From conventional to machine learning methods for maritime riskassessment

• Autorzy: Rawson A. , Brito M. , Sabeur Z. , Tran-Thanh L.

Identyfikatory

DOI

10.12716/1001.15.04.06

• Języki publikacji: EN

Abstrakty

EN

Within the last thirty years, the range and complexity of methodologies proposed to assess maritime risk have increased significantly. Techniques such as expert judgement, incident analysis, geometric models, domain analysis and Bayesian Networks amongst many others have become dominant within both the literature and industry. On top of this, advances in machine learning algorithms and big data have opened opportunities for new methods which might overcome some limitations of conventional approaches. Yet, determining the suitability or validity of one technique over another is challenging as it requires a systematic multicriteria approach to compare the inputs, assumptions, methodologies and results of each method. Within this paper, such an approach is proposed and tested within an isolated waterway in order to justify the proposed advantages of a machine learning approach to maritime risk assessment and should serve as inspiration for future work.

Słowa kluczowe

EN

risk assessment; machine learning method; Bayesian network; machine learning algorithms; multicriteria approach; maritime risk

• Wydawca: Faculty of Navigation, Gdynia Maritime University
• Czasopismo: TransNav : International Journal on Marine Navigation and Safety of Sea Transportation
• Rocznik: 2021
• Tom: Vol. 15 No. 4
• Strony: 757--764
• Opis fizyczny: Bibliogr. 42 poz., rys., tab.

Twórcy

autor

Rawson A.

• University of Southampton, Southampton, UK

autor

Brito M.

• University of Southampton, Southampton, UK

autor

Sabeur Z.

• Bournemouth University, Bournemouth, UK

autor

Tran-Thanh L.

• University of Warwick, Warwick, UK

Bibliografia

• 1. Altan, Y.C.: Collision diameter for maritime accidents considering the drifting of vessels. Ocean Engineering. 187, 106158 (2019). https://doi.org/10.1016/j.oceaneng.2019.106158.
• 2. Aven, T., Zio, E.: Some considerations on the treatment of uncertainties in risk assessment for practical decision making. Reliability Engineering & System Safety. 96, 1, 64–74 (2011). https://doi.org/10.1016/j.ress.2010.06.001.
• 3. Bye, R.J., Almklov, P.G.: Normalization of maritime accident data using AIS. Marine Policy. 109, 103675 (2019). https://doi.org/10.1016/j.marpol.2019.103675.
• 4. Chen, P., Huang, Y., Mou, J., van Gelder, P.H.A.J.M.: Probabilistic risk analysis for ship-ship collision: State-of-the-art. Safety Science. 117, 108–122 (2019). https://doi.org/10.1016/j.ssci.2019.04.014.
• 5. Dorsey, L.C., Wang, B., Grabowski, M., Merrick, J., Harrald, J.R.: Self healing databases for predictive risk analytics in safety-critical systems. Journal of Loss Prevention in the Process Industries. 63, 104014 (2020). https://doi.org/10.1016/j.jlp.2019.104014.
• 6. Du, L., Goerlandt, F., Kujala, P.: Review and analysis of methods for assessing maritime waterway risk based on non-accident critical events detected from AIS data. Reliability Engineering & System Safety. 200, 106933 (2020). https://doi.org/10.1016/j.ress.2020.106933.
• 7. EMSA: Joint Workshop on Risk Assessment and Response Planning in Europe. , London (2018).
• 8. Friis-Hansen, P.: IWRAP MK II: Working Document: Basic Modelling Principles for Prediction of Collision and Grounding Frequencies, https://www.ialaaism.org/wiki/iwrap/images/2/2b/IWRAP_Theory.pdf, last accessed 2020/12/15.
• 9. Fujino, I., Claramunt, C., Boudraa, A.-O.: Extracting Courses of Vessels from AIS Data and Real-Time Warning Against Off-Course. In: Proceedings of the 2nd International Conference on Big Data Research. pp. 62–69 Association for Computing Machinery, New York, NY, USA (2018). https://doi.org/10.1145/3291801.3291823.
• 10. Gao, M., Shi, G., Li, S.: Online Prediction of Ship Behavior with Automatic Identification System Sensor Data Using Bidirectional Long Short-Term Memory Recurrent Neural Network. Sensors. 18, 12, (2018). https://doi.org/10.3390/s18124211.
• 11. Goerlandt, F., Kujala, P.: On the reliability and validity of ship–ship collision risk analysis in light of different perspectives on risk. Safety Science. 62, 348–365 (2014). https://doi.org/10.1016/j.ssci.2013.09.010.
• 12. Goodwin, E.M.: A Statistical Study of Ship Domains. Journal of Navigation. 28, 3, 328–344 (1975). https://doi.org/10.1017/S0373463300041230.
• 13. Hänninen, M.: Bayesian networks for maritime traffic accident prevention: Benefits and challenges. Accident Analysis & Prevention. 73, 305–312 (2014). https://doi.org/10.1016/j.aap.2014.09.017.
• 14. Hassel, M., Asbjørnslett, B.E., Hole, L.P.: Underreporting of maritime accidents to vessel accident databases. Accident Analysis & Prevention. 43, 6, 2053–2063 (2011). https://doi.org/10.1016/j.aap.2011.05.027.
• 15. Hegde, J., Rokseth, B.: Applications of machine learning methods for engineering risk assessment – A review. Safety Science. 122, 104492 (2020). https://doi.org/10.1016/j.ssci.2019.09.015.
• 16. Hörteborn, A., Ringsberg, J.W., Svanberg, M., Holm, H.: A Revisit of the Definition of the Ship Domain based on AIS Analysis. Journal of Navigation. 72, 3, 777–794 (2019). https://doi.org/10.1017/S0373463318000978.
• 17. Hubbard, D.W.: The Failure of Risk Management: Why It’s Broken and How to Fix It. Wiley (2020).
• 18. IMO: Revised Guidelines for Formal Safety Assessment (FSA) For Use in the IMO Rule-Making Process. (2018).
• 19. Jin, M., Shi, W., Yuen, K.F., Xiao, Y., Li, K.X.: Oil tanker risks on the marine environment: An empirical study and policy implications. Marine Policy. 108, 103655 (2019). https://doi.org/10.1016/j.marpol.2019.103655.
• 20. Kim, H., Koo, J., Kim, D., Park, B., Jo, Y., Myung, H., Lee, D.: Vision-Based Real-Time Obstacle Segmentation Algorithm for Autonomous Surface Vehicle. IEEE Access. 7, 179420–179428 (2019). https://doi.org/10.1109/ACCESS.2019.2959312.
• 21. Kulkarni, K., Goerlandt, F., Li, J., Banda, O.V., Kujala, P.: Preventing shipping accidents: Past, present, and future of waterway risk management with Baltic Sea focus. Safety Science. 129, 104798 (2020). https://doi.org/10.1016/j.ssci.2020.104798.
• 22. Li, S., Meng, Q., Qu, X.: An overview of maritime waterway quantitative risk assessment models. Risk Anal. 32, 3, 496–512 (2012). https://doi.org/10.1111/j.1539-6924.2011.01697.x.
• 23. Lim, G.J., Cho, J., Bora, S., Biobaku, T., Parsaei, H.: Models and computational algorithms for maritime risk analysis: a review. Annals of Operations Research. 271, 2, 765–786 (2018). https://doi.org/10.1007/s10479-018-2768-4.
• 24. Liu, Z., Wu, Z., Zheng, Z.: A novel framework for regional collision risk identification based on AIS data. Applied Ocean Research. 89, 261–272 (2019). https://doi.org/10.1016/j.apor.2019.05.020.
• 25. Mazaheri, A., Montewka, J., Kotilainen, P., Edvard Sormunen, O.-V., Kujala, P.: Assessing Grounding Frequency using Ship Traffic and Waterway Complexity. Journal of Navigation. 68, 1, 89–106 (2015). https://doi.org/10.1017/S0373463314000502.
• 26. Mazaheri, A., Montewka, J., Kujala, P.: Towards an evidence-based probabilistic risk model for ship-grounding accidents. Safety Science. 86, 195–210 (2016). https://doi.org/10.1016/j.ssci.2016.03.002.
• 27. Mazaheri, A., Ylitalo, J.: Comments on Geometrical Modeling of Ship Grounding. Presented at the 5th International Conference on Collision and Grounding of Ships (2010). https://doi.org/10.13140/2.1.3359.3284.
• 28. OpenRisk: OpenRisk Guideline for Regional Risk Management to Improve European Pollution Preparedness and Response at Sea, https://portal.helcom.fi/meetings/OPENRISK%20WS%203-2018-527/Related%20Information/OPENRISK%20Guide_Final_13_6_18.pdf, last accessed 2020/12/15.
• 29. Pedersen, P.: Collision and grounding mechanics. The Danish Society of Naval Architects and Marine Engineers. 125–157 (1995).
• 30. Rawson, A.: An Analysis of Vessel Traffic Flow Before and After the Grounding of the MV Rena, 2011. In: Weintrit, A. (ed.) Marine Navigation. pp. 203–209 CRC Press (2017). https://doi.org/10.1201/9781315099132-24.
• 31. Rawson, A., Brito, M.: A critique of the use of domain analysis for spatial collision risk assessment. Ocean Engineering. 219, 108259 (2021). https://doi.org/10.1016/j.oceaneng.2020.108259.
• 32. Rawson, A.D., Brito, M.: Modelling of ship navigation in extreme weather events using machine learning. In: Proceedings of the 30th European Safety and Reliability Conference and the 15th Probabilistic Safety Assessment And Management Conference. Research Publlishing (2020).
• 33. Riveiro, M., Pallotta, G., Vespe, M.: Maritime anomaly detection: A review. WIREs Data Mining and Knowledge Discovery. 8, 5, e1266 (2018). https://doi.org/10.1002/widm.1266.
• 34. Suo, Y., Chen, W., Claramunt, C., Yang, S.: A Ship Trajectory Prediction Framework Based on a Recurrent Neural Network. Sensors. 20, 18, (2020). https://doi.org/10.3390/s20185133.
• 35. Szlapczynski, R., Szlapczynska, J.: Review of ship safety domains: Models and applications. Ocean Engineering. 145, 277–289 (2017). https://doi.org/10.1016/j.oceaneng.2017.09.020.
• 36. Tang, L., Tang, Y., Zhang, K., Du, L., Wang, M.: Prediction of Grades of Ship Collision Accidents Based on Random Forests and Bayesian Networks. In: 2019 5th International Conference on Transportation Information and Safety (ICTIS). pp. 1377–1381 (2019). https://doi.org/10.1109/ICTIS.2019.8883590.
• 37. Tetlock, P.E.: Expert Political Judgment: How Good Is It? How Can We Know? Princeton University Press (2005).
• 38. Tversky, A., Kahneman, D.: Judgment under Uncertainty: Heuristics and Biases. Science. 185, 4157, 1124–1131 (1974). https://doi.org/10.1126/science.185.4157.1124.
• 39. Van Dorp, J., Merrick, J.: VTRA 2010 Final Report. George Washington University (2014).
• 40. Wang, N.: An Intelligent Spatial Collision Risk Based on the Quaternion Ship Domain. Journal of Navigation. 63, 4, 733–749 (2010).
• 41. Zhang, G., Thai, V.V.: Expert elicitation and Bayesian Network modeling for shipping accidents: A literature review. Safety Science. 87, 53–62 (2016). https://doi.org/10.1016/j.ssci.2016.03.019.
• 42. Zhang, W., Feng, X., Goerlandt, F., Liu, Q.: Towards a Convolutional Neural Network model for classifying regional ship collision risk levels for waterway risk analysis. Reliability Engineering & System Safety. 204, 107127 (2020). https://doi.org/10.1016/j.ress.2020.107127.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).