Predicting vessel speed in the Arctic without knowing ice conditions using AIS data and decision trees

Adamovich, 1995, The empiric model of vessel movement in ice and generalization of the experience of the model usage in hydrometeorological support of shipping in the Arctic, 2, 30 Afonin, 2018, 2018. Study of ship speed regimes in the Arctic sea ice conditions, IOP Conf. Ser. Earth Environ. Sci., 194, 10.1088/1755-1315/194/7/072012 Andersen, 2021, Scheduling ships with uncertain arrival times through the Kiel Canal, Marit.Transp. Res., 2 Bergström, 2016, A simulation-based probabilistic design method for Arctic sea transport systems, J. Mar. Sci. Appl., 15, 349, 10.1007/s11804-016-1379-1 Breiman, 2001, Random forests, Mach. Learn., 45, 5, 10.1023/A:1010933404324 Breiman, 1984 Chen, 2016, Xgboost: a scalable tree boosting system, 785 dateandtime.info, 2020. Retrieved June 3 from https://dateandtime.info/city.php?id=1538111. Department of Navigation and Oceanography of the Ministry of Defense of the Russian Federation, 1995. Руководство для сквозного плавания судов по Северному морскому пути. – С.П-б: Изд. ГУНИО МО РФ, 415 с. (In Russian). Dumanskaya, 2013, Типовые условия на основных судоходных трассах морей европейской части России для зим различной суровости, Тр. Гидрометцентра РФ., 2013350, 142 Erceg, 2014, A numerical model to initiate the icebreaking pattern in level ice Fagerholt, 2010, Reducing fuel emissions by optimizing speed on shipping routes, J. Oper. Res. Soc., 61, 523, 10.1057/jors.2009.77 Frederking, 2003, A model for ship routing in ice, 467 Jeong, 2017, Prediction of ship resistance in level ice based on empirical approach, Int. J. Nav. Arch. Ocean, 9, 613, 10.1016/j.ijnaoe.2017.03.007 Ke, 2017, LightGBM: a highly efficient gradient boosting decision tree Kim, 2020, Predicting ship speeds in the Arctic using deep learning on historical AIS data Kotovirta, 2009, A system for route optimization in ice-covered waters, Cold Reg. Sci. Technol., 55, 52, 10.1016/j.coldregions.2008.07.003 Kuuliala, 2017, Estimating operability of ships in ridged ice fields, Cold Reg. Sci. Technol., 135, 51, 10.1016/j.coldregions.2016.12.003 Lau, 2006, Discrete element modeling of ship manoeuvring in ice Lensu, 2015, Assessing the Ice Performance of Ships in Terms of AIS Data, Proceedings of the International Conference on Port and Ocean Engineering Under Arctic Conditions Li, 2018, Evaluation of selected state-of-the-art methods for ship transit simulation in various ice conditions based on full-scale measurement, Cold Regions Science and Technology, 151, 94, 10.1016/j.coldregions.2018.03.008 Li, 2019, An extended ice failure model to improve the fidelity of icebreaking pattern in numerical simulation of ship performance in level ice, Ocean Eng., 176, 169, 10.1016/j.oceaneng.2019.02.051 Lindqvist, 1989, A straightforward method for calculation of ice resistance of ships Louppe, 2014 Löptien, 2014, Ice and AIS: ship speed data and sea ice forecasts in the Baltic Sea, Cryosphere, 8, 2409, 10.5194/tc-8-2409-2014 Lubbad, 2011, A numerical model for real-time simulation of ship–ice interaction, Cold Reg. Sci. Technol., 65, 111, 10.1016/j.coldregions.2010.09.004 Milaković, 2020, A machine learning-based method for simulation of ship speed profile in a complex ice field, Ships and Offshore Structures, 15, 974, 10.1080/17445302.2019.1697075 Montewka, 2015, Towards probabilistic models for the prediction of a ship performance in dynamic ice, Cold Reg. Sci. Technol., 112, 14, 10.1016/j.coldregions.2014.12.009 Montewka, 2019, Toward a hybrid model of ship performance in ice suitable for route planning purpose, Proc. Inst. Mech. Eng. O J. Risk Reliab., 233, 18 Montewka, 2013, Modelling ship performance in ice using Bayesian networks Ng, 2019, Vessel speed optimization in container shipping: a new look, J. Oper. Res. Soc., 70, 541, 10.1080/01605682.2018.1447253 Ol'khovik, E.O., 2018. Исследование влияния мелководья на изменение скоростных режимов судов в акватории Северного морского пути. Вестник Государственного университета морского и речного флота имени адмирала С. О. Макарова. 10 (3), 486–496. (In Russian). Ol'khovik, 2019, Study of changes of vessel's speed in ice conditions on the Northern Sea route Pedregosa, 2011, Scikit-learn: machine learning in Python, JMLR, 12, 2825 Quinlan, 1986, Induction of decision trees, Mach. Learn., 1, 81, 10.1007/BF00116251 Riska, 1997 Sawamura, 2008, Finite element analysis of fluid–ice interaction during ice bending, 191 SCF Newsletter, 2019. Корпоративное издание группы СКФ December 05 (65). (In Russian). Shukurov, 2018, A link between sea ice concentration in Kara Sea in November and large-scale atmospheric circulation, v10833 Shumovsky, S.A. 2012. О диких проблемах с которыми сталкнется ЯМАЛ-СПГ при вывозе продукции. Профессионально об энергетике. (In Russian). Similä, 2018, Estimating the speed of ice-going ships by integrating SAR imagery and ship data from an Automatic identification system, Remote Sens., 10, 1132, 10.3390/rs10071132 Su, 2010, A numerical method for the prediction of ship performance in level ice, Cold Reg. Sci. Technol., 60, 177, 10.1016/j.coldregions.2009.11.006 Topaj, 2019, Optimal ice routing of a ship with icebreaker assistance, Applied Ocean Research, 86, 177, 10.1016/j.apor.2019.02.021 Valanto, 2001, The resistance of ships in level ice, SNAME Trans., 109, 53 Valkonen, 2013, COSSARC – concept selection for shipping in the arctic von Westarp, 2021, Support of the speed decision in liner operation by evaluating the trade-off between bunker fuel consumption and reliability, Marit. Transp. Res., 2 Wang, 2001 Wetzel, 2020, Integrating fleet deployment into liner shipping vessel repositioning, Transp. Res. Part E Logist. Transp. Rev., 143, 10.1016/j.tre.2020.102101 Zhou, 2016, Numerical investigations of ship–ice interaction and maneuvering performance in level ice, Cold Reg. Sci. Technol., 122, 36, 10.1016/j.coldregions.2015.10.015 Zivot, 2006, Vector Autoregressive Models for Multivariate Time Series, 385