Enhancing machine learning classification of microstructures - A workflow study on joining image data and metadata in CNN

Aug 5, 2026

Upload by Maeve

Data-driven research in materials science increases the need to manage large datasets effectively. FAIR principles place strong emphasis on metadata, motivating a workflow that extracts metadata directly from micrograph image files. The proposed pipeline combines image data with associated metadata for microstructure classification using a deep learning model, benchmarked against a classic machine-learning approach. Results show excellent performance both with and without metadata, supporting further improvements across community use cases.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Abstract

Introduction: motivation

FAIR principles and metadata in data-driven research

CNN-based micrograph analysis in materials science

Microstructure characterization and the need for automated methods

MRS Communications (2024) 14:363–371 © The Author(s), 2024 [https://doi.org/10.1557/s43579-024-00549-0](https://doi.org/10.1557/s43579-024-00549-0) Enhancing machine learning classification of microstructures: A workflow study on joining image data and metadata in CNN Marie Stiefel, Department of Materials Science, Saarland University, 66123 Saarbrücken, Germany Martin Müller, and Björn‑Ivo Bachmann, Department of Materials Science, Saarland University, 66123 Saarbrücken, Germany; Material Engineering Center Saarland, 66123 Saarbrücken, Germany Maria Agustina Guitar, and Ullal Pranav Nayak, Department of Materials Science, Saarland University, 66123 Saarbrücken, Germany Frank Mücklich, Department of Materials Science, Saarland University, 66123 Saarbrücken, Germany; Material Engineering Center Saarland, 66123 Saarbrücken, Germany Address all correspondence to Marie Stiefel at marie.stiefel@uni‑[saarland.de](saarland.de)[ ](saarland.de)(Received 5 January 2024; accepted 21 March 2024; published online: 10 April 2024) Abstract In view of the paradigm shift toward data-driven research in materials science and engineering, handling large amounts of data becomes increasingly important. The application of FAIR (findable, accessible, interoperable, reusable) data principles emphasizes the importance of metadata describing datasets. We propose a novel data processing and machine learning (ML) pipeline to extract metadata from micrograph image files, then combine image data and their metadata for microstructure classification with a deep learning approach compared to a classic ML approach. The ML model attained excellent performances with and without metadata and bears potential for performance improvement of further use cases within the community. Introduction: motivation Research in materials science and engineering (MSE) is subject to a paradigm shift with data-driven science emerging as a new field and big data being the new resource for scientific breakthroughs.[1,2] In order to handle large amounts of data and, more importantly, enabling new discoveries through data exploration, good data management is crucial. [3] In 2016, Wilkinson et al. have proposed the FAIR guiding principles for research data management and stewardship, designed by various stakeholders from academia, industry, publishing, and funding. [3] Since then, the GO FAIR initiative was founded, aiming to implement the FAIR data principles ([go-fair.org](go-fair.org)), and numerous others have decided to lead by example (e.g., FAIRmat[4]) . In order to satisfy the FAIR guidelines, research data must be Findable, Accessible, Interoperable, and Reusable ([go-fair.org/](go-fair.org/)[ ](go-fair.org/)[fair-principles](fair-principles)), as prerequisites for widespread usability in the scientific community. Scheffler et al. reinterpreted the acronym as ‘Findable and AI-ready,’properties of research datasets they deem indispensable for future scientific research, especially regarding their use in AI or machine learning applications. [4] In order for research data to be considered as FAIR, an important property is their richness in metadata, on which the community puts a special focus. [5,6] Metadata provides information on the dataset itself and its main purpose is to facilitate organization and findability of the data, by supplying, e.g. , details on the authors, purpose of the data, or the data acquisition. [7] The thorough collection and usage of metadata aim to increase the reproducibility of research findings, also enabling other researchers within the community to reuse the data and reproduce experiments, which unlocks the potential to greatly ameliorate collaboration within the community as well as to facilitate reviews and verification of research findings in order to ensure high-quality research. [4,7] In addition, with the emergence of artificial intelligence (AI) and machine learning (ML) and the reuse of research data, it is of relevance

FAQs

Why are metadata important for data-driven materials research?

FAIR data principles emphasize metadata to ensure datasets are findable, accessible, interoperable, and reusable, and metadata supports organization, acquisition details, and reproducibility.

What is the main contribution of the proposed workflow?

It extracts metadata from micrograph image files, then integrates image data and metadata for microstructure classification using a deep learning approach.

How does the deep learning approach compare to a classic machine-learning approach?

The deep learning model achieves excellent performance both with and without metadata, and the work benchmarks it against a classic ML approach to demonstrate the value of the workflow.

Aug 5, 2026

Upload by Maeve