Full Length Article
Data fusion and machine learning for ship fuel efficiency modeling: Part II – Voyage report data, AIS data and meteorological data

https://doi.org/10.1016/j.commtr.2022.100073Get rights and content
Under a Creative Commons license
open access

Abstract

When voyage report data is utilized as the main data source for ship fuel efficiency analysis, its information on weather and sea conditions is often regarded as unreliable. To solve this issue, this study approaches AIS data to obtain the ship's actual detailed geographical positions along its sailing trajectory and then further retrieve the weather and sea condition information from publicly accessible meteorological data sources. These more reliable data about weather and sea conditions the ship sails through is fused into voyage report data in order to improve the accuracy of ship fuel consumption rate models. Eight 8100-TEU to 14,000-TEU containerships from a global shipping company were used in experiments. For each ship, nine datasets were constructed based on data fusion and eleven widely-adopted machine learning models were tested. Experimental results revealed the benefits of fusing voyage report data, AIS data, and meteorological data in improving the fit performances of machine learning models of forecasting ship fuel consumption rate. Over the best datasets, the performances of several decision tree-based models are promising, including Extremely randomized trees (ET), AdaBoost (AB), Gradient Tree Boosting (GB) and XGBoost (XG). With the best datasets, their R2 values over the training sets are all above 0.96 and mostly reach the level of 0.99–1.00, while their R2 values over the test sets are in the range from 0.75 to 0.90. Fit errors of ET, AB, GB, and XG on daily bunker fuel consumption, measured by RMSE and MAE, are usually between 0.8 and 4.5 ton/day. These results are slightly better than our previous study, which confirms the benefits of adopting the actual geographical positions of the ship recorded by AIS data, compared with the estimated geographical positions derived from the great circle route, in retrieving weather and sea conditions the ship sails through.

Keywords

Ship fuel efficiency
Fuel consumption rate
Voyage report
AIS
Data fusion
Machine learning

Cited by (0)

Yuquan Du is a Senior Lecturer in the Centre for Maritime and Logistics Management at Australian Maritime College (AMC), University of Tasmania, Australia. He obtained his PhD in Control Theory and Control Engineering in June 2012 from Nankai University, and then worked for 3 ​years ​as a Research Fellow at the Centre for Maritime Studies, National University of Singapore. His current research concentrates on machine learning models, optimization models, and solution algorithms for management science problems in transportation, logistics, and supply chain management. He is a member of the Australian Maritime Logistics Research Network.

Yanyu Chen is a PhD candidate in the Institute for Marine and Antarctic Studies (IMAS), University of Tasmania (UTAS), Australia. She obtained her master's degree in Information and Communication Technology in July 2021 from UTAS, and then worked as a Research Assistant in the Centre for Maritime and Logistics Management at Australian Maritime College, UTAS. Her current research concentrates on machine learning models, deep learning models, optimization models, and solution algorithms for research problems in marine biology, fishery management, and supply chain management.

Xiaohe Li graduated from Harbin Engineering University. He obtained his PhD in Power Engineering and Engineering Thermophysics from Harbin Engineering University in March 2022. His current research focuses on ship fuel consumption prediction models, machine learning models, energy efficiency optimization models, solution algorithms, and energy efficiency management software development for the shipping industry.

Alessandro Schönborn is an Assistant Professor at World Maritime University (WMU) in the Maritime Energy Management (MEM) specialization. His research interests focus on fuel and propulsion technology, and on marine renewable energy from wave, tidal and ocean currents, but he has further interests in solar and wind power for marine applications. He graduated from University College London (UCL) with an M.Eng. degree in Mechanical Engineering and holds a PhD in combustion (UCL) for a thesis on renewable fuels for diesel engines. Before joining WMU, he worked at MAN Energy Solutions, SINTEF Energy Research, and Lund University.

Zhuo Sun is a Professor at the Department of Logistics in Dalian Maritime University. He received his dual bachelor's degree in Civil Engineering and Computer Science from Dalian University of Technology in China in 2003, master's degree in Hydraulics from Dong-A University in South Korea in 2005, and PhD in Urban Planning from Nagoya University in Japan in 2008. He conducted his postdoctoral research in the Centre for Maritime Studies of National University of Singapore from 2009 to 2012. His research interests are in the areas of shipping network design and port planning. He won the Gold Prize for the “Next Generation Container Port Challenge” in the Singapore in 2013 and the third-place winner of the “The Last Mile Delivery” Algorithm Competition organized by Alibaba, Hong Kong University of Science and Technology, and INFORMS in 2016. He developed a spatial planning tool named MicroCity (https://microcity.github.io).