International journal of advanced smart convergence

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Development of a Carbon Emission Prediction Model for Bulk Carrier Based on EEDI Guidelines and Factor Interpretation Using SHAP

  • Hyunju Kim (Department of Intelligent Convergence Research, Korea Marine Equipment Research Institute) ;
  • Byeongseok Yu (Department of Smart Machine Mobility Engineering, Pukyong National University) ;
  • Donghyun Kim (Department of Smart Machine Mobility Engineering, Pukyong National University)
  • Received : 2024.07.09
  • Accepted : 2024.07.22
  • Published : 2024.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

The model developed in this study holds significant importance in predicting carbon emissions in maritime transport. By utilizing ship data and EEDI (Energy Efficiency Design Index) guidelines, the model presents a highly accurate prediction tool, providing a solid foundation for maximizing operational efficiency and effectively managing carbon emissions in ship operations. The model's accuracy was demonstrated by an R2 score of 0.95 and a Mean Absolute Percentage Error (MAPE) of 1.4%. Through SHAP (SHapley Additive exPlanations) and Partial Dependence Plots (PDP), it was identified that Speed Over Ground and relative wind speed are the most significant variables, both showing a positive correlation with increased CO2 emissions. Additionally, environmental factors such as exceeding an average draft of 22(m), a Leeway over 5°, and a current angle exceeding 200° were found to increase emissions significantly. Specific ranges of wind and swell wave angles also notably affected emissions. Conversely, lower pitch, roll, and rudder angle were associated with reduced emissions, indicating that stable ship operation enhances efficiency.

Keywords

Acknowledgement

This work was supported Commercialization Promotion Agency for R&D Outcomes(COMPA) and Busan Innovation Institute of Industry, Science & Technology Planning(BISTEP) by grant funded by the Korea government(MSIT) and a local government(Busan) (No.2023-0487)

References

  1. B. Mary Nathisiya, "Article Title: Adoption of IoT technology in Maritime Sector Adoption of IoT technology in Maritime Sector," IJATEM.
  2. D. Kaklis, T. J. Varelas, I. Varlamis, P. Eirinakis, G. Giannakopoulos, and C. V Spyropoulos, "From STEAM to Machine: Emissions control in the shipping 4.0 era," Mar. 07, 2023. DOI: https://doi.org/10.5957/SOME-2023-020.
  3. Y. C. Shih, Y. A. Tzeng, C. W. Cheng, and C. H. Huang, "Speed Optimization in Bulk Carriers: A Weather-Sensitive Approach for Reducing Fuel Consumption," J. Mar. Sci. Eng., vol. 11, no. 10, 2023, DOI: https://doi.org/10.3390/jmse11102000.
  4. Y. Yuan, X. Wang, L. Tong, R. Yang, and B. Shen, "Research on Multi-Objective Energy Efficiency Optimization Method of Ships Considering Carbon Tax," J. Mar. Sci. Eng., vol. 11, no. 1, 2023, DOI: https://doi.org/10.3390/jmse11010082.
  5. T. Committee, "80 session of the Marine Environment Protection Committee ( MEPC 80 )," no. July 2023, pp. 3-7, 2025.
  6. IMO MEPC, "Fourth IMO Greenhouse Gas Study: Executive Summary," IMO Greenh. Gas Study, vol. 4, no. 1, p. 46, 2020.
  7. IMO, "Resolution MEPC.231(65): 2013 Guidelines for Calculation of Reference Lines for Use with the Energy Efficiency Design Index (EEDI)," Marine Environment Protection Committee, 2013.
  8. IMO, "Resolution MEPC.328(76): Amendments to the Annex of the Protocol of 1997 to Amend the International Convention for the Prevention of Pollution from Ships, 1973, as Modified by the Protocol of 1978 Relating Thereto" (2021 Revised MARPOL Annex VI), Marine Environment Protection Committee, 2021.
  9. J. Barreiro, S. Zaragoza, and V. Diaz-Casas, "Review of ship energy efficiency," Ocean Eng., vol. 257, no. January, p. 111594, 2022, DOI: https://doi.org/10.1016/j.oceaneng.2022.111594.
  10. K. Alexiou, E. G. Pariotis, and H. C. Leligou, "Sensor Data Quality in Ships: A Time Series Forecasting Approach to Compensate for Missing Data and Drift in Measurements of Speed through Water Sensors," Designs, vol. 7, no. 2, 2023, DOI: https://doi.org/10.3390/designs7020046
  11. Y. R. Kim, M. Jung, and J. B. Park, "Development of a fuel consumption prediction model based on machine learning using ship in-service data," J. Mar. Sci. Eng., vol. 9, no. 2, pp. 1-25, Feb. 2021, DOI: https://doi.org/10.3390/jmse9020137.
  12. M. P. Handayani, H. Kim, S. Lee, and J. Lee, "Navigating Energy Efficiency: A Multifaceted Interpretability of Fuel Oil Consumption Prediction in Cargo Container Vessel Considering the Operational and Environmental Factors," J. Mar. Sci. Eng., vol. 11, no. 11, Nov. 2023, DOI: https://doi.org/10.3390/jmse11112165.
  13. S. Wang, X. Wang, Y. Han, X. Wang, H. Jiang, and Z. Zhang, "Ship Fuel and Carbon Emission Estimation Utilizing Artificial Neural Network and Data Fusion Techniques," J. Softw. Eng. Appl., vol. 16, no. 03, pp. 51-72, 2023, DOI: https://doi.org/10.4236/jsea.2023.163004.
  14. T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., vol. 13-17-August-2016, pp. 785-794, 2016, DOI: https://doi.org/10.1145/2939672.293978.
  15. H. K. M. P. J. Lee, "A Study on the Prediction of Fuel Consumption of Bulk Ship Main Engine Using Explainable Artificial Intelligence," vol. 47, no. 4, pp. 182-190, 2023.
  16. Y. Ning et al., "Shapley variable importance clouds for interpretable machine learning," ArXiv, vol. abs/2110.02484, 2021, DOI: https://doi.org/10.48550/arXiv.2110.02484.
  17. S. M. Lundberg and S. I. Lee, "A unified approach to interpreting model predictions," Adv. Neural Inf. Process. Syst., vol. 2017-December, no. Section 2, pp. 4766-4775, 2017, DOI: https://doi.org/10.48550/arXiv.1705.07874.
  18. A. Guryanov, "Efficient Computation of SHAP Values for Piecewise-Linear Decision Trees," Proc. ITNT 2021 - 7th IEEE Int. Conf. Inf. Technol. Nanotechnol., pp. 1-4, 2021, DOI: https://doi.org/10.1109/ITNT52450.2021.9649051.
  19. K. Kwon and J. So, "Future Smart Logistics Technology Based on Patent Analysis Using Temporal Network," Sustain., vol. 15, no. 10, May 2023, DOI: https://doi.org/10.3390/su15108159