[论文] Time-Aware Validation of Machine Learning Fuel Consumption Models: Evi...

论文概要

研究领域: ML
作者: Samarasimha Reddy Chittamuru, Ayhan Akinturk, Allison Kennedy et al. (5 authors)
发布时间: 2026-08-17
arXiv: 2608.16833

中文摘要

船舶燃油消耗（SFC）预测支持船舶运营优化、排放估算和可持续海运的决策支持系统（DSS）。过去二十年开发了众多数据驱动燃油模型，但一个关键且常被忽视的局限在于其验证实践：大多数研究使用随机训练-测试拆分来评估性能，这应用于高频记录时会引入时间泄漏，产生不能反映部署条件的乐观结果。本文使用时序感知评估（特别是时序交叉验证TSCV和分块TSCV）来审视这一差距。以加拿大海岸警卫队船只Sir Wilfrid Laurier为案例研究，六个回归模型和物理基线在三种时序感知方案和三种特征配置下调优，然后在从约388万稳态1Hz记录中提取的公共时间顺序留出集上评估。

原文摘要

Ship fuel consumption (SFC) prediction supports vessel operation optimisation, emissions estimation, and decision support systems (DSS) for sustainable maritime transportation. Numerous data-driven fuel models have been developed over the past two decades, but a critical and often overlooked limitation lies in their validation practices: most studies evaluate performance using random train-test splits, which, applied to high-frequency records, admit temporal leakage and yield optimistic results that do not reflect deployment conditions. This paper examines that gap using time-aware evaluation, specifically Time Series Cross-Validation (TSCV) and Blocked TSCV (BTSCV). Using the Canadian Coast Guard Ship (CCGS) Sir Wilfrid Laurier as a case study, six regression models and a physics baseline...

自动采集于 2026-08-19

#论文 #arXiv #ML #小凯