A deep learning approach for complex microstructure inference

Ali Riza Durmaz (), Martin Müller, Bo Lei, Akhil Thomas, Dominik Britz, Elizabeth A. Holm, Chris Eberl, Frank Mücklich and Peter Gumbsch
Additional contact information
Ali Riza Durmaz: Fraunhofer Institute for Mechanics of Materials IWM
Martin Müller: Saarland University
Bo Lei: Carnegie Mellon University
Akhil Thomas: Fraunhofer Institute for Mechanics of Materials IWM
Dominik Britz: Saarland University
Elizabeth A. Holm: Carnegie Mellon University
Chris Eberl: Fraunhofer Institute for Mechanics of Materials IWM
Frank Mücklich: Saarland University
Peter Gumbsch: Fraunhofer Institute for Mechanics of Materials IWM

Nature Communications, 2021, vol. 12, issue 1, 1-15

Abstract: Abstract Automated, reliable, and objective microstructure inference from micrographs is essential for a comprehensive understanding of process-microstructure-property relations and tailored materials development. However, such inference, with the increasing complexity of microstructures, requires advanced segmentation methodologies. While deep learning offers new opportunities, an intuition about the required data quality/quantity and a methodological guideline for microstructure quantification is still missing. This, along with deep learning’s seemingly intransparent decision-making process, hampers its breakthrough in this field. We apply a multidisciplinary deep learning approach, devoting equal attention to specimen preparation and imaging, and train distinct U-Net architectures with 30–50 micrographs of different imaging modalities and electron backscatter diffraction-informed annotations. On the challenging task of lath-bainite segmentation in complex-phase steel, we achieve accuracies of 90% rivaling expert segmentations. Further, we discuss the impact of image context, pre-training with domain-extrinsic data, and data augmentation. Network visualization techniques demonstrate plausible model decisions based on grain boundary morphology.

Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-021-26565-5 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:12:y:2021:i:1:d:10.1038_s41467-021-26565-5

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-021-26565-5

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().