Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Data Analytics for Improving Energy Efficiency in Short Sea Shipping

Mohamed Abuella, Hadi Fanaee, M. Amine Atou, Slawomir Nowaczyk, Simon Johansson, Ethan Faghani

TL;DR

The paper addresses energy efficiency in short-sea shipping by fusing high-resolution onboard data with external environmental data to model vessel energy use and optimize voyages under arrival-time constraints. It introduces a data-driven framework that combines a spatiotemporal aggregation approach, an explainable AI component, and four time-series speed-optimization models (LSTM, kNN, 1NN-DTW, HMM), plus a path-identification framework using distance-based ANND and segmented Gaussian likelihood. The approach is validated through case studies on fixed-route vessels (Cinderella II and Buro), demonstrating that the efficiency-score model and especially the HMM-based optimization yield meaningful fuel savings and robust performance across weather states, while the path-identification framework achieves high clustering accuracy in identifying repeatable routes. The work contributes to practical maritime energy-management by enabling more informed voyage planning, route analysis, and safety-conscious routing in short-sea shipping, with clear avenues for future enhancements in spatial features, scalability, and real-time integration.

Abstract

To meet the urgent requirements for the climate change mitigation, several proactive measures of energy efficiency have been implemented in maritime industry. Many of these practices depend highly on the onboard data of vessel's operation and environmental conditions. In this paper, a high resolution onboard data from passenger vessels in short-sea shipping (SSS) have been collected and preprocessed. We first investigated the available data to deploy it effectively to model the physics of the vessel, and hence the vessel performance. Since in SSS, the weather measurements and forecasts might have not been in temporal and spatial resolutions that accurately representing the actual environmental conditions. Then, We proposed a data-driven modeling approach for vessel energy efficiency. This approach addresses the challenges of data representation and energy modeling by combining and aggregating data from multiple sources and seamlessly integrates explainable artificial intelligence (XAI) to attain clear insights about the energy efficiency for a vessel in SSS. After that, the developed model of energy efficiency has been utilized in developing a framework for optimizing the vessel voyage to minimize the fuel consumption and meeting the constraint of arrival time. Moreover, we developed a spatial clustering approach for labeling the vessel paths to detect the paths for vessels with operating routes of repeatable and semi-repeatable paths.

Data Analytics for Improving Energy Efficiency in Short Sea Shipping

TL;DR

The paper addresses energy efficiency in short-sea shipping by fusing high-resolution onboard data with external environmental data to model vessel energy use and optimize voyages under arrival-time constraints. It introduces a data-driven framework that combines a spatiotemporal aggregation approach, an explainable AI component, and four time-series speed-optimization models (LSTM, kNN, 1NN-DTW, HMM), plus a path-identification framework using distance-based ANND and segmented Gaussian likelihood. The approach is validated through case studies on fixed-route vessels (Cinderella II and Buro), demonstrating that the efficiency-score model and especially the HMM-based optimization yield meaningful fuel savings and robust performance across weather states, while the path-identification framework achieves high clustering accuracy in identifying repeatable routes. The work contributes to practical maritime energy-management by enabling more informed voyage planning, route analysis, and safety-conscious routing in short-sea shipping, with clear avenues for future enhancements in spatial features, scalability, and real-time integration.

Abstract

To meet the urgent requirements for the climate change mitigation, several proactive measures of energy efficiency have been implemented in maritime industry. Many of these practices depend highly on the onboard data of vessel's operation and environmental conditions. In this paper, a high resolution onboard data from passenger vessels in short-sea shipping (SSS) have been collected and preprocessed. We first investigated the available data to deploy it effectively to model the physics of the vessel, and hence the vessel performance. Since in SSS, the weather measurements and forecasts might have not been in temporal and spatial resolutions that accurately representing the actual environmental conditions. Then, We proposed a data-driven modeling approach for vessel energy efficiency. This approach addresses the challenges of data representation and energy modeling by combining and aggregating data from multiple sources and seamlessly integrates explainable artificial intelligence (XAI) to attain clear insights about the energy efficiency for a vessel in SSS. After that, the developed model of energy efficiency has been utilized in developing a framework for optimizing the vessel voyage to minimize the fuel consumption and meeting the constraint of arrival time. Moreover, we developed a spatial clustering approach for labeling the vessel paths to detect the paths for vessels with operating routes of repeatable and semi-repeatable paths.
Paper Structure (36 sections, 11 equations, 28 figures, 9 tables, 2 algorithms)

This paper contains 36 sections, 11 equations, 28 figures, 9 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. General Background
  3. Main Outcomes
  4. Related Work
  5. Vessel Energy Efficiency Modeling
  6. Vessel Voyage Optimization
  7. Vessel Path Identification
  8. Data Collection and Preparation
  9. Data Collection
  10. Data Preparation and Validation
  11. Methodology
  12. Energy Efficiency Modeling
  13. Framework of Voyage Optimization
  14. Long Short-Term Memory (LSTM)
  15. k-Nearest Neighbors (kNN)
  16. ...and 21 more sections

Figures (28)

  • Figure 1: European short-sea shipping of freight versus total sea transport, in 2021 Eurostat2021.
  • Figure 2: Vessel's data analytics and standard performance graph for the case study
  • Figure 3: The vessel voyages and the aggregated data projected by the Efficiency Score.
  • Figure 4: Four clusters of voyages based on their efficiency.
  • Figure 5: Workflow of modeling and analysis of energy efficiency in short-sea shipping
  • ...and 23 more figures