# Neural Network Modeling Based on the Bayesian Method for Evaluating Shipping Mitigation Measures

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Ship Energy System

## 3. Materials and Methods

#### 3.1. Data Sources

^{3}. The maximum draft was 12.4 m. The data of seven factors and fuel consumption used for estimating mitigation measures were recorded in multiple data sources. The AIS, the Noon Report, the weather report, and onboard measurement data of this tanker were collected from January 2017 to March 2018. The way of recording data for different data sources is different. Some data sources may have a certain degree of uncertainty. For instance, the Noon Report contains the data record of ship working conditions during ship navigation by crews, manually. Human error is inevitable in the Noon Report [22]. The AIS records a real-time record of static and dynamic data during the ship navigation through a global positioning system. The accuracy of AIS data is slightly higher than Noon Report data [29]. However, they both have data uncertainty, as do the weather reports and onboard measurements.

#### 3.2. Model Frameworks

#### 3.2.1. BPNN Modeling Without Uncertainty Analysis

#### 3.2.2. Bayesian Neural Network Modeling with Uncertainty Analysis

#### 3.3. Mitigation Potential Evaluation Using BPNN and BNN

#### 3.4. Cost-Effectiveness Evaluation

## 4. Results and Discussion

## 5. Conclusions

## Author Contributions

## Funding

## Conflicts of Interest

## References

- UNCTAD. Review of Maritime Transport 2018; United Nations Conference on Trade and Development (UNCTAD): New York, NY, USA, 2018; ISBN 978-92-1-112928-1. [Google Scholar]
- IMO. Report of the Marine Environment Protection Committee on Its Seventy-second Session; International Maritime Organization (IMO): London, UK, 2018. [Google Scholar]
- Julià, E.; Tillig, F.; Ringsberg, J.W. Concept Design and Performance Evaluation of a Fossil-Free Operated Cargo Ship with Unlimited Range. Sustainability
**2020**, 12, 6609. [Google Scholar] [CrossRef] - IMO. Energy Saving Potentials for Existing Ships and Candidate Measures Submitted by CESA; Reduction of GHG Emissions from Ships; International Maritime Organization (IMO): London, UK, 2018. [Google Scholar]
- Nian, V.; Yuan, J. A method for analysis of maritime transportation systems in the life cycle approach—The oil tanker example. Appl. Energy
**2017**, 206, 1579–1589. [Google Scholar] [CrossRef] - IMO. Marginal Abatement Costs and Cost-Effectiveness of Energy-Efficiency Measures; Reduction of GHG Emissions from Ships; International Maritime Organization (IMO): London, UK, 2011. [Google Scholar]
- IMO. Further Technical and Operational Measures for Enhancing the Energy Efficiency of International Shipping; International Maritime Organization (IMO): London, UK, 2018. [Google Scholar]
- Smith, T.; Jalkanen, J.; Anderson, B.; Corbett, J.; Faber, J.; Hanayama, S. Third IMO GHG Study; International Maritime Organization (IMO): London, UK, 2014. [Google Scholar]
- Kim, K.-I.; Lee, K.M. Dynamic Programming-Based Vessel Speed Adjustment for Energy Saving and Emission Reduction. Energies
