Update of the eurotop neural network tool: Improved prediction of wave overtopping

Barbara Zanuttigh; Sara Mizar Formentin; Jentsje W. Van Der Meer

Update of the eurotop neural network tool: Improved prediction of wave overtopping

Barbara Zanuttigh, Sara Mizar Formentin, Jentsje W. Van Der Meer

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

Abstract

The goal of this work is to present a synthesis of the improvements and updates developed to deliver the final version of the ANN tool adopted by the second edition of the wave overtopping manual, EurOtop, released on the internet in 2016. This tool consists of three identical but independent ANNs able to predict the main parameters representative of the wave-structure interaction processes, i.e. The mean wave overtopping discharge, the wave transmission and the wave reflection coefficients. The contribution focuses on the modifications of the ANN architecture carried out since the last ICCE conference to achieve an optimized representation of the wave overtopping, especially in case of low and extreme values of the overtopping discharge. The consistency of the ANN predictions is assessed through an artificial dataset including geometrical and climate input parameters that are varied with continuity, while the robustness of the tool is checked by applying the ANN to selected geometries excluded from the training database.

Original language	English
Title of host publication	Proceedings of the 35th International Conference on Coastal Engineering, ICCE 2016
Editors	P. Lynett
Publisher	American Society of Civil Engineers (ASCE)
Pages	13-29
Volume	35
ISBN (Electronic)	9780989661133
ISBN (Print)	978-1-5108-4408-7
Publication status	Published - 2016
Externally published	Yes
Event	35th International Conference on Coastal Engineering - Antalya, Turkey Duration: 17 Nov 2016 → 20 Nov 2016 Conference number: 35 http://www.icce2016.com/en/

Publication series

Name	Proceedings of the 35th International Conference on Coastal Engineering
Volume	35

Conference

Conference	35th International Conference on Coastal Engineering
Abbreviated title	ICCE 2016
Country/Territory	Turkey
City	Antalya
Period	17/11/16 → 20/11/16
Internet address	http://www.icce2016.com/en/

Keywords

Artificial neural networks
Database
Generalization
Training
Wave overtopping
Wave reflection
Wave transmission

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Cite this

Zanuttigh, B., Formentin, S. M., & Van Der Meer, J. W. (2016). Update of the eurotop neural network tool: Improved prediction of wave overtopping. In P. Lynett (Ed.), Proceedings of the 35th International Conference on Coastal Engineering, ICCE 2016 (Vol. 35, pp. 13-29). (Proceedings of the 35th International Conference on Coastal Engineering; Vol. 35). American Society of Civil Engineers (ASCE).

Zanuttigh, Barbara ; Formentin, Sara Mizar ; Van Der Meer, Jentsje W. / Update of the eurotop neural network tool : Improved prediction of wave overtopping. Proceedings of the 35th International Conference on Coastal Engineering, ICCE 2016. editor / P. Lynett. Vol. 35 American Society of Civil Engineers (ASCE), 2016. pp. 13-29 (Proceedings of the 35th International Conference on Coastal Engineering).

@inproceedings{397c405be36a485b9915e9640b910d08,

title = "Update of the eurotop neural network tool: Improved prediction of wave overtopping",

abstract = "The goal of this work is to present a synthesis of the improvements and updates developed to deliver the final version of the ANN tool adopted by the second edition of the wave overtopping manual, EurOtop, released on the internet in 2016. This tool consists of three identical but independent ANNs able to predict the main parameters representative of the wave-structure interaction processes, i.e. The mean wave overtopping discharge, the wave transmission and the wave reflection coefficients. The contribution focuses on the modifications of the ANN architecture carried out since the last ICCE conference to achieve an optimized representation of the wave overtopping, especially in case of low and extreme values of the overtopping discharge. The consistency of the ANN predictions is assessed through an artificial dataset including geometrical and climate input parameters that are varied with continuity, while the robustness of the tool is checked by applying the ANN to selected geometries excluded from the training database.",

keywords = "Artificial neural networks, Database, Generalization, Training, Wave overtopping, Wave reflection, Wave transmission",

author = "Barbara Zanuttigh and Formentin, {Sara Mizar} and {Van Der Meer}, {Jentsje W.}",

year = "2016",

language = "English",

isbn = "978-1-5108-4408-7",

volume = "35",

series = "Proceedings of the 35th International Conference on Coastal Engineering",

