A machine learning approach for monitoring ship safety in extreme weather events
A machine learning approach for monitoring ship safety in extreme weather events
Extreme weather events can result in loss of life, environmental pollution and major damage to vessels caught in their path. Many methods to characterise this risk have been proposed, however, they typically utilise deterministic thresholds of wind and wave limits which might not accurately reflect risk. To address this limitation, we investigate the potential of machine learning algorithms to quantify the relative likelihood of an incident during the US Atlantic hurricane season. By training an algorithm on vessel traffic, weather and historical casualty data, accident candidates can be identified from historic vessel tracks. Amongst the various methods tested, Support Vector Machines showed good performance with Recall at 95% and Accuracy reaching 92%. Finally, we implement the developed model using a case study of Hurricane Matthew (October 2016). Our method contributes to enhancements in maritime safety by enabling machine intelligent risk-aware ship routing and monitoring of vessel transits by Coastguard agencies.
Machine learning, Maritime Risk Assessment, Navigation Safety, Severe Weather Events
Rawson, Andrew David
2f5d38d7-f4c9-45f5-a8de-c7f91b8f68c7
Brito, Mario
82e798e7-e032-4841-992e-81c6f13a9e6c
Sabeur, Zoheir
e6e98155-eadb-4b0f-ba88-ba5c313f0e24
Tran-Thanh, Long
aecacf50-460e-410a-83be-b0c2a5ae226e
September 2021
Rawson, Andrew David
2f5d38d7-f4c9-45f5-a8de-c7f91b8f68c7
Brito, Mario
82e798e7-e032-4841-992e-81c6f13a9e6c
Sabeur, Zoheir
e6e98155-eadb-4b0f-ba88-ba5c313f0e24
Tran-Thanh, Long
aecacf50-460e-410a-83be-b0c2a5ae226e
Rawson, Andrew David, Brito, Mario, Sabeur, Zoheir and Tran-Thanh, Long
(2021)
A machine learning approach for monitoring ship safety in extreme weather events.
Safety Science, 141, [105336].
(doi:10.1016/j.ssci.2021.105336).
Abstract
Extreme weather events can result in loss of life, environmental pollution and major damage to vessels caught in their path. Many methods to characterise this risk have been proposed, however, they typically utilise deterministic thresholds of wind and wave limits which might not accurately reflect risk. To address this limitation, we investigate the potential of machine learning algorithms to quantify the relative likelihood of an incident during the US Atlantic hurricane season. By training an algorithm on vessel traffic, weather and historical casualty data, accident candidates can be identified from historic vessel tracks. Amongst the various methods tested, Support Vector Machines showed good performance with Recall at 95% and Accuracy reaching 92%. Finally, we implement the developed model using a case study of Hurricane Matthew (October 2016). Our method contributes to enhancements in maritime safety by enabling machine intelligent risk-aware ship routing and monitoring of vessel transits by Coastguard agencies.
Text
Hurricane_SS_02
- Accepted Manuscript
More information
Accepted/In Press date: 4 May 2021
e-pub ahead of print date: 28 May 2021
Published date: September 2021
Additional Information:
Funding Information:
This work is partly funded by the University of Southampton's Marine and Maritime Institute (SMMI) and the European Research Council under the European Union's Horizon 2020 research and innovation program (grant agreement number: 723526: SEDNA).
Funding Information:
This work is partly funded by the University of Southampton’s Marine and Maritime Institute (SMMI) and the European Research Council under the European Union’s Horizon 2020 research and innovation program (grant agreement number: 723526: SEDNA).
Publisher Copyright:
© 2021 Elsevier Ltd
Keywords:
Machine learning, Maritime Risk Assessment, Navigation Safety, Severe Weather Events
Identifiers
Local EPrints ID: 448996
URI: http://eprints.soton.ac.uk/id/eprint/448996
ISSN: 0925-7535
PURE UUID: 6c3a1c5e-c33d-44bc-b79e-44d151aef352
Catalogue record
Date deposited: 13 May 2021 16:30
Last modified: 17 Mar 2024 06:34
Export record
Altmetrics
Contributors
Author:
Andrew David Rawson
Author:
Zoheir Sabeur
Author:
Long Tran-Thanh
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics