Merchant vessels often require icebreaker (IB) assistance to create safe pathways and improve efficiency when navigating in the Baltic Sea. Since IB resources are limited, an accurate estimation on the need for IB assistance is important. Whether IB assistance is needed depends on multiple factors. While practical experience from captains is naturally a source of valuable information for the decision on the need for IB assistance, systematic analysis of the reasoning is limited. The primary aim of this paper is to holistically investigate the influencing factors and their effect on estimating the need for IB assistance through data-driven techniques. Based on a comprehensive list of potential factors, different of data such as traffic history, environmental conditions, and ship specifications are gathered to present complex navigational scenarios. Each scenario is labeled by different navigation modes (independent navigation or IB assistance), laying the foundation for influencing factor identification and effect quantification. Logistic regression is applied to evaluate the effect of the factors on the need for IB assistance. The results show that the impact of the factors is diverse, and ridged ice concentration has the most significant impact. The effectiveness of identified factors is measured by comparing it to that of the factors that have been implemented by the existing studies (e.g., the combination of ice concentration, thickness, and ship ice class, or only ship speed). By considering the factors in this study, the classification performance can be improved by at least 5.6%. The findings in this paper can provide insights for predicting IB workloads and optimizing IB resources and have the potential to support the development of an intelligent decision-support system for winter navigation.

中文翻译：

---

关于影响冰覆盖水域破冰船援助需求因素的数据驱动调查

商船在波罗的海航行时通常需要破冰船 (IB) 协助来开辟安全通道并提高效率。由于 IB 资源有限，因此准确估计 IB 援助需求非常重要。是否需要 IB 援助取决于多种因素。虽然船长的实践经验自然是决定是否需要 IB 援助的宝贵信息来源，但对推理的系统分析是有限的。本文的主要目的是通过数据驱动技术全面研究影响因素及其对估计 IB 援助需求的影响。基于潜在因素的全面列表，收集交通历史、环境条件和船舶规格等不同数据以呈现复杂的导航场景。每个场景都标有不同的导航模式（独立导航或IB辅助），为影响因素识别和效果量化奠定基础。应用逻辑回归来评估因素对 IB 援助需求的影响。结果表明，影响因素多样，其中脊冰浓度影响最为显着。已确定因素的有效性是通过将其与现有研究已实施的因素进行比较来衡量的（例如，冰浓度、厚度和船舶冰级的组合，或仅船速）。通过考虑本研究中的因素，分类性能至少可以提高5.6%。本文的研究结果可以为预测 IB 工作负载和优化 IB 资源提供见解，并有可能支持冬季导航智能决策支持系统的开发。