elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Predicting compressive strength and behavior of ice and analyzing feature importance with explainable machine learning models

Kellner, Leon and Stender, Merten and von Bock und Polach, Franz and Ehlers, Sören (2022) Predicting compressive strength and behavior of ice and analyzing feature importance with explainable machine learning models. Ocean Engineering, 255. Elsevier. doi: 10.1016/j.oceaneng.2022.111396. ISSN 0029-8018.

Full text not available from this repository.

Official URL: https://www.sciencedirect.com/science/article/abs/pii/S0029801822007806?via%3Dihub

Abstract

Building and using ice-related models is challenging due to the complexity of the material. A common issue, shared by both material models and (semi-)empirical approaches, is estimating unknown input parameters such as compressive strength. This is often done with additional empirical formulas which have drawbacks, e.g., they are based on a limited amount of data. Regarding material modeling, a strongly related problem is the prioritization of effects to include in the model. This is mostly done based on a subjective mix of knowledge, model purpose, and experimental studies limited to that purpose, which risks overlooking effects or interaction of effects, and limits transferability of material models to other scenarios. To tackle these issues, a hybrid approach of domain knowledge and explainable machine learning was used. A large ice test database was compiled to train machine learning models to predict compressive strength and behavior type. The machine learning models’ predictions were more accurate than existing empirical or analytical approaches and can thus be used as an alternative, though less straightforward, tool for such predictions. Further, the SHAP explainable AI method was applied to the predictions. Impact rankings of experimental parameters and interaction effects between parameters were analyzed and discussed in terms of ice mechanics. Top features were strain rate, triaxial stress state, temperature, and loading direction, but impact rankings were highly dependent on prediction target and type of ice. Few interaction effects were found. The approach adds objectivity to the prioritization of effects for material modeling and generated further insights into ice mechanics. It is also considered useful for other natural materials or generally when there is more data than knowledge.

Item URL in elib:https://elib.dlr.de/187547/
Document Type:Article
Title:Predicting compressive strength and behavior of ice and analyzing feature importance with explainable machine learning models
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Kellner, LeonHamburg University of Technology Hamburg, GermanyUNSPECIFIEDUNSPECIFIED
Stender, MertenHamburg University of Technology Hamburg, GermanyUNSPECIFIEDUNSPECIFIED
von Bock und Polach, FranzHamburg University of Technology Hamburg, GermanyUNSPECIFIEDUNSPECIFIED
Ehlers, SörenUNSPECIFIEDhttps://orcid.org/0000-0001-5698-9354UNSPECIFIED
Date:1 July 2022
Journal or Publication Title:Ocean Engineering
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:255
DOI:10.1016/j.oceaneng.2022.111396
Publisher:Elsevier
ISSN:0029-8018
Status:Published
Keywords:Ice mechanics Ice compressive strength Material modeling Ductile Brittle Machine learning Explainable AI
HGF - Research field:Energy
HGF - Program:other
HGF - Program Themes:E - no assignment
DLR - Research area:Energy
DLR - Program:E - no assignment
DLR - Research theme (Project):E - no assignment
Location: Geesthacht
Institutes and Institutions:Institute of Maritime Energy Systems
Deposited By: Piazza, Hilke Charlotte
Deposited On:17 Oct 2022 07:19
Last Modified:02 Dec 2022 09:21

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.