A machine learning method for the evaluation of probabilistic grounding risk reflecting ship motion uncertainties

Mingyang Zhang; Pentti Kujala; Spyros Hirdaris

doi:10.1201/9781003462170-15

A machine learning method for the evaluation of probabilistic grounding risk reflecting ship motion uncertainties

Mingyang Zhang, Pentti Kujala, Spyros Hirdaris

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Scientific › peer-review

1 Citation (Scopus)

Abstract

The paper introduces a machine learning method for the evaluation of probabilistic grounding risk accounting for ship motion uncertainties in real operational conditions. The approach makes use of big data from Automatic Identification System (AIS), nowcast and gridded bathymetry (GEBCO) data. A machine learning method that combines Principal Component Analysis (PCA) with Multiple-Output Gaussian Process Regression (MOGPR) methods is used to predict selected features of ship motion dynamics namely ship sway, surge accelerations and drift angles. Predicted ship motion trajectories are quantified to present ship position distribution functions in the time domain using a Gaussian Progress Regression (GPR) flow method while the dynamic safety contours of bathymetry maps are extracted based on the ship’s draft and Under Keel Clearance (UKC). The method is applied for probabilistic grounding risk evaluation of a Ro-Pax ship operating between two ports in the Gulf of Finland. The results demonstrate that the presented methodology can predict probabilistic grounding risk reflecting ship motion uncertainties. Thus, it may assist with the development of novel ship decision support systems for proactive grounding risk mitigation.

Original language	English
Title of host publication	Advances in the Collision and Grounding of Ships and Offshore Structures - Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures, ICCGS 2023
Subtitle of host publication	Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures
Editors	Herve La Sourne, Carlos Guedes Soares
Publisher	CRC Press
Pages	101-109
Number of pages	9
ISBN (Electronic)	978-1-003-46217-0
ISBN (Print)	978-1-032-61130-3
DOIs	https://doi.org/10.1201/9781003462170-15
Publication status	Published - 2024
MoE publication type	A3 Book section, Chapters in research books
Event	International Conference on Collision and Grounding of Ships and Offshore Structures - Institut Catholique d'Arts et Métiers, Nantes, France Duration: 11 Sept 2023 → 13 Sept 2023 Conference number: 9

Publication series

Name	Proceedings in Marine Technology and Ocean Engineering
Publisher	CRC Press (Taylor and Francis Group)
Volume	12
ISSN (Print)	2638-647X
ISSN (Electronic)	2638-6461

Conference

Conference	International Conference on Collision and Grounding of Ships and Offshore Structures
Abbreviated title	ICCGS
Country/Territory	France
City	Nantes
Period	11/09/2023 → 13/09/2023

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1201/9781003462170-15

Cite this

Zhang, M., Kujala, P., & Hirdaris, S. (2024). A machine learning method for the evaluation of probabilistic grounding risk reflecting ship motion uncertainties. In H. La Sourne, & C. Guedes Soares (Eds.), Advances in the Collision and Grounding of Ships and Offshore Structures - Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures, ICCGS 2023: Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures (pp. 101-109). (Proceedings in Marine Technology and Ocean Engineering; Vol. 12). CRC Press. https://doi.org/10.1201/9781003462170-15

Zhang, Mingyang ; Kujala, Pentti ; Hirdaris, Spyros. / A machine learning method for the evaluation of probabilistic grounding risk reflecting ship motion uncertainties. Advances in the Collision and Grounding of Ships and Offshore Structures - Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures, ICCGS 2023: Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures. editor / Herve La Sourne ; Carlos Guedes Soares. CRC Press, 2024. pp. 101-109 (Proceedings in Marine Technology and Ocean Engineering).

@inbook{2ca67908666b48e8b75ce973962e4c6f,

title = "A machine learning method for the evaluation of probabilistic grounding risk reflecting ship motion uncertainties",

abstract = "The paper introduces a machine learning method for the evaluation of probabilistic grounding risk accounting for ship motion uncertainties in real operational conditions. The approach makes use of big data from Automatic Identification System (AIS), nowcast and gridded bathymetry (GEBCO) data. A machine learning method that combines Principal Component Analysis (PCA) with Multiple-Output Gaussian Process Regression (MOGPR) methods is used to predict selected features of ship motion dynamics namely ship sway, surge accelerations and drift angles. Predicted ship motion trajectories are quantified to present ship position distribution functions in the time domain using a Gaussian Progress Regression (GPR) flow method while the dynamic safety contours of bathymetry maps are extracted based on the ship{\textquoteright}s draft and Under Keel Clearance (UKC). The method is applied for probabilistic grounding risk evaluation of a Ro-Pax ship operating between two ports in the Gulf of Finland. The results demonstrate that the presented methodology can predict probabilistic grounding risk reflecting ship motion uncertainties. Thus, it may assist with the development of novel ship decision support systems for proactive grounding risk mitigation.",

author = "Mingyang Zhang and Pentti Kujala and Spyros Hirdaris",

year = "2024",

doi = "10.1201/9781003462170-15",

language = "English",

isbn = "978-1-032-61130-3",

series = "Proceedings in Marine Technology and Ocean Engineering",

publisher = "CRC Press",

pages = "101--109",

editor = "{La Sourne}, Herve and {Guedes Soares}, Carlos",

booktitle = "Advances in the Collision and Grounding of Ships and Offshore Structures - Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures, ICCGS 2023",

address = "United States",

note = "International Conference on Collision and Grounding of Ships and Offshore Structures , ICCGS ; Conference date: 11-09-2023 Through 13-09-2023",

}

Zhang, M , Kujala, P & Hirdaris, S 2024, A machine learning method for the evaluation of probabilistic grounding risk reflecting ship motion uncertainties. in H La Sourne & C Guedes Soares (eds), Advances in the Collision and Grounding of Ships and Offshore Structures - Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures, ICCGS 2023: Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures. Proceedings in Marine Technology and Ocean Engineering, vol. 12, CRC Press, pp. 101-109, International Conference on Collision and Grounding of Ships and Offshore Structures , Nantes, France, 11/09/2023. https://doi.org/10.1201/9781003462170-15

A machine learning method for the evaluation of probabilistic grounding risk reflecting ship motion uncertainties. / Zhang, Mingyang ; Kujala, Pentti; Hirdaris, Spyros.
Advances in the Collision and Grounding of Ships and Offshore Structures - Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures, ICCGS 2023: Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures. ed. / Herve La Sourne; Carlos Guedes Soares. CRC Press, 2024. p. 101-109 (Proceedings in Marine Technology and Ocean Engineering; Vol. 12).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Scientific › peer-review

TY - CHAP

T1 - A machine learning method for the evaluation of probabilistic grounding risk reflecting ship motion uncertainties

AU - Zhang, Mingyang

AU - Kujala, Pentti

AU - Hirdaris, Spyros

N1 - Conference code: 9

PY - 2024

Y1 - 2024

N2 - The paper introduces a machine learning method for the evaluation of probabilistic grounding risk accounting for ship motion uncertainties in real operational conditions. The approach makes use of big data from Automatic Identification System (AIS), nowcast and gridded bathymetry (GEBCO) data. A machine learning method that combines Principal Component Analysis (PCA) with Multiple-Output Gaussian Process Regression (MOGPR) methods is used to predict selected features of ship motion dynamics namely ship sway, surge accelerations and drift angles. Predicted ship motion trajectories are quantified to present ship position distribution functions in the time domain using a Gaussian Progress Regression (GPR) flow method while the dynamic safety contours of bathymetry maps are extracted based on the ship’s draft and Under Keel Clearance (UKC). The method is applied for probabilistic grounding risk evaluation of a Ro-Pax ship operating between two ports in the Gulf of Finland. The results demonstrate that the presented methodology can predict probabilistic grounding risk reflecting ship motion uncertainties. Thus, it may assist with the development of novel ship decision support systems for proactive grounding risk mitigation.

AB - The paper introduces a machine learning method for the evaluation of probabilistic grounding risk accounting for ship motion uncertainties in real operational conditions. The approach makes use of big data from Automatic Identification System (AIS), nowcast and gridded bathymetry (GEBCO) data. A machine learning method that combines Principal Component Analysis (PCA) with Multiple-Output Gaussian Process Regression (MOGPR) methods is used to predict selected features of ship motion dynamics namely ship sway, surge accelerations and drift angles. Predicted ship motion trajectories are quantified to present ship position distribution functions in the time domain using a Gaussian Progress Regression (GPR) flow method while the dynamic safety contours of bathymetry maps are extracted based on the ship’s draft and Under Keel Clearance (UKC). The method is applied for probabilistic grounding risk evaluation of a Ro-Pax ship operating between two ports in the Gulf of Finland. The results demonstrate that the presented methodology can predict probabilistic grounding risk reflecting ship motion uncertainties. Thus, it may assist with the development of novel ship decision support systems for proactive grounding risk mitigation.

UR - https://www.routledge.com/Advances-in-the-Collision-and-Grounding-of-Ships-and-Offshore-Structures/Sourne-Soares/p/book/9781032611303

UR - https://doi.org/10.1201/9781003462170

UR - http://www.scopus.com/inward/record.url?scp=85175821579&partnerID=8YFLogxK

U2 - 10.1201/9781003462170-15

DO - 10.1201/9781003462170-15

M3 - Chapter

SN - 978-1-032-61130-3

T3 - Proceedings in Marine Technology and Ocean Engineering

SP - 101

EP - 109

BT - Advances in the Collision and Grounding of Ships and Offshore Structures - Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures, ICCGS 2023

A2 - La Sourne, Herve

A2 - Guedes Soares, Carlos

PB - CRC Press

T2 - International Conference on Collision and Grounding of Ships and Offshore Structures

Y2 - 11 September 2023 through 13 September 2023

ER -

Zhang M , Kujala P, Hirdaris S. A machine learning method for the evaluation of probabilistic grounding risk reflecting ship motion uncertainties. In La Sourne H, Guedes Soares C, editors, Advances in the Collision and Grounding of Ships and Offshore Structures - Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures, ICCGS 2023: Proceedings of the 9th International Conference on Collision and Grounding of Ships and Offshore Structures. CRC Press. 2024. p. 101-109. (Proceedings in Marine Technology and Ocean Engineering). doi: 10.1201/9781003462170-15

A machine learning method for the evaluation of probabilistic grounding risk reflecting ship motion uncertainties

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this