**2018**, 11, 1273. [Google Scholar] [CrossRef] [Green Version] - Wang, S.; Ji, B.; Zhao, J.; Liu, W.; Xu, T. Predicting ship fuel consumption based on LASSO regression. Transp. Res. Part D Transp. Environ.
**2018**, 65, 817–824. [Google Scholar] [CrossRef] - Kee, K.-K.; Simon, B.-Y.L.; Renco, K.-H. Artificial Neural Network Back-Propagation Based Decision Support System for Ship Fuel Consumption Prediction; Institution of Engineering and Technology: Kuala Lumpur, Malaysia, 2018; 13p. [Google Scholar]
- Gkerekos, C.; Lazakis, I.; Theotokatos, G. Machine learning models for predicting ship main engine Fuel Oil Consumption: A comparative study. Ocean Eng.
**2019**, 188, 106282. [Google Scholar] [CrossRef] - Yuan, J.; Nian, V. Ship Energy Consumption Prediction with Gaussian Process Metamodel. Energy Procedia
**2018**, 152, 655–660. [Google Scholar] [CrossRef] - Lago, J.; De Ridder, F.; De Schutter, B. Forecasting spot electricity prices: Deep learning approaches and empirical comparison of traditional algorithms. Appl. Energy
**2018**, 221, 386–405. [Google Scholar] [CrossRef] - Yuan, J.; Wei, S. Comparison of Using Artificial Neural Network and Gaussian Process in Ship Energy Consumption Evaluation. DEStech Trans. Environ. Energy Earth Sci.
**2019**. [Google Scholar] [CrossRef] - Yuan, J.; Wang, H.; Ng, S.H.; Nian, V. Ship Emission Mitigation Strategies Choice Under Uncertainty. Energies
**2020**, 13, 2213. [Google Scholar] [CrossRef] - Anagnostis, A.; Papageorgiou, E.I.; Bochtis, D. Application of Artificial Neural Networks for Natural Gas Consumption Forecasting. Sustainability
**2020**, 12, 6409. [Google Scholar] [CrossRef] - Golzar, F.; Nilsson, D.; Martin, V. Forecasting Wastewater Temperature Based on Artificial Neural Network (ANN) Technique and Monte Carlo Sensitivity Analysis. Sustainability
**2020**, 12, 6386. [Google Scholar] [CrossRef] - Mandal, S.; Prabaharan, N. Ocean wave forecasting using recurrent neural networks. Ocean Eng.
**2006**, 33, 1401–1410. [Google Scholar] [CrossRef] - Beşikçi, E.B.; Arslan, O.; Turan, O.; Ölçer, A. An artificial neural network based decision support system for energy efficient ship operations. Comput. Oper. Res.
**2016**, 66, 393–401. [Google Scholar] [CrossRef] [Green Version] - Jeon, M.; Noh, Y.; Shin, Y.; Lim, O.-K.; Lee, I.; Cho, D. Prediction of ship fuel consumption by using an artificial neural network. J. Mech. Sci. Technol.
**2018**, 32, 5785–5796. [Google Scholar] [CrossRef] - Aldous, L.; Smith, T.; Bucknall, R. Noon Report Data Uncertainty. In Proceedings of the Low Carbon Shipping Conference, London, UK, 9–10 September 2013; p. 13. [Google Scholar]
- Safaei, A.A.; Ghassemi, H.; Ghiasi, M. Correcting and Enriching Vessel’s Noon Report Data Using Statistical and Data Mining Methods. Eur. Trans.
**2018**, 14, 1–13. [Google Scholar] - Safaei, A.A.; Ghassemi, H.; Ghiasi, M. Methodology of Acquiring Valid Data by Combining Oil Tankers’ Noon Report and Automatic Identification System Satellite Data. Promet–Traffic Transp.
**2019**, 31, 299–309. [Google Scholar] [CrossRef] - Deo, R.; Chandra, R. Multi-step-ahead Cyclone Intensity Prediction with Bayesian Neural Networks. In PRICAI 2019: Trends in Artificial Intelligence; Nayak, A.C., Sharma, A., Eds.; Springer International Publishing: Cham, Switzerland, 2019; Volume 11671, pp. 282–295. ISBN 978-3-030-29910-1. [Google Scholar]
- Wright, W. Bayesian approach to neural-network modeling with input uncertainty. IEEE Trans. Neural Netw.
