Cements and concretes materials characterisation using machine-learning-based reconstruction and 3D quantitative mineralogy via X-ray microscopy

Aug 5, 2026

3D imaging via X-ray microscopy (XRM) enables nondestructive characterization of grains, particles, interfaces, and pores across multiple scales, which is critical for understanding the composition, structure, and failure mechanisms of building materials. The work focuses on improving XRM data acquisition and processing for challenging samples, especially those limited by size, density, and required resolution. Three AI and machine-learning reconstruction approaches for cements and concretes are applied to enhance image quality, increase throughput, upscale fields of view, and enable quantitative 3D phase identification.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Abstract

Introduction

3D imaging via X-ray microscopy (XRM)

Importance for cement and concrete characterization

Key approaches and outcomes

DeepRecon Pro: contrast and denoising for thick samples

DeepScout: upscaling to larger fields of view

Mineralogic 3D: quantitative automated mineralogy in 3D

This is a repository copy of Cements and concretes materials characterisation using machine‐learning‐based reconstruction and 3D quantitative mineralogy via X‐ray microscopy. White Rose Research Online URL for this paper: [https://eprints.whiterose.ac.uk/210151/](https://eprints.whiterose.ac.uk/210151/) Version: Published Version Article: Mitchell, R.L., Holwell, A., Torelli, [G. orcid.org/0000-0002-0607-695X et al](G. orcid.org/0000-0002-0607-695X et al). (5 more authors) (2024) Cements and concretes materials characterisation using machine‐ learning‐based reconstruction and 3D quantitative mineralogy via X‐ray microscopy. Journal of Microscopy, 294 (2) . pp. 137-145. ISSN 0022-2720 [https://doi.org/10.1111/jmi.13278](https://doi.org/10.1111/jmi.13278) Reuse This article is distributed under the terms of the Creative Commons Attribution (CC BY) licence. This licence allows you to distribute, remix, tweak, and build upon the work, even commercially, as long as you credit the authors for the original work. More information and the full terms of the licence here: [https://creativecommons.org/licenses/](https://creativecommons.org/licenses/) Takedown If you consider content in White Rose Research Online to be in breach of UK law, please notify us by emailing [eprints@whiterose.ac.uk](eprints@whiterose.ac.uk) including the URL of the record and the reason for the withdrawal request. [eprints@whiterose.ac.uk](eprints@whiterose.ac.uk)[ ](eprints@whiterose.ac.uk)[https://eprints.whiterose.ac.uk/](https://eprints.whiterose.ac.uk/) Received: 29 September 2023 Revised: 30 January 2024 Accepted: 5 February 2024 DOI: 10.1111/jmi.13278 TH EMED ISSUE ARTICLE Cements and concretes materials characterisation using machine-learning-based reconstruction and 3D quantitative mineralogy via X-ray microscopy Ria L. Mitchell1 Andy Holwell1 Giacomo Torelli2 John Provis3,4 Kajanan Selvaranjan2 Dan Geddes3 Antonia Yorkshire3 Sarah Kearney3 1 Carl Zeiss Microscopy, ZEISS House, Cambridge, UK 2 Department of Civil and Structural Engineering, The University of Sheffield, Sheffield, UK 3 Department of Materials Science and Engineering, The University of Sheffield, Sheffield, UK 4 Paul Scherrer Institut, Laboratory for Waste Management (LES), Forschungsstrasse 111, Villigen PSI, Switzerland Correspondence Ria L. Mitchell, Carl Zeiss Microscopy, ZEISS House, 1030 Cambourne Business Park, Cambourne, Cambridge CB23 6DW, UK. Email: [ria.mitchell@zeiss.com](ria.mitchell@zeiss.com) Funding information EPSRC, Grant/Award Numbers: EP/T006390/1, EP/V007025/1; EU Horizon, Grant/Award Number: 101123293; Horizon Europe Guarantee Extension via UKRI, Grant/Award Number: 10089449 Abstract 3D imaging via X-ray microscopy (XRM), a form of tomography, is revolutionising materials characterisation. Nondestructive imaging to classify grains, particles, interfaces and pores at various scales is imperative for our understanding of the composition, structure, and failure of building materials. Various workflows now exist to maximise data collection and to push the boundaries of what has been achieved before, either from singular instruments, software or combinations through multimodal correlative microscopy. An evolving area on interest is the XRM data acquisition and data processing workflow; of particular importance is the improvement of the data acquisition process of samples that are challenging to image, usually because of their size, density (atomic number) and/or the resolution they need to be imaged at. Modern advances include deep/machine learning and AI resolutions for this problem, which address artefact detection during data reconstruction, provide advanced denoising, improved quantification of features, upscaling of data/images, and increased throughput, with the goal to enhance segmentation and visualisation during postprocessing leading to better characterisation of samples. Here, we apply three AI

FAQs

Why is 3D imaging via X-ray microscopy important for cement and concrete studies?

It provides nondestructive visualization of grains, particles, interfaces, and pores in all axes, supporting holistic interpretation of composition, structure, and failure-related transformations.

What challenge motivates the use of AI in the XRM workflow?

Certain cement/concrete samples are difficult to image due to their size, density, and/or the resolution required, creating issues during reconstruction and quantification.

Which AI and software approaches are used and what do they improve?

DeepRecon Pro enhances contrast and denoising for thick cores, DeepScout upscales data to larger fields of view, and Mineralogic 3D enables quantitative automated mineralogy and phase quantification in 3D.

Aug 5, 2026

Upload by Ava Thompson