Skip to main content

Sensitivity analysis of parameters governing the iceberg draft through neural network-based models


Precise estimation of the iceberg draft may significantly reduce the collision risk of deep keel icebergs with the offshore facilities comprising the submarine pipelines, wellheads, communication cables, and hydrocarbon loading equipment crossing the Arctic shallow waters. As such, in this study, the iceberg drafts were simulated using a self-adaptive machine learning (ML) algorithm entitled self-adaptive extreme learning machine (Sa-ELM) for the first time, to the best of our knowledge. Initially, the parameters governing the iceberg drafts were specified, and then nine Sa-ELM models were defined using these parameters. To test and train the Sa-ELM models, a comprehensive dataset was constructed, where 60% of the dataset was utilized for model training and 40% for model validation. In addition, several hyper parameters have been optimized during the training procedure to obtain the most accurate results. The superior Sa-ELM model and the most influencing input parameters were determined by conducting a sensitivity analysis. The comparison of the premium Sa-ELM model with the artificial neural network (ANN) and extreme learning machine (ELM) models demonstrated that the Sa-ELM model had the highest level of accuracy and correlation as well as the lowest degree of complexity. Ultimately, a Sa-ELM-based equation was presented to estimate the iceberg draft in practical applications.

Graphical abstract

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10


  • Allaire PE (1972) Stability of simply shaped icebergs. J Can Petrol Technol 11:04

    Article  Google Scholar 

  • Azimi H, Shiri H (2020a) Ice-seabed interaction analysis in sand using a gene expression programming-based approach. Appl Ocean Res 98:102120

    Article  Google Scholar 

  • Azimi H, Shiri H (2020b) Dimensionless groups of parameters governing the ice-seabed interaction process. J Offshore Mech Arctic Eng 142(5):051601

    Article  Google Scholar 

  • Azimi H, Shiri H (2021a) Evaluation of ice-seabed interaction mechanism in sand by using self-adaptive evolutionary extreme learning machine. Ocean Eng 239:109795

    Article  Google Scholar 

  • Azimi H, Shiri H (2021b) Assessment of ice-seabed interaction process in clay using extreme learning machine. Inter J Offshore Polar Eng 31(04):411–420

    Article  Google Scholar 

  • Azimi H, Bonakdari H, Ebtehaj I, Gharabaghi B, Khoshbin F (2018) Evolutionary design of generalized group method of data handling-type neural network for estimating the hydraulic jump roller length. Acta Mech 229(3):1197–1214

    Article  Google Scholar 

  • Azimi H, Shiri H, Zendehboudi S (2022) Ice-seabed interaction modeling in clay by using evolutionary design of generalized group method of data handling. Cold Reg Sci Technol 193:103426

    Article  Google Scholar 

  • Azimi H, Shiri H, Zendehboudi S (2023) Prediction of ice-induced subgouge soil deformation in sand using group method of data handling–based neural network. J Cold Reg Eng 37(2):04023006

    Article  Google Scholar 

  • Barker A, Sayed M, Carrieres T (2004) Determination of iceberg draft, mass and cross-sectional areas. 14th Int Offshore Polar Eng Conf. Toulon, France, May 23–28, ISOPE-I-04-116

  • Bass DW (1980) Stability of icebergs. Ann Glaciol 1:43–47

    Article  Google Scholar 

  • Bilhan O, Emiroglu ME, Kisi O (2010) Application of two different neural network techniques to lateral outflow over rectangular side weirs located on a straight channel. Adv Eng Soft 41(6):831–837

    Article  MATH  Google Scholar 

  • Brooks LD (1980) Another hypothesis about iceberg draft. 5th Int Conf Port Ocean Eng under Arc Cond. Jun, Trondheim, Norway, 241–252

  • C-CORE (2001) Documentation of iceberg grounding events from the 2000 season. C-CORE publication 01-C10 (Revision 0). Report submitted to the Geological Survey of Canada, Atlantic

  • Coast Guard (1991) Report of the International Ice Patrol in the North Atlantic. Bulletin 77

  • Dowdeswell JA, Bamber JL (2007) Keel depths of modern Antarctic icebergs and implications for sea-floor scouring in the geological record. Marine Geolog 243(1–4):120–131

    Article  Google Scholar 

  • Ebtehaj I, Bonakdari H, Zaji AH, Azimi H, Khoshbin F (2015) GMDH-type neural network approach for modeling the discharge coefficient of rectangular sharpcrested side weirs. Eng Sci Technol Int J 18(4):746–757

    Google Scholar 

  • El-Tahan M, El-Tahan H, Courage D, Mitten P (1985) Documentation of iceberg groundings. Environ Stud Res Funds. Report ESRF Vol. 7.

  • Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Machine Lear Res 3:1157–1182

    MATH  Google Scholar 

  • Hertz JA (2018) Introduction to the Theory of Neural Computation. CRC Press

    Book  Google Scholar 

  • Hotzel IS, Miller JD (1983) Icebergs: their physical dimensions and the presentation and application of measured data. Annal Glaciol 4:116–123

    Article  Google Scholar 

  • Huang GB, Zhu QY, Siew CK (2004) Extreme learning machine: a new learning scheme of feedforward neural networks. In 2004 IEEE Inter joint Conf on Neural Net, Budapest, Hungary, July 25–29 2: 985–990

  • King T, Younan A, Richard M, Bruce J, Fuglem M, Phillips R (2016) Subsea risk update using high resolution iceberg profiles. OTC Arctic Technol Conf, St. John's, NL, Canada, October 24–26, OTC-27358-MS

  • King T (2012) Iceberg interaction frequency model for subsea structures. OTC Arctic Technol Conf,Houston, Texas, USA, December 3–5, OTC-23787-MS

  • Liang B (2001) Iceberg stability and deterioration. Doctoral dissertation, Memorial University of Newfoundland

  • Løset S, Carstens T (1996) Sea ice and iceberg observations in the western Barents Sea in 1987. Cold Reg Sci Technol 24(4):323–340

    Article  Google Scholar 

  • Ma L, Resvanis TL, Vandiver JK (2020) Using machine learning to identify important parameters for flow-induced vibration. 39th Inter Conf Ocean, Offshore Arctic Eng, Virtual Conference, August 3–7, 84355:V004T04A011

  • Mahdianpari M, Homayouni S, Foucher S (2021) CJRS’ special issue on deep learning for environmental applications of remote sensing data. Can J Remote Sens 47(2):159–161

    Article  Google Scholar 

  • McGuire P, Younan A, Wang Y, Bruce J, Gandi M, King T, Regular K (2016) Smart iceberg management system–rapid iceberg profiling system. OTC Arctic Technol Conf, St. John's, Newfoundland and Labrador, Canada, October 24–26, OTC-27473-MS

  • McKenna R, King T (2009) Modelling iceberg shape, mass and draft changes. In: Proceedings of the Inter Conf on Port and Ocean Eng Under Arctic Cond, Luleå, Sweden, June 9–12, No. POAC09–107

  • McKenna R, King T, Crocker G, Bruneau S, German P (2019) Modelling iceberg grounding on the grand banks. In: Proceedings of the Inter Conf on Port and Ocean Eng under Arctic Cond, Delft, The Netherlands, June 9–13, pp. 9–19

  • McKenna R (2004) Development of iceberg shape characterization for risk to Grand Banks installations. PERD/CHC Report, 20473

  • Mognor K, Zorn R (1979) Discussion of another hypothesis about iceberg draft. 3rd Inter Conf on Port and Ocean Eng Under Arctic Cond, POAC, Fairbanks, Alaska, USA, August 11–15

  • Robe RQ, Farmer LD (1976) Physical properties of icebergs. Part I. height to draft ratios of icebergs. Part II. mass estimation of Arctic icebergs. Coast Guard Research and Development Center Groton Conn

  • Rudkin P (2014) Comprehensive iceberg management database report 2005 update. PERD/CHC Report 20–72. National Research Council of Canada (NRC) and Panel on Energy Research and Development (PERD), 2005, (March 2005)

  • Sacchetti F, Benetti S, Cofaigh CÓ, Georgiopoulou A (2012) Geophysical evidence of deep-keeled icebergs on the Rockall Bank, Northeast Atlantic Ocean. Geomor 159:63–72

    Article  Google Scholar 

  • Sattar A, Ertuğrul ÖF, Gharabaghi B, McBean EA, Cao J (2019) Extreme learning machine model for water network management. Neural Comput Appl 31(1):157–169

    Article  Google Scholar 

  • Schulman PR (2022) Reliability, uncertainty and the management of error: new perspectives in the COVID-19 era. J Contingen Crisis Manag 30(1):92–101

    Article  Google Scholar 

  • Sen D (2014) The uncertainty relations in quantum mechanics. Curr Sci 2:203–218

    Google Scholar 

  • Shahin MA, Jaksa MB, Maier HR (2001) Artificial neural network applications in geotechnical engineering. Aust Geomech 36(1):49–62

    Google Scholar 

  • Shipilova O, Olsson A (2022) Thomson M (2022) On the shape factor in iceberg deterioration by forced convection. Cold Reg Sci Technol 195:103472

    Article  Google Scholar 

  • Sonnichsen G, Hundert T, Myers R, Pocklington P (2006) Documentation of recent iceberg grounding evens and a comparison with older events of know age. Environ Stud Res Funds. Report ESRF Vol. 157

  • Storn R, Price K (1997) Differential evolution–a simple and efficient heuristic for global optimization over continuous spaces. J Glob Opt 11(4):341–359

    Article  MathSciNet  MATH  Google Scholar 

  • Stuckey P, Fuglem M, Younan A, Shayanfar H, Huang Y, Liu L, King T (2021) Iceberg load software update using 2019 iceberg profile dataset. 40th Inter Conf on Ocean, Offshore and Arctic Eng, Virtual Conference, June 21–30, 85178: V007T07A018

  • Stuckey PD (2008) Drift speed distribution of icebergs on the grand banks and influence on design loads. Doctoral dissertation, Memorial University of Newfoundland

  • Talimi V, Ni S, Qiu W, Fuglem M, MacNeill A, Younan A (2016) Investigation of iceberg hydrodynamics. OTC Arctic Technol Conf, St. John's, Newfoundland and Labrador, Canada, October 24–26, OTC-27493-MS

  • Turnbull ID, Fournier N, Stolwijk M, Fosnaes T, McGonigal D (2015) Operational iceberg drift forecasting in Northwest Greenland. Cold Reg Sci Technol 110:1–18

    Article  Google Scholar 

  • Turnbull ID, King T, Ralph F (2018) Development of a new operational iceberg drift forecast model for the Grand Banks of Newfoundland. OTC Arctic Technol Conf, Houston, Texas, USA, November 5–7, OTC-29109-MS

  • Walton R, Binns A, Bonakdari H, Ebtehaj I, Gharabaghi B (2019) Estimating 2-year flood flows using the generalized structure of the group method of data handling. J Hydrol 575:671–689

    Article  Google Scholar 

  • Woodworth-Lynas CMT, Simms A, Rendell CM (1985) Iceberg grounding and scouring on the labrador continental Shelf. Cold Reg Sci Technol 10(2):163–186

    Article  Google Scholar 

  • Younan A, Ralph F, Ralph T, Bruce J (2016) Overview of the 2012 iceberg profiling program. OTC Arctic Technol Conf.St. John's, Newfoundland and Labrador, Canada, October 24–26, OTC-27469-MS

  • Zhou M (2017) Underwater iceberg profiling and motion estimation using autonomous underwater vehicles. Doctoral dissertation, Memorial University of Newfoundland

Download references


The authors gratefully acknowledge the financial support of “Wood Group,” which established a Research Chair program in Arctic and Harsh Environment Engineering at the Memorial University of Newfoundland, the “Natural Science and Engineering Research Council of Canada (NSERC)”, and the “Newfoundland Research and Development Corporation (RDC) (now TCII)” through “Collaborative Research and Developments Grants (CRD)”. Special thanks are extended to Memorial University for providing excellent resources to conduct this research.


This declaration is not applicable.

Author information

Authors and Affiliations



HA: simulation, analysis, writing; HS: conceptualization, funding, revision; MM: conceptualization, revision.

Corresponding author

Correspondence to Hamed Azimi.

Ethics declarations

Conflict of interest

The authors do not have any conflicts of interest to disclose.

Ethical approval

This declaration is not applicable.

Availability of data and materials

The data will be provided upon reasonable request.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 1988 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Azimi, H., Shiri, H. & Mahdianpari, M. Sensitivity analysis of parameters governing the iceberg draft through neural network-based models. J. Ocean Eng. Mar. Energy 9, 587–602 (2023).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: