DOI : https://doi.org/10.18517/ijaseit.15.1.12374

Machine Learning-Driven Insights for Optimizing Ship Fuel Consumption: Predictive Modeling and Operational Efficiency

Phuoc Quy Phong Nguyen (1), Duy Tan Nguyen (2), Nhi Ha Thi Yen (3), Quang Le (4), Nhat Thang Nguyen (5), Nguyen Dang Khoa Pham (6)
(1) Maritime College II, Ho Chi Minh City, Vietnam
(2) Institute of Maritime, Ho Chi Minh City University of Transport, Ho Chi Minh City, Vietnam
(3) Faculty of Foreign Languages, Dong Nai Technology University, Bien Hoa City, Vietnam
(4) Faculty of Engineering, Dong Nai Technology University, Bien Hoa City, Vietnam
(5) Faculty of Engineering, Dong Nai Technology University, Bien Hoa City, Vietnam
(6) Institute of Maritime, Ho Chi Minh City University of Transport, Ho Chi Minh City, Vietnam
Fulltext View | Download
How to cite (IJASEIT) :
[1]
P. Q. P. Nguyen, D. T. Nguyen, N. H. T. Yen, Q. Le, N. T. Nguyen, and N. D. Khoa Pham, “Machine Learning-Driven Insights for Optimizing Ship Fuel Consumption: Predictive Modeling and Operational Efficiency”, Int. J. Adv. Sci. Eng. Inf. Technol., vol. 15, no. 1, pp. 27–35, Feb. 2025.
Citation Format :
Specific fuel consumption significantly impacts the shipping industry's operational costs and environmental footprint. Therefore, the development of modeling for predicting ship fuel consumption aiming to maximize the operation efficiency and minimize the pollutant emissions from ship operation is very necessary. By the use of predictive models such as Artificial Neural Networks (ANN) and eXtreme Gradient Boosting (XGBoost), this work optimizes ship fuel usage using machine learning approaches, in which we developed and tested both models using a 149-point dataset split between 70% training and 30% testing data. With a high R-value of 0.9851, MSE of 129.8261, and a low MAPE of 0.2541%, ANN showed good training performance. XGBoost topped ANN in training with a flawless R² of 1.000, MSE of 0.01, and MAPE of 0.21%. With a MAPE of 0.2121%, ANN showed great proportional accuracy on the test set; nevertheless, its high MSE of 26,300 indicated strong sensitivity to outliers. XGBoost showed strong outliers handling with a lower MSE of 259.45 but had a larger MAPE of 16.97%, thereby suggesting lowered proportional accuracy. The findings highlight both models' trade-offs and merits. XGBoost shows higher performance in controlling severe deviations, ANN shines in proportional accuracy. These realizations emphasize the need for model selection depending on application needs as they help predictive modeling for enhancing operational efficiency and reducing fuel consumption in the shipping industry.

IMO, “Fourth IMO GHG study 2020,” 2020. [Online]. Available: https://safety4sea.com/wp-content/uploads/2020/08/MEPC-75-7-15-Fourth-IMO-GHG-Study-2020-Final-report-Secretariat.pdf.

M. Zhang, N. Tsoulakos, P. Kujala, and S. Hirdaris, “A deep learning method for the prediction of ship fuel consumption in real operational conditions,” Eng. Appl. Artif. Intell., vol. 130, p. 107425, Apr. 2024, doi: 10.1016/j.engappai.2023.107425.

H. P. Nguyen et al., “The electric propulsion system as a green solution for management strategy of CO2 emission in ocean shipping: A comprehensive review,” Int. Trans. Electr. Energy Syst., vol. 31, no. 11, p. e12580, 2021, doi: 10.1002/2050-7038.12580.

V. V. Pham and A. T. Hoang, “Technological perspective for reducing emissions from marine engines,” Int. J. Adv. Sci. Eng. Inf. Technol., vol. 9, no. 6, pp. 1989–2000, 2019, doi: 10.18517/ijaseit.9.6.10429.

W. Tarelko and K. Rudzki, “Applying artificial neural networks for modelling ship speed and fuel consumption,” Neural Comput. Appl., vol. 32, no. 23, pp. 17379–17395, Dec. 2020, doi: 10.1007/s00521-020-05111-2.

K. Rudzki, P. Gomulka, and A. T. Hoang, “Optimization Model to Manage Ship Fuel Consumption and Navigation Time,” Polish Marit. Res., vol. 29, no. 3, pp. 141–153, Sep. 2022, doi: 10.2478/pomr-2022-0034.

V. G. Nguyen et al., “Using Artificial Neural Networks for Predicting Ship Fuel Consumption,” Polish Marit. Res., vol. 30, no. 2, pp. 39–60, Jun. 2023, doi: 10.2478/pomr-2023-0020.

T. Chu Van, J. Ramirez, T. Rainey, Z. Ristovski, and R. J. Brown, “Global impacts of recent IMO regulations on marine fuel oil refining processes and ship emissions,” Transp. Res. Part D Transp. Environ., vol. 70, pp. 123–134, May 2019, doi: 10.1016/j.trd.2019.04.001.

IMO, “Initial IMO Strategy on reduction of GHG emissions from ships,” 2018.

P. Serra and G. Fancello, “Towards the IMO’s GHG Goals: A Critical Overview of the Perspectives and Challenges of the Main Options for Decarbonizing International Shipping,” Sustainability, vol. 12, no. 8, p. 3220, Apr. 2020, doi: 10.3390/su12083220.

A. T. Hoang et al., “Technological solutions for boosting hydrogen role in decarbonization strategies and net-zero goals of world shipping: Challenges and perspectives,” Renew. Sustain. Energy Rev., vol. 188, p. 113790, Dec. 2023, doi: 10.1016/j.rser.2023.113790.

T. Cepowski, P. Chorab, and D. Łozowicka, “Application of an Artificial Neural Network and Multiple Nonlinear Regression to Estimate Container Ship Length Between Perpendiculars,” Polish Marit. Res., vol. 28, no. 2, pp. 36–45, 2021, doi: doi:10.2478/pomr-2021-0019.

J. Herdzik, “Decarbonization of Marine Fuels—The Future of Shipping,” Energies, vol. 14, no. 14, p. 4311, Jul. 2021, doi:10.3390/en14144311.

L. Changxiong, Y. Hu, Z. Yang, and H. Guo, “Experimental Study of Fuel Combustion and Emission Characteristics of Marine Diesel Engines Using Advanced Fuels,” Polish Marit. Res., vol. 30, no. 3, pp. 48–58, Sep. 2023, doi: 10.2478/pomr-2023-0038.

W. Zeńczak and A. K. Gromadzińska, “Preliminary Analysis of the Use of Solid Biofuels in a Ship’s Power System,” Polish Marit. Res., vol. 27, no. 4, pp. 67–79, Dec. 2020, doi: 10.2478/pomr-2020-0067.

V. N. Nguyen, N. Chung, G. N. Balaji, K. Rudzki, and A. T. Hoang, “Internet of things-driven approach integrated with explainable machine learning models for ship fuel consumption prediction,” Alexandria Eng. J., vol. 118, pp. 664–680, Apr. 2025, doi:10.1016/j.aej.2025.01.067.

F.-M. Tzu and D.-T. Su, “Evaluation of carbon dioxide emission based on energy efficiency existing ship index during oceanographic navigation,” J. Oper. Oceanogr., vol. 17, no. 3, pp. 151–164, Sep. 2024, doi: 10.1080/1755876X.2023.2254133.

V. Yalama, O. Yakovleva, V. Trandafilov, and M. Khmelniuk, “Future Sustainable Maritime Sector: Fishing Carriers and their Adoption to the Environmental Regulations. Part I,” Polish Marit. Res., vol. 29, no. 3, pp. 69–77, Sep. 2022, doi: 10.2478/pomr-2022-0027.

A. T. Hoang et al., “Energy-related approach for reduction of CO2 emissions: A critical strategy on the port-to-ship pathway,” J. Clean. Prod., vol. 355, p. 131772, Jun. 2022, doi:10.1016/j.jclepro.2022.131772.

Q. Meng, Y. Du, and Y. Wang, “Shipping log data based container ship fuel efficiency modeling,” Transp. Res. Part B Methodol., 2016, doi: 10.1016/j.trb.2015.11.007.

N. Gray, S. McDonagh, R. O’Shea, B. Smyth, and J. D. Murphy, “Decarbonising ships, planes and trucks: An analysis of suitable low-carbon fuels for the maritime, aviation and haulage sectors,” Adv. Appl. Energy, vol. 1, p. 100008, Feb. 2021, doi: 10.1016/j.adapen.2021.100008.

A. Fan, J. Yang, L. Yang, D. Wu, and N. Vladimir, “A review of ship fuel consumption models,” Ocean Eng., vol. 264, p. 112405, Nov. 2022, doi: 10.1016/j.oceaneng.2022.112405.

Z. Hu, Y. Jin, Q. Hu, S. Sen, T. Zhou, and M. T. Osman, “Prediction of Fuel Consumption for Enroute Ship Based on Machine Learning,” IEEE Access, vol. 7, pp. 119497–119505, 2019, doi:10.1109/access.2019.2933630.

P. Karagiannidis, N. Themelis, G. Zaraphonitis, C. Spandonidis, and C. Giordamlis, “Ship fuel consumption prediction using artificial neural networks,” in Proceedings of the Annual meeting of marine technology conference proceedings, Athens, Greece, 2019, pp. 46–51.

S. Nguyen, X. Fu, D. Ogawa, and Q. Zheng, “An application-oriented testing regime and multi-ship predictive modeling for vessel fuel consumption prediction,” Transp. Res. Part E Logist. Transp. Rev., vol. 177, p. 103261, Sep. 2023, doi: 10.1016/j.tre.2023.103261.

T. T. Le et al., “Development of comprehensive models for precise prognostics of ship fuel consumption,” J. Mar. Eng. Technol., vol. 23, no. 6, pp. 451–465, Nov. 2024, doi: 10.1080/20464177.2024.2372888.

T. Zhou, Q. Hu, Z. Hu, and R. Zhen, “An adaptive hyper parameter tuning model for ship fuel consumption prediction under complex maritime environments,” J. Ocean Eng. Sci., vol. 7, no. 3, pp. 255–263, Jun. 2022, doi: 10.1016/j.joes.2021.08.007.

Y. Zhu, Y. Zuo, and T. Li, “Predicting Ship Fuel Consumption based on LSTM Neural Network,” in 2020 7th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS), Nov. 2020, pp. 310–313, doi: 10.1109/ICCSS52145.2020.9336914.

Z. Wang and S. Chen, “Real-time Forecast of Fuel Consumption of Ship Main Engine Based on LSTM Neural Network [J],” J. Wuhan Univ. Technol. (Transportation Sci. Eng., vol. 44, no. 05, pp. 923–927, 2020.

C. Sui, P. de Vos, D. Stapersma, K. Visser, and Y. Ding, “Fuel Consumption and Emissions of Ocean-Going Cargo Ship with Hybrid Propulsion and Different Fuels over Voyage,” J. Mar. Sci. Eng., vol. 8, no. 8, p. 588, Aug. 2020, doi: 10.3390/jmse8080588.

T. Uyanık, Ç. Karatuğ, and Y. Arslanoğlu, “Machine learning approach to ship fuel consumption: A case of container vessel,” Transp. Res. Part D Transp. Environ., vol. 84, p. 102389, Jul. 2020, doi: 10.1016/j.trd.2020.102389.

L. Moreira, R. Vettor, and C. Guedes Soares, “Neural Network Approach for Predicting Ship Speed and Fuel Consumption,” J. Mar. Sci. Eng., vol. 9, no. 2, p. 119, Jan. 2021, doi: 10.3390/jmse9020119.

Z. Yuan, J. Liu, Y. Liu, Y. Yuan, Q. Zhang, and Z. Li, “Fitting Analysis of Inland Ship Fuel Consumption Considering Navigation Status and Environmental Factors,” IEEE Access, vol. 8, pp. 187441–187454, 2020, doi: 10.1109/ACCESS.2020.3030614.

R. Yan, S. Wang, and Y. Du, “Development of a two-stage ship fuel consumption prediction and reduction model for a dry bulk ship,” Transp. Res. Part E Logist. Transp. Rev., vol. 138, p. 101930, Jun. 2020, doi: 10.1016/j.tre.2020.101930.

S. Feng et al., “The Impact of Alternative Fuels on Ship Engine Emissions and Aftertreatment Systems: A Review,” Catalysts, vol. 12, no. 2, p. 138, Jan. 2022, doi: 10.3390/catal12020138.

T. Cong My, L. Dang Khanh, and P. Minh Thao, “An Artificial Neural Networks (ANN) Approach for 3 Degrees of Freedom Motion Controlling,” JOIV Int. J. Informatics Vis., vol. 7, no. 2, p. 301, May 2023, doi: 10.30630/joiv.7.2.1817.

C. Halim, N. G. Eka Putra, N. A. Nugroho, and D. Suhartono, “Chest X-ray Image Classification to Identify Lung Diseases Using Convolutional Neural Network and Convolutional Block Attention Module,” JOIV Int. J. Informatics Vis., vol. 7, no. 3, pp. 651–658, Sep. 2023, doi: 10.30630/joiv.7.3.1136.

J. Hadi, Z. Y. Tay, and D. Konovessis, “Ship Navigation and Fuel Profiling based on Noon Report using Neural Network Generative Modeling,” J. Phys. Conf. Ser., vol. 2311, no. 1, p. 012005, Jul. 2022, doi: 10.1088/1742-6596/2311/1/012005.

P. K. Kanti, P. Sharma, B. Koneru, P. Banerjee, and K. D. Jayan, “Thermophysical profile of graphene oxide and MXene hybrid nanofluids for sustainable energy applications: Model prediction with a Bayesian optimized neural network with K-cross fold validation,” FlatChem, vol. 39, p. 100501, May 2023, doi:10.1016/j.flatc.2023.100501.

I. Veza et al., “Review of artificial neural networks for gasoline, diesel and homogeneous charge compression ignition engine,” Alexandria Eng. J., vol. 61, no. 11, pp. 8363–8391, Nov. 2022, doi:10.1016/j.aej.2022.01.072.

T. M. Shami, M. A. Summakieh, M. Alswaitti, M. A. Al Jahdhami, A. M. Sheikh, and A. A. El-Saleh, “TPPSO: A Novel Two-Phase Particle Swarm Optimization,” JOIV Int. J. Informatics Vis., vol. 7, no. 3–2, p. 2095, Nov. 2023, doi: 10.30630/joiv.7.3-2.2331.

H. Adun, I. Wole-Osho, E. C. Okonkwo, O. Bamisile, M. Dagbasi, and S. Abbasoglu, “A neural network-based predictive model for the thermal conductivity of hybrid nanofluids,” Int. Commun. Heat Mass Transf., vol. 119, p. 104930, Dec. 2020, doi:10.1016/j.icheatmasstransfer.2020.104930.

Z. Pang, F. Niu, and Z. O’Neill, “Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons,” Renew. Energy, vol. 156, pp. 279–289, Aug. 2020, doi: 10.1016/j.renene.2020.04.042.

A. Tuan Hoang et al., “A review on application of artificial neural network (ANN) for performance and emission characteristics of diesel engine fueled with biodiesel-based fuels,” Sustain. Energy Technol. Assessments, vol. 47, p. 101416, Oct. 2021, doi:10.1016/j.seta.2021.101416.

P. Kumar K, M. Alruqi, H. A. Hanafi, P. Sharma, and V. V. Wanatasanappan, “Effect of particle size on second law of thermodynamics analysis of Al2O3 nanofluid: Application of XGBoost and gradient boosting regression for prognostic analysis,” Int. J. Therm. Sci., vol. 197, p. 108825, Mar. 2024, doi:10.1016/j.ijthermalsci.2023.108825.

Z. Said, P. Sharma, B. J. Bora, and A. K. Pandey, “Sonication impact on thermal conductivity of f-MWCNT nanofluids using XGBoost and Gaussian process regression,” J. Taiwan Inst. Chem. Eng., vol. 145, p. 104818, Apr. 2023, doi: 10.1016/j.jtice.2023.104818.

B. Akbar, H. Tayara, and K. T. Chong, “Unveiling dominant recombination loss in perovskite solar cells with a XGBoost-based machine learning approach,” iScience, vol. 27, no. 3, p. 109200, Mar. 2024, doi: 10.1016/j.isci.2024.109200.

J. Noh, T. Na, and S.-S. Kang, “Modeling Solar Irradiance in Tajikistan with XGBoost Algorithm,” J. Eng. Geol., vol. 33, no. 3, pp. 403–411, 2023.

T. Chen and C. Guestrin, “XGBoost,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug. 2016, pp. 785–794, doi: 10.1145/2939672.2939785.

J. Dong, Y. Chen, B. Yao, X. Zhang, and N. Zeng, “A neural network boosting regression model based on XGBoost,” Appl. Soft Comput., vol. 125, p. 109067, Aug. 2022, doi: 10.1016/j.asoc.2022.109067.

Q. T. Phan, Y. K. Wu, and Q. D. Phan, “A Hybrid Wind Power Forecasting Model with XGBoost, Data Preprocessing Considering Different NWPs,” Appl. Sci., vol. 11, no. 3, p. 1100, Jan. 2021, doi:10.3390/app11031100.

O. Sagi and L. Rokach, “Approximating XGBoost with an interpretable decision tree,” Inf. Sci. (Ny)., vol. 572, pp. 522–542, Sep. 2021, doi: 10.1016/j.ins.2021.05.055.

S. Roy, A. Ghosh, A. K. Das, and R. Banerjee, “Development and validation of a GEP model to predict the performance and exhaust emission parameters of a CRDI assisted single cylinder diesel engine coupled with EGR,” Appl. Energy, vol. 140, pp. 52–64, Feb. 2015, doi:10.1016/j.apenergy.2014.11.065.

P. Sharma, “Artificial intelligence‐based model prediction of biodiesel‐fueled engine performance and emission characteristics: A comparative evaluation of gene expression programming and artificial neural network,” Heat Transf., vol. 50, no. 6, pp. 5563–5587, Sep. 2021, doi: 10.1002/htj.22138.

B. Kwon, F. Ejaz, and L. K. Hwang, “Machine learning for heat transfer correlations,” Int. Commun. Heat Mass Transf., vol. 116, p. 104694, Jul. 2020, doi: 10.1016/j.icheatmasstransfer.2020.104694.

S. Pak and T. Oh, “Correlation and Simple Linear Regression,” J. Vet. Clin., vol. 27, no. 4, pp. 427–434, 2010.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).