Atlantes: A system of GPS transformers for global-scale real-time maritime intelligence

2025-04-26

AI Summary

Unsustainable exploitation of global marine resources and climate change critically threaten coastal communities, necessitating high-temporal-resolution, high-accuracy maritime activity monitoring. To address this, we propose the first real-time vessel behavioral awareness system designed specifically for global GPS trajectory streams. Our method introduces a novel spatiotemporal Transformer architecture optimized for millisecond-scale streaming sequence modeling and lightweight behavioral representation learning, integrated within a distributed real-time inference engine. The system achieves low-latency (<500 ms) and high-accuracy (>92% classification accuracy) online behavioral modeling across global maritime domains, generating policy-actionable insights for anomalous activities. Deployed across hundreds of maritime regulatory and environmental protection agencies, it enables real-time detection and intervention for high-risk activities—including illegal, unreported, and unregulated (IUU) fishing and smuggling—thereby significantly enhancing responsiveness and effectiveness in ocean governance.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Unsustainable exploitation of the oceans exacerbated by global warming is threatening coastal communities worldwide. Accurate and timely monitoring of maritime activity is an essential step to effective governance and to inform future policy. In support of this complex global-scale effort, we built Atlantes, a deep learning based system that provides the first-ever real-time view of vessel behavior at global scale. Atlantes leverages a series of bespoke transformers to distill a high volume, continuous stream of GPS messages emitted by hundreds of thousands of vessels into easily quantifiable behaviors. The combination of low latency and high performance enables operationally relevant decision-making and successful interventions on the high seas where illegal and exploitative activity is too common. Atlantes is already in use by hundreds of organizations worldwide. Here we provide an overview of the model and infrastructure that enables this system to function efficiently and cost-effectively at global-scale and in real-time.

Problem

• Monitor global maritime activity in real-time
• Detect illegal and exploitative vessel behavior
• Provide actionable intelligence for ocean governance

Innovation

• Deep learning system for real-time maritime monitoring
• Transformers process high-volume GPS data streams
• Low-latency, high-performance global vessel behavior analysis