Predicting vessel speed in the Arctic without knowing ice conditions using AIS data and decision trees
The vessel speed is one of the important parameters that govern safety, emergency, and transport planning in the Arctic. While previous studies have traditionally relied on physics-based simulations to predict vessel's speed in ice-covered waters, most have not fully explored data-driven approa...
Published in: | Maritime Transport Research |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Elsevier
2021
|
Subjects: | |
Online Access: | https://doi.org/10.1016/j.martra.2021.100024 https://doaj.org/article/8e562597326841448c6bfac7116ffcc0 |
id |
ftdoajarticles:oai:doaj.org/article:8e562597326841448c6bfac7116ffcc0 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:8e562597326841448c6bfac7116ffcc0 2023-05-15T14:55:47+02:00 Predicting vessel speed in the Arctic without knowing ice conditions using AIS data and decision trees Prithvi S Rao Ekaterina Kim Bjørnar Brende Smestad Bjørn Egil Asbjørnslett Anirban Bhattacharyya 2021-01-01T00:00:00Z https://doi.org/10.1016/j.martra.2021.100024 https://doaj.org/article/8e562597326841448c6bfac7116ffcc0 EN eng Elsevier http://www.sciencedirect.com/science/article/pii/S2666822X21000162 https://doaj.org/toc/2666-822X 2666-822X doi:10.1016/j.martra.2021.100024 https://doaj.org/article/8e562597326841448c6bfac7116ffcc0 Maritime Transport Research, Vol 2, Iss , Pp 100024- (2021) Arctic AIS Decision trees Speed Shipment of goods. Delivery of goods HF5761-5780 article 2021 ftdoajarticles https://doi.org/10.1016/j.martra.2021.100024 2022-12-31T15:38:39Z The vessel speed is one of the important parameters that govern safety, emergency, and transport planning in the Arctic. While previous studies have traditionally relied on physics-based simulations to predict vessel's speed in ice-covered waters, most have not fully explored data-driven approaches and powerful supervised machine learning tools to aid speed prediction. This study offers a perspective of applying supervised machine learning models to predict MV SOG using historical Automatic Identification System (AIS) data and without explicit knowledge of local ice conditions. This paper presents a case-study from the region of the Eastern Barents Sea and the Southern Kara Sea. We first analyzed the vessel traffic situation for the years 2017 and 2018, and then used this knowledge to build statistical models to predict vessel speeds. Finally, we evaluated the models’ performance on a test dataset from January 2019. Performance of three models (Random Forest, XGBoost, and LightGBM) have been tested with a variety of date-time handling techniques, and data input mode being permuted to arrive at the most optimal model. The results demonstrate the ability of the models to predict the vessel's speed based on its geographical location, time of the year and other engineered features such as daylight information and route. With the proposed approach we were able to achieve mean absolute error 3.5 knots in average on a test dataset without explicit knowledge of local ice conditions around the vessel, with the majority of the errors being in the Kara Strait region and the Sabetta Channel. Article in Journal/Newspaper Arctic Barents Sea Kara Sea ice covered waters Directory of Open Access Journals: DOAJ Articles Arctic Barents Sea Kara Sea Sog ENVELOPE(-20.972,-20.972,63.993,63.993) Sabetta ENVELOPE(72.039,72.039,71.214,71.214) Maritime Transport Research 2 100024 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Arctic AIS Decision trees Speed Shipment of goods. Delivery of goods HF5761-5780 |
spellingShingle |
Arctic AIS Decision trees Speed Shipment of goods. Delivery of goods HF5761-5780 Prithvi S Rao Ekaterina Kim Bjørnar Brende Smestad Bjørn Egil Asbjørnslett Anirban Bhattacharyya Predicting vessel speed in the Arctic without knowing ice conditions using AIS data and decision trees |
topic_facet |
Arctic AIS Decision trees Speed Shipment of goods. Delivery of goods HF5761-5780 |
description |
The vessel speed is one of the important parameters that govern safety, emergency, and transport planning in the Arctic. While previous studies have traditionally relied on physics-based simulations to predict vessel's speed in ice-covered waters, most have not fully explored data-driven approaches and powerful supervised machine learning tools to aid speed prediction. This study offers a perspective of applying supervised machine learning models to predict MV SOG using historical Automatic Identification System (AIS) data and without explicit knowledge of local ice conditions. This paper presents a case-study from the region of the Eastern Barents Sea and the Southern Kara Sea. We first analyzed the vessel traffic situation for the years 2017 and 2018, and then used this knowledge to build statistical models to predict vessel speeds. Finally, we evaluated the models’ performance on a test dataset from January 2019. Performance of three models (Random Forest, XGBoost, and LightGBM) have been tested with a variety of date-time handling techniques, and data input mode being permuted to arrive at the most optimal model. The results demonstrate the ability of the models to predict the vessel's speed based on its geographical location, time of the year and other engineered features such as daylight information and route. With the proposed approach we were able to achieve mean absolute error 3.5 knots in average on a test dataset without explicit knowledge of local ice conditions around the vessel, with the majority of the errors being in the Kara Strait region and the Sabetta Channel. |
format |
Article in Journal/Newspaper |
author |
Prithvi S Rao Ekaterina Kim Bjørnar Brende Smestad Bjørn Egil Asbjørnslett Anirban Bhattacharyya |
author_facet |
Prithvi S Rao Ekaterina Kim Bjørnar Brende Smestad Bjørn Egil Asbjørnslett Anirban Bhattacharyya |
author_sort |
Prithvi S Rao |
title |
Predicting vessel speed in the Arctic without knowing ice conditions using AIS data and decision trees |
title_short |
Predicting vessel speed in the Arctic without knowing ice conditions using AIS data and decision trees |
title_full |
Predicting vessel speed in the Arctic without knowing ice conditions using AIS data and decision trees |
title_fullStr |
Predicting vessel speed in the Arctic without knowing ice conditions using AIS data and decision trees |
title_full_unstemmed |
Predicting vessel speed in the Arctic without knowing ice conditions using AIS data and decision trees |
title_sort |
predicting vessel speed in the arctic without knowing ice conditions using ais data and decision trees |
publisher |
Elsevier |
publishDate |
2021 |
url |
https://doi.org/10.1016/j.martra.2021.100024 https://doaj.org/article/8e562597326841448c6bfac7116ffcc0 |
long_lat |
ENVELOPE(-20.972,-20.972,63.993,63.993) ENVELOPE(72.039,72.039,71.214,71.214) |
geographic |
Arctic Barents Sea Kara Sea Sog Sabetta |
geographic_facet |
Arctic Barents Sea Kara Sea Sog Sabetta |
genre |
Arctic Barents Sea Kara Sea ice covered waters |
genre_facet |
Arctic Barents Sea Kara Sea ice covered waters |
op_source |
Maritime Transport Research, Vol 2, Iss , Pp 100024- (2021) |
op_relation |
http://www.sciencedirect.com/science/article/pii/S2666822X21000162 https://doaj.org/toc/2666-822X 2666-822X doi:10.1016/j.martra.2021.100024 https://doaj.org/article/8e562597326841448c6bfac7116ffcc0 |
op_doi |
https://doi.org/10.1016/j.martra.2021.100024 |
container_title |
Maritime Transport Research |
container_volume |
2 |
container_start_page |
100024 |
_version_ |
1766327798461366272 |