This paper investigates the potential of a Digital Twin (DT) for freight routing across inland waterway networks under uncertain water-level conditions. Existing approaches insufficiently account for increasing climate-induced volatility in water levels, which often result in higher operational costs and emissions due to the need for more expensive transport alternatives, such as road transport. These existing methods often rely on reactive countermeasures to remain resilient. To address these limitations, six interviews with experts in domains related to inland shipping were conducted to identify three common contingency scenarios and appropriate operational responses. These scenarios were subsequently incorporated into a time-sliced simulation environment in which predictive decision-making, enabled by a DT environment, was compared against reactive approaches. The results demonstrate that predictive modeling substantially reduces operational costs and modal shifts at prediction accuracies between 70% and 100%, despite extreme conditions. In addition, the predictive model achieves an average 28.3% reduction in fuel-related costs by reducing the total distance ships travel. The simulation outcomes were evaluated together with domain experts to assess the practical relevance and applicability of the proposed DT-enabled approach.

翻译：本文研究了在不确定水位条件下，数字孪生（DT）在内河航道网络货运路径规划中的潜力。现有方法未能充分应对日益加剧的气候引起的水位波动，这往往导致运营成本和排放增加，因为需要采用更昂贵的运输替代方案，如公路运输。这些现有方法通常依赖被动应对措施来保持韧性。为解决这些局限，本研究对六位内河航运领域专家进行了访谈，以识别三种常见应急情景及相应的运营应对策略。随后，将这些情景整合到时域切片仿真环境中，在该环境中，由数字孪生赋能预测性决策与被动式方法进行了对比。结果表明，在预测准确率达到70%至100%的情况下，即便在极端条件下，预测性建模也能显著降低运营成本和运输方式转换。此外，通过减少船舶总航行距离，该预测模型平均降低了28.3%的燃料相关成本。仿真结果与领域专家共同评估，以验证所提出的数字孪生方法的实际相关性和适用性。