Machine learning for ship fuel consumption prediction from sensory data: a comparative analysis

Habib Zahmani, N, Yuksel, O ORCID: 0000-0002-5728-5866, Blanco-Davis, E ORCID: 0000-0001-8080-4997 and Tsoulakos, N (2026) Machine learning for ship fuel consumption prediction from sensory data: a comparative analysis. Journal of Marine Engineering and Technology. ISSN 2046-4177

Preview

Text Machine learning for ship fuel consumption prediction from sensory data a comparative analysis.pdf - Published Version Available under License Creative Commons Attribution. Download (5MB) | Preview

Abstract

Machine learning models are increasingly used to predict ship fuel consumption from high-frequency operational data. However, the strong temporal autocorrelation of shipboard sensor measurements raises concerns regarding the validity of commonly adopted evaluation practices. Many existing studies rely on random data partitioning and cross-validation schemes that can introduce information leakage, resulting in overly optimistic performance estimates. This study examined the impact of the validation strategy on fuel consumption prediction using one-minute operational data collected from a bulk carrier over approximately 16 months. Gradient-boosted decision tree models (XGBoost and CatBoost) and deep learning architectures were evaluated using three validation schemes: random train–test splitting, blocked chronological hold-out, and rolling-window temporal evaluation. The results demonstrate that random splitting substantially inflates the predictive performance, with coefficients of determination exceeding 0.99, whereas temporally consistent validation reveals significantly reduced accuracy and performance degradation across unseen operating periods. Under realistic temporal testing, gradient-boosted models exhibit greater robustness than deep learning models, which exhibit higher sensitivity to distributional shifts. These findings highlight the critical importance of temporally aware validation for obtaining credible generalisation estimates in ship fuel consumption modelling.

Item Type:	Article
Uncontrolled Keywords:	Ship fuel consumption prediction; machine learning; temporal validation; time-series data; gradient boosting; shipboard sensor data; 46 Information and Computing Sciences; 40 Engineering; 4611 Machine Learning; Machine Learning and Artificial Intelligence; Networking and Information Technology R&D (NITRD); 4007 Control engineering, mechatronics and robotics; 4015 Maritime engineering; 4602 Artificial intelligence
Subjects:	Q Science > QA Mathematics > QA76 Computer software T Technology > TA Engineering (General). Civil engineering (General)
Divisions:	Civil Engineering and Built Environment
Publisher:	Taylor and Francis
Date of acceptance:	8 May 2026
Date of first compliant Open Access:	5 August 2026
Date Deposited:	05 Aug 2026 14:05
Last Modified:	05 Aug 2026 14:05
DOI or ID number:	10.1080/20464177.2026.2673233
URI:	https://researchonline.ljmu.ac.uk/id/eprint/29112

View Item