Trustworthy AI-based crack-tip segmentation using domain-guided explanations

Talies, Jesco and Breitbarth, Eric and Melching, David (2026) Trustworthy AI-based crack-tip segmentation using domain-guided explanations. Machine Learning: Science and Technology, 7, 015015. Institute of Physics (IOP) Publishing. doi: 10.1088/2632-2153/ae3660. ISSN 2632-2153.

PDF - Published version
3MB

Item URL in elib:

https://elib.dlr.de/223756/

Document Type:

Article

Title:

Trustworthy AI-based crack-tip segmentation using domain-guided explanations

Authors:

Authors	Institution or Email of Authors	Author's ORCID iD	ORCID Put Code
Talies, Jesco	jesco.talies (at) dlr.de	https://orcid.org/0009-0000-0786-7908	211157056
Breitbarth, Eric	Eric.Breitbarth (at) dlr.de	https://orcid.org/0000-0002-3479-9143	211157057
Melching, David	David.Melching (at) dlr.de	https://orcid.org/0000-0001-5111-6511	UNSPECIFIED

Date:

21 January 2026

Journal or Publication Title:

Machine Learning: Science and Technology

Refereed publication:

Yes

Open Access:

Yes

Gold Open Access:

Yes

In SCOPUS:

Yes

In ISI Web of Science:

Yes

Volume:

DOI:

10.1088/2632-2153/ae3660

Page Range:

015015

Publisher:

Institute of Physics (IOP) Publishing

ISSN:

2632-2153

Status:

Published

Keywords:

deep learning, attention-guided training, explainable AI, quantitative evaluation metrics, domain knowledge, fracture mechanics, digital image correlation

HGF - Research field:

Aeronautics, Space and Transport

HGF - Program:

Aeronautics

HGF - Program Themes:

Components and Systems

DLR - Research area:

Aeronautics

DLR - Program:

L CS - Components and Systems

DLR - Research theme (Project):

L - Structural Materials and Design, D - W2

Location:

Köln-Porz

Institutes and Institutions:

Institute for Frontier Materials on Earth and in Space > Digital Integrated Microstructure and Mechanics

Deposited By:

Melching, David

Deposited On:

09 Apr 2026 10:03

Last Modified:

09 Apr 2026 10:03

Repository Staff Only: item control page