Routeview: an intelligent route planning system for ships sailing through Arctic ice zones based on big Earth data

• Published in: International journal of digital earth Vol. 15; no. 1; pp. 1588 - 1613
• Main Authors: Wu, Adan, Che, Tao, Li, Xin, Zhu, Xiaowen
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 31.12.2022; Taylor & Francis Ltd; Taylor & Francis Group
• Subjects: Arctic northeast passage; Deep learning; ice-water classification; information extraction system; Information retrieval; Information services; Interactive systems; Machine learning; Marine environment; Meteorological data; Navigation; Polar environments; Real time; reinforcement learning; Route planning; Sailing; SAR (radar); Sea ice; Shipping; Ships; Synthetic aperture radar; U-Net; Arctic region
• ISSN: 1753-8947; 1753-8955
• DOI: 10.1080/17538947.2022.2126016

The potential of Arctic routes (ARs) has attracted global attention, and exploiting the Arctic has become an important strategy for many countries. However, there are still some challenges for ships sailing in Arctic ice zones, including harsh marine environments and the insufficient service capacity of sea ice information service systems. To better understand the route changes in the Arctic and extract real-time ship navigation routes, we developed an online interactive route planning system (RouteView) for ships sailing in the Arctic based on big Earth data. RouteView includes two main features: (1) an online calculation interface is provided for optimal routes along the Arctic Northeast Passage (NEP) 60 days into the future by utilizing reinforcement learning (RL) based on sea ice and meteorological data, and (2) an online ice-water classification is established based on synthetic aperture radar (SAR) data and deep learning to help users extract the sea ice distribution in real time. This work can potentially enhance the safety of shipping navigation along the NEP and improve information extraction methods for ARs.