**1999**, 10, 1261–1270. [Google Scholar] [CrossRef] - Baldi, F. Modelling, Analysis and Optimisation of Ship Energy Systems; Doktorsavhandlingar vid Chalmers Tekniska Högskola; Chalmers University of Technology: Gothenburg, Sweden, 2016; ISBN 978-91-7597-359-3. [Google Scholar]
- Yuan, J.; Nian, V.; He, J.; Yan, W. Cost-effectiveness analysis of energy efficiency measures for maritime shipping using a metamodel based approach with different data sources. Energy
**2019**, 189, 116205. [Google Scholar] [CrossRef] - Mao, S.; Tu, E.; Zhang, G.; Rachmawati, L.; Rajabally, E.; Huang, G.-B. An Automatic Identification System (AIS) Database for Maritime Trajectory Prediction and Data Mining. In Proceedings of ELM-2016; Cao, J., Cambria, E., Lendasse, A., Miche, Y., Vong, C.M., Eds.; Springer International Publishing: Cham, Switzerland, 2018; Volume 9, pp. 241–257. ISBN 978-3-319-57420-2. [Google Scholar]
- Zhao, Z.; Xin, H.; Ren, Y.; Guo, X. Application and Comparison of BP Neural Network Algorithm in MATLAB. In Proceedings of the 2010 International Conference on Measuring Technology and Mechatronics Automation, Changsha, China, 13–14 March 2010; IEEE: Piscataway, NJ, USA, 2010; Volume 1, pp. 590–593. [Google Scholar]
- Ding, S.; Su, C.; Yu, J. An optimizing BP neural network algorithm based on genetic algorithm. Artif. Intell. Rev.
**2011**, 36, 153–162. [Google Scholar] [CrossRef] - Meng, F.H.; Sun, L.P.; Zhu, L.K. The Intelligent Controller Design of Parallel Online Mixing and Supplying Glue System. Appl. Mech. Mater.
**2010**, 44, 4089–4093. [Google Scholar] [CrossRef] - Nan, X.; Li, Q.; Qiu, D.; Zhao, Y.; Guo, X. Short-term wind speed syntheses correcting forecasting model and its application. Int. J. Electr. Power Energy Syst.
**2013**, 49, 264–268. [Google Scholar] [CrossRef] - Lin, H.; Chen, S.; Luo, L.; Wang, Z.; Zeng, Y. Research on the Speed Optimization Model Based on BP Neural Network and Genetic Algorithm (GA). In Proceedings of the 29th International Ocean and Polar Engineering Conference, Honolulu, HI, USA, 16–21 June 2019. [Google Scholar]
- Wright, W. Neural Network Regression with Input Uncertainty. In Neural Networks for Signal Processing VIII, Proceedings of the 1998 IEEE Signal Processing Society Workshop (Cat. No.98TH8378), Cambridge, UK, 2 September 1998; IEEE: Piscataway, NJ, USA, 2002; pp. 284–293. [Google Scholar] [CrossRef] [Green Version]
- Taimre, T.; Kroese, D.P.; Botev, Z.I. Monte Carlo methods. In Wiley StatsRef: Statistics Reference Online; John Wiley & Sons, Ltd.: Hoboken, NJ, USA, 2019; p. 10. [Google Scholar]
- Buyukada, M. Uncertainty estimation by Bayesian approach in thermochemical conversion of walnut hull and lignite coal blends. Bioresour. Technol.
**2017**, 232, 87–92. [Google Scholar] [CrossRef] [PubMed] - Vahidinasab, V.; Jadid, S. Bayesian neural network model to predict day-ahead electricity prices. Eur. Trans. Electr. Power
**2008**, 20. [Google Scholar] [CrossRef] - Wang, H.; Yuan, J.; Ng, S.H. Gaussian process based optimization algorithms with input uncertainty. IISE Trans.
**2019**, 52, 377–393. [Google Scholar] [CrossRef] - Yuan, J.; Ng, S.H. Emission reduction measures ranking under uncertainty. Appl. Energy
**2017**, 188, 270–279. [Google Scholar] [CrossRef] - Reflections on the International Coordination of Carbon Pricing. Glob. Carbon Pricing
**2017**, 13. [CrossRef] [Green Version]

**Figure 3.**The fit of observed and predicted fuel consumption using backpropagation neural network BPNN for training data (

**a**) and validation data (

**b**).

**Figure 4.**The fit of observed and predicted fuel consumption using Bayesian neural network (BNN) for training data (

**a**) and validation data (

**b**).

**Figure 5.**The fit of observed and predicted fuel consumption using Gaussian process (GP) for training data (

**a**) and validation data (

**b**).

Network Structure | Performance for the Training Set | Performance for the Validation Set |
---|---|---|

MSE | MSE | |

7–1–1 | 0.0307 | 0.0608 |

7–2–1 | 0.0275 | 0.0464 |

7–3–1 | 0.0256 | 0.0413 |

7–4–1 | 0.0294 | 0.0468 |

7–5–1 | 0.0318 | 0.0592 |

7–6–1 | 0.0320 | 0.0617 |

7–7–1 | 0.0314 | 0.0685 |

7–8–1 | 0.0342 | 0.0692 |

7–9–1 | 0.0355 | 0.0737 |

7–10–1 | 0.0411 | 0.0780 |

7–11–1 | 0.0467 | 0.0843 |

7–12–1 | 0.0432 | 0.0967 |

Network Structure | Performance for the Training Set | Performance for the Validation Set |
---|---|---|

MSE | MSE | |

7–1–1 | 0.0262 | 0.0566 |

7–2–1 | 0.0229 | 0.0412 |

7–3–1 | 0.0193 | 0.0360 |

7–4–1 | 0.0244 | 0.0404 |

7–5–1 | 0.0274 | 0.0548 |

7–6–1 | 0.0256 | 0.0553 |

7–7–1 | 0.0263 | 0.0629 |

7–8–1 | 0.0281 | 0.0638 |

7–9–1 | 0.0295 | 0.0676 |

7–10–1 | 0,0328 | 0.0691 |

7–11–1 | 0.0361 | 0.0734 |

7–12–1 | 0.0398 | 0.0865 |

**Table 3.**Average MSE values, using BPNN, BNN and Gaussian process (GP) models for training data and validation data.

Models | Performance for the Training Data | Performance for the Validation Data |
---|---|---|

Average MSE | Average MSE | |

BPNN | 0.0283 | 0.0436 |

BNN | 0.0189 | 0.0347 |

GP | 0.0194 | 0.0353 |

Performance (Metric Tons) | Speed Reduction (10%) | Weather Routing | Draft Optimization | Trim Optimization |
---|---|---|---|---|

Annual energy saving | 525.47 | 68.85 | 47.80 | 45.80 |

Emission reduction | 1636.32 | 214.40 | 148.84 | 142.64 |

Mitigation Measures | Annual Emission Reduction (MT) | Implementation Cost (US$) | MCE (US$/MT) | Ranking |
---|---|---|---|---|

Speed Reduction (10%) | 1636.32 | −20,402 | 12.55 | 1 |

Weather Routing | 214.40 | −38,241 | −233.45 | 2 |

Draft Optimization | 148.84 | −22,936 | −5.81 | 3 |

Trim Optimization | 142.64 | −22,900 | - | 4 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Yuan, J.; Zhu, J.; Nian, V.
Neural Network Modeling Based on the Bayesian Method for Evaluating Shipping Mitigation Measures. *Sustainability* **2020**, *12*, 10486.
https://doi.org/10.3390/su122410486

**AMA Style**

Yuan J, Zhu J, Nian V.
Neural Network Modeling Based on the Bayesian Method for Evaluating Shipping Mitigation Measures. *Sustainability*. 2020; 12(24):10486.
https://doi.org/10.3390/su122410486

**Chicago/Turabian Style**

Yuan, Jun, Jiang Zhu, and Victor Nian.
2020. "Neural Network Modeling Based on the Bayesian Method for Evaluating Shipping Mitigation Measures" *Sustainability* 12, no. 24: 10486.
https://doi.org/10.3390/su122410486