publisher = "American Society of Civil Engineers (ASCE)",

pages = "13--29",

editor = "P. Lynett",

booktitle = "Proceedings of the 35th International Conference on Coastal Engineering, ICCE 2016",

address = "United States",

note = "35th International Conference on Coastal Engineering, ICCE 2016 ; Conference date: 17-11-2016 Through 20-11-2016",

url = "http://www.icce2016.com/en/",

}

Zanuttigh, B, Formentin, SM & Van Der Meer, JW 2016, Update of the eurotop neural network tool: Improved prediction of wave overtopping. in P Lynett (ed.), Proceedings of the 35th International Conference on Coastal Engineering, ICCE 2016. vol. 35, Proceedings of the 35th International Conference on Coastal Engineering, vol. 35, American Society of Civil Engineers (ASCE), pp. 13-29, 35th International Conference on Coastal Engineering, Antalya, Turkey, 17/11/16.

Update of the eurotop neural network tool : Improved prediction of wave overtopping. / Zanuttigh, Barbara; Formentin, Sara Mizar; Van Der Meer, Jentsje W.

Proceedings of the 35th International Conference on Coastal Engineering, ICCE 2016. ed. / P. Lynett. Vol. 35 American Society of Civil Engineers (ASCE), 2016. p. 13-29 (Proceedings of the 35th International Conference on Coastal Engineering; Vol. 35).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Update of the eurotop neural network tool

T2 - 35th International Conference on Coastal Engineering

AU - Zanuttigh, Barbara

AU - Formentin, Sara Mizar

AU - Van Der Meer, Jentsje W.

N1 - Conference code: 35

PY - 2016

Y1 - 2016

N2 - The goal of this work is to present a synthesis of the improvements and updates developed to deliver the final version of the ANN tool adopted by the second edition of the wave overtopping manual, EurOtop, released on the internet in 2016. This tool consists of three identical but independent ANNs able to predict the main parameters representative of the wave-structure interaction processes, i.e. The mean wave overtopping discharge, the wave transmission and the wave reflection coefficients. The contribution focuses on the modifications of the ANN architecture carried out since the last ICCE conference to achieve an optimized representation of the wave overtopping, especially in case of low and extreme values of the overtopping discharge. The consistency of the ANN predictions is assessed through an artificial dataset including geometrical and climate input parameters that are varied with continuity, while the robustness of the tool is checked by applying the ANN to selected geometries excluded from the training database.

AB - The goal of this work is to present a synthesis of the improvements and updates developed to deliver the final version of the ANN tool adopted by the second edition of the wave overtopping manual, EurOtop, released on the internet in 2016. This tool consists of three identical but independent ANNs able to predict the main parameters representative of the wave-structure interaction processes, i.e. The mean wave overtopping discharge, the wave transmission and the wave reflection coefficients. The contribution focuses on the modifications of the ANN architecture carried out since the last ICCE conference to achieve an optimized representation of the wave overtopping, especially in case of low and extreme values of the overtopping discharge. The consistency of the ANN predictions is assessed through an artificial dataset including geometrical and climate input parameters that are varied with continuity, while the robustness of the tool is checked by applying the ANN to selected geometries excluded from the training database.

KW - Artificial neural networks

KW - Database

KW - Generalization

KW - Training

KW - Wave overtopping

KW - Wave reflection

KW - Wave transmission

UR - http://www.scopus.com/inward/record.url?scp=85028650348&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85028650348

SN - 978-1-5108-4408-7

VL - 35

T3 - Proceedings of the 35th International Conference on Coastal Engineering

SP - 13

EP - 29

BT - Proceedings of the 35th International Conference on Coastal Engineering, ICCE 2016

A2 - Lynett, P.

PB - American Society of Civil Engineers (ASCE)

Y2 - 17 November 2016 through 20 November 2016

ER -

Zanuttigh B, Formentin SM, Van Der Meer JW. Update of the eurotop neural network tool: Improved prediction of wave overtopping. In Lynett P, editor, Proceedings of the 35th International Conference on Coastal Engineering, ICCE 2016. Vol. 35. American Society of Civil Engineers (ASCE). 2016. p. 13-29. (Proceedings of the 35th International Conference on Coastal Engineering).

Update of the eurotop neural network tool: Improved prediction of wave overtopping

Abstract

Publication series

Conference

Keywords

UN SDGs

Other files and links

Fingerprint

Cite this