Ship Surrogate Modelling and Voyage Optimisation for Short-Sea Shipping Fuel Efficiency
Doktorsavhandling, 2026
Short-sea shipping (SSS), essential for European transport logistics, is increasingly challenged by strict environmental regulations such as the EU Emissions Trading System, fuel price volatility, and the need to maintain tight schedules on short voyages. This thesis reframes SSS operations as a data-driven voyage-optimisation problem, developing an integrated framework that combines operational ship data, metocean data, machine learning (ML) models, and advanced optimisation algorithms to minimise voyage fuel consumption and emissions while meeting estimated time of arrival targets.
The framework was developed through the two interconnected fields of modelling and optimisation. (1) Modelling established surrogate models for ship performance: multiple ML regression algorithms were benchmarked for fuel consumption prediction, with XGBoost identified as the most stable and reliable. Independently, Gaussian process regression was employed to estimate added resistance in head waves for model-scale ships. When integrated into a grey-box neural network fuel model, it reduced prediction errors by a factor of 3 relative to semi-empirical methods. (2) Optimisation involved introducing a methodology to optimise the total fuel consumption of a voyage, validated across two case-study ships.
For a double-ended ferry, a complete decision-support system using Bayesian optimisation (BO) was implemented to determine the optimal power profile across an entire voyage. This achieved simulated fuel savings of up to 43%, with an 18% reduction confirmed during full-scale sea trials. For longer SSS voyages, the framework was extended to a chemical tanker case study. A metocean-aware segmentation algorithm, MS-PELT, was developed to divide routes into operationally meaningful legs, outperforming state-of-the-art methods whilst enabling near-real-time application. Voyage optimisation was subsequently performed using parallel coupled dynamic programming (PCDP), achieving up to 14.8% fuel savings. A final refinement step combining PCDP and BO achieved a potential fuel saving of 9.3% relative to measured voyage fuel consumption.
The framework was developed through the two interconnected fields of modelling and optimisation. (1) Modelling established surrogate models for ship performance: multiple ML regression algorithms were benchmarked for fuel consumption prediction, with XGBoost identified as the most stable and reliable. Independently, Gaussian process regression was employed to estimate added resistance in head waves for model-scale ships. When integrated into a grey-box neural network fuel model, it reduced prediction errors by a factor of 3 relative to semi-empirical methods. (2) Optimisation involved introducing a methodology to optimise the total fuel consumption of a voyage, validated across two case-study ships.
For a double-ended ferry, a complete decision-support system using Bayesian optimisation (BO) was implemented to determine the optimal power profile across an entire voyage. This achieved simulated fuel savings of up to 43%, with an 18% reduction confirmed during full-scale sea trials. For longer SSS voyages, the framework was extended to a chemical tanker case study. A metocean-aware segmentation algorithm, MS-PELT, was developed to divide routes into operationally meaningful legs, outperforming state-of-the-art methods whilst enabling near-real-time application. Voyage optimisation was subsequently performed using parallel coupled dynamic programming (PCDP), achieving up to 14.8% fuel savings. A final refinement step combining PCDP and BO achieved a potential fuel saving of 9.3% relative to measured voyage fuel consumption.
decision support system
voyage simulation
Bayesian optimisation
short sea shipping
voyage optimisation
modelling
machine learning
Lecture Hall VDL, Campus Johanneberg, Chalmers Tvärgata 4C
Opponent: Qiang Meng, Professor, Director of the Centre for Transport Research, Department of Civil and Environmental Engineering, National University of Singapore, Singapore.
Författare
Daniel Vergara
Chalmers, Mekanik och maritima vetenskaper, Marin teknik
Shipping is vital for global trade but heavily relies on fossil fuels, making the reduction of emissions a deeply concerning environmental challenge. This thesis introduces a smart, data-driven approach to navigation. It combines machine learning with advanced mathematics to determine the most fuel-efficient way to operate a ship’s engines from departure to destination. First, artificial intelligence surrogate models learn exactly how a specific ship behaves and consumes fuel in different weather conditions. Then, using weather forecast data, the voyage is divided into distinct segments; using optimisation algorithms, the perfect amount of engine power for each part of the journey is calculated. Instead of fighting rough seas at full power, the system advises adjusting the engine load dynamically. This involves reducing power during bad weather and increasing it when conditions improve, whilst ensuring the ship still arrives strictly on schedule. The research tested these methods on a double-ended passenger ferry and a commercial chemical tanker. Real-world experiments and computational simulations demonstrated substantial benefits, revealing potential fuel savings of up to 18% for the ferry and 16% for the tanker on longer voyages. The findings from this research provide a practical, highly efficient software solution for shipping sustainability. It offers the maritime industry a vital tool to lower greenhouse gas emissions and decarbonise short-sea shipping, all without requiring expensive physical modifications to existing vessels.
Styrkeområden
Transport
Energi
Ämneskategorier (SSIF 2025)
Transportteknik och logistik
Marinteknik
DOI
10.63959/chalmers.dt/5856
ISBN
978-91-8103-399-1
Doktorsavhandlingar vid Chalmers tekniska högskola. Ny serie: 5856
Utgivare
Chalmers
Lecture Hall VDL, Campus Johanneberg, Chalmers Tvärgata 4C
Opponent: Qiang Meng, Professor, Director of the Centre for Transport Research, Department of Civil and Environmental Engineering, National University of Singapore, Singapore.