation enables a GeoAI framework in which spatially indexed, queryable data become directly usable for machine learning. The resulting data product reveals predominantly noise-dominated conditions, with vessel contributions emerging mainly at shorter ranges, indicating that the task lies in extracting structure under background-limited regimes. Spectrogram and quantitative analyses show weak tonal signatures embedded in noise and a consistent decay of signal-to-noise ratio with distance, supporting the use of this representation for scalable machine learning, similarity analysis, and predictive acoustic modelling in real maritime environments.

Problem

• passive acoustic monitoring
• AIS alignment
• vessel contact
• background-limited regime
• scalable data processing

Innovation

• database-native workflow
• spatiotemporal join
• passive acoustic monitoring
• AIS alignment
• GeoAI