Mitchell, Ria L., Holwell, Andy, Torelli, Giacomo, Provis, John, Selvaranjan, Kajanan, Geddes, Dan, Yorkshire, Antonia, and Kearney, Sarah
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 and machine‐learning‐based reconstruction approaches to cements and concretes to assist with image improvement, faster throughput of samples, upscaling of data, and quantitative phase identification in 3D. We show that by applying advanced machine learning reconstruction approaches, it is possible to (i) vastly improve the scan quality and increase throughput of 'thick' cores of cements/concretes through enhanced contrast and denoising using DeepRecon Pro, (ii) upscale data to larger fields of view using DeepScout and (iii) use quantitative automated mineralogy to spatially characterise and quantify the mineralogical/phase components in 3D using Mineralogic 3D. These approaches significantly improve the quality of collected XRM data, resolve features not previously accessible, and streamline scanning and reconstruction processes for greater throughput. LAY DESCRIPTION: 3D imaging via X‐ray microscopy (XRM), a form of tomography, is revolutionising the understanding of various human‐made materials. It provides non‐destructive imaging to classify grains, particles, interfaces and pores at various resolutions. It is particularly important for our understanding of the composition, structure, and failure of building materials such as cements and concretes. 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, high density and/or the resolution they need to be imaged at. Modern advances include deep/machine learning and AI, which could help with this problem, which are able to pick out image artefacts during data reconstruction, provide advanced denoising, improved quantification of features, upscaling of data/images, and increased sample throughput. All of these improvements enhance data leading to better characterisation and interpretation of samples, and to spot aspects of failure. Here, we apply three AI and machine‐learning‐based reconstruction approaches to cements and concretes to assist with image improvement, faster throughput of samples, upscaling of data, and quantitative phase identification in 3D. We show that by applying advanced machine learning reconstruction approaches, it is possible to (i) vastly improve the scan quality and increase throughput of 'thick' cores of cements/concretes through enhanced contrast and denoising using DeepRecon Pro, (ii) upscale data to larger fields of view using DeepScout and (iii) use quantitative automated mineralogy to characterise and quantify the mineralogical/phase components in 3D using Mineralogic 3D. These approaches significantly improve the quality of collected XRM data for cements and concretes, resolve features not previously seen, and streamline scanning and reconstruction processes so more samples can be scanned. [ABSTRACT FROM AUTHOR]