Session: 07-01-01 Operations in ice

Submission Number: 156595

Comparative Analysis of Ice Datasets to Inform Decision Support Models for Winter Navigation 

The Baltic Sea can be covered by ice during winter, with up to 40% of its area affected, significantly impacting ship route planning and traffic management. Accurate ice information is critical for safe and efficient decision-making for winter navigation. For example, severe ice conditions may require many merchant vessels to seek icebreaker assistance to navigate safely and avoid hull damage or becoming trapped. With the emergence of extensive maritime data and advanced machine learning models, there is a growing focus on developing data-driven decision support tools for winter navigation. The effectiveness of these tools heavily depends on the ice data they utilize. Ice data sources can be broadly classified into forecast models such as HELMI and NEMO, and satellite-derived data like Ice Analysis, BALFI, and Ice Chart. While each of these datasets has its own strengths and weaknesses, a comprehensive assessment comparing these sources and evaluating their suitability for various decision support tools in winter navigation is lacking.

This paper seeks to fill that gap by comparing five ice datasets to identify the contexts in which each is most beneficial for decision-makers, using qualitative metrics (data acquisition complexity, resolution, and comprehensiveness) and quantitative metrics (ice concentration and thickness distributions). Based on the results, Ice Chart is recommended for daily operations due to its user-friendly maps, good resolution, and comprehensiveness. BALFI is advantageous when information on measurement uncertainty is critical, while Ice Analysis offers a time- and cost-effective use of satellite data. Among all the datasets, forecast models like HELMI and NEMO offer the advantage of suitability for potential 'what-if' type scenario analyses.

Presenting Author: Mashrura Musharraf Aalto University

Presenting Author Biography: I am an Assistant Professor of Marine Technology. My research interest is in applying data mining, machine learning, and AI techniques to build and deploy human-centered systems and solutions and create a Safer marine industry. With the successful demonstration of the world's first fully autonomous ferry, it is anticipated that ship intelligence will continue to reshape the maritime industry in the coming years. While decision-making by Autonomous systems is somewhat straightforward for local vessel operations, it would be fairly complex for ocean-going ships in harsh conditions. For marine operations in ice, optimized task performance is not the only issue, rather auxiliary criteria such as safety and reliability are equally important. As the Foundations for futuristic ships are being set, my research aims to acknowledge the importance of interpretability and transparency of the AI ​​algorithms that would replace or support the limited crew on board.

Full researcher profile
https://research.aalto.fi/fi/persons/mashrura-musharraf