Leveraging Copernicus for Ice Block Detection: A Step Towards Safer Arctic Navigation

Abstract

Background The Arctic is becoming more accessible due to ice melting, posing challenges for navigation due to floating ice blocks. Detecting these ice blocks is crucial for ensuring the safety of vessels navigating these waters. Methods This study introduces a novel method for detecting ice blocks in the Arctic using Artificial Intelligence (AI) and Synthetic Aperture Radar (SAR) satellite images from the Sentinel-1 mission of the Copernicus program. Our approach combines state-of-the-art image segmentation and deep learning techniques. We utilize a Convolutional Neural Network (CNN) classifier to accurately locate ice blocks within the images and retrieve their geographic coordinates. The method's performance is validated using precision, recall, and F1-score metrics. Results Our CNN classifier demonstrates robust performance in detecting ice blocks, validated through precision, recall, and F1-score metrics. The practical application of our technology was showcased in the AI-ARC project’s Arctic demo, receiving positive feedback from coast guards across various European countries. The system provides near-real-time alerts about detected ice blocks, allowing for timely route adjustments and reducing collision risks. Conclusions The developed system significantly contributes to Arctic navigation safety by providing accurate and timely detection of ice blocks. This work underscores the transformative potential of AI in environmental monitoring and maritime safety. Future refinements will be based on user feedback and advancements in AI technology, enhancing the system's effectiveness and reliability.