Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion

Kench, Steve; Cooper, Samuel J.

doi:10.1038/s42256-021-00322-1

Cited by 170 publications

(129 citation statements)

References 19 publications

Supporting

Mentioning

128

Contrasting

Order By: Relevance

“…Despite that the ARTISTIC website contains already in house experimental data, the main limitation of this modeling approach is the difficulty of systematic 3D‐resolved validations with respect to experimental microstructures. This would require large datasets constituted of series of electrode microstructures obtained by imaging techniques, such as X‐ray computed tomography or FIB‐SEM, [28–32] associated with specific manufacturing conditions and distinguishing between AM, CBD, and pore phases through appropriate segmentation approaches. Building such a dataset and sharing it with the battery community could be a major help for the development of procedures to consistently validate the electrode microstructures obtained by the models presented here, as well as other computational approaches that start to emerge in the literature [33–38] .…”

Section: The Artistic Manufacturing Modelsmentioning

confidence: 99%

The ARTISTIC Online Calculator: Exploring the Impact of Lithium‐Ion Battery Electrode Manufacturing Parameters Interactively Through Your Browser

Lombardo

Caro

Ngandjong

et al. 2022

Batteries & Supercaps

View full text Add to dashboard Cite

This article presents the ARTISTIC online calculator, a web platform that enables both experimental and computational researchers to access the ARTISTIC project three‐dimensional (3D) manufacturing models. This platform is free of charge and utilizes a user‐friendly interface to guide users among the different manufacturing steps and their parameters. The current version of the online calculator accounts for the slurry phase, its drying, and electrode calendering; it gives access to a variety of relevant parameters, as slurry solid content, electrode formulation, particle size distribution, and drying/calendering conditions. To utilize this platform, the user should simply register freely to the ARTISTIC computational portal, select the manufacturing parameters of interest, and launch the simulations through the user‐friendly interface. As soon as the simulation ends, the user who launched it receives an email with the links to visualize and recover the resulting electrode/slurry microstructure. Furthermore, all the results obtained through this platform are shared among all the users, i. e., everyone can visualize and recover all the microstructures available. Therefore, this platform also constitutes an open‐access database linking manufacturing conditions and simulated electrode microstructures. In addition, these microstructures can be embedded straightforwardly in electrochemical models. In brief, we hope that the battery community will see this online platform as a tool to explore the vast manufacturing parameter space accessible through our 3D models and to establish a deeper knowledge of the manufacturing‐microstructure‐electrochemistry relationships in a collaborative and fully transparent way.

show abstract

Section: The Artistic Manufacturing Modelsmentioning

confidence: 99%

The ARTISTIC Online Calculator: Exploring the Impact of Lithium‐Ion Battery Electrode Manufacturing Parameters Interactively Through Your Browser

Lombardo

Caro

Ngandjong

et al. 2022

Batteries & Supercaps

View full text Add to dashboard Cite

show abstract

“…This would also become easier if one were to create 3D images with FIB-SEM serial sectioning, since the additional deposition steps at each FIB slice would sequentially fill in the pores more. However gests that capturing a large, high quality 2D image may be more valuable than a 3D volume with the equivalent number of pixels, as the 2D image will contain more information and can then be used to generate more representative 3D volumes [13]. Some of the NMC particles contained features that are slightly darker than the surrounding NMC and only a few pixels across, as can be seen in Fig.…”

Section: Almentioning

confidence: 99%

Kintsugi Imaging of Battery Electrodes: Unambiguously Distinguishing Pores from the Carbon Binder Domain using Pt Deposition

Cooper¹,

Roberts²,

Zhao³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The mesostructure of porous electrodes used in lithium-ion batteries strongly influences cell performance. Accurate imaging of the distribution of phases in these electrodes would allow this relationship to be better understood through simulation. However, imaging the nanoscale features in these components is challenging. While scanning electron microscopy is able to achieve the required resolution, it has well established difficulties imaging porous media. This because the flat imaging planes prepared using focused ion beam milling will intersect with the pores, which makes the images hard to interpret as the inside walls of the pores are observed. It is common to infiltrate porous media with resin prior to imaging to help resolve this issue, but both the nanoscale porosity and the chemical similarity of the resins to the battery materials undermine the utility of this approach for most electrodes. In this study, a new technique is demonstrated which uses \textit{in situ} infiltration of platinum to fill the pores and thus enhance their contrast during imaging. Reminiscent of the Japanese art of repairing cracked ceramics with precious metals, this technique is referred to as the \textit{kintsugi} method. The images resulting from applying this technique to a conventional porous cathode are presented and then segmented using a multi-channel convolutional method. We show that while some cracks in active material particles were filled with the carbon binder phase, others remained empty, which will have implications for the rate performance of the cell. Energy dispersive X-ray spectroscopy was used to validate the distribution of phases resulting from image analysis, which also suggested a graded distribution of the binder relative to the carbon addative. The equipment required to use the kintsugi method is commonly available in major research facilities and so we hope that this method will be rapidly adopted to improve the imaging of electrode materials and porous media in general.

show abstract

“…On top of GANs, Shams et al (2020) integrated it with auto-encoder networks to produce sandstone samples with multiscale pores, enabling GANs to predict inter-grain pores while auto-encoder networks provide GANs with intragrain pores. Some other representative applications also exist, such as adopting GANs to reconstruct shale digital cores (Zha et al 2020), utilizing GANs to augment resolution and recover the texture of micro-CT images of rocks (Wang et al 2019(Wang et al , 2020, and reconstructing three-dimension structures from two-dimension slices with GANs (Feng et al 2020;Kench and Cooper 2021;You et al 2021).…”

Section: Introductionmentioning

confidence: 99%

Digital Rock Reconstruction with User-Defined Properties Using Conditional Generative Adversarial Networks

Zheng

Zhang

2022

Transp Porous Med

View full text Add to dashboard Cite

Uncertainty is ubiquitous with multiphase flow in subsurface rocks due to their inherent heterogeneity and lack of in-situ measurements. To complete uncertainty analysis in a multi-scale manner, it is a prerequisite to provide sufficient rock samples. Even though the advent of digital rock technology offers opportunities to reproduce rocks, it still cannot be utilized to provide massive samples due to its high cost, thus leading to the development of diversified mathematical methods. Among them, two-point statistics (TPS) and multi-point statistics (MPS) are commonly utilized, which feature incorporating low-order and high-order statistical information, respectively. Recently, generative adversarial networks (GANs) are becoming increasingly popular since they can reproduce training images with excellent visual and consequent geologic realism. However, standard GANs can only incorporate information from data, while leaving no interface for user-defined properties, and thus may limit the representativeness of reconstructed samples. In this study, we propose conditional GANs for digital rock reconstruction, aiming to reproduce samples not only similar to the real training data, but also satisfying user-specified properties. In fact, the proposed framework can realize the targets of MPS and TPS simultaneously by incorporating high-order information directly from rock images with the GANs scheme, while preserving low-order counterparts through conditioning. We conduct three reconstruction experiments, and the results demonstrate that rock type, rock porosity, and correlation length can be successfully conditioned to affect the reconstructed rock images. The randomly reconstructed samples with specified rock type, porosity and correlation length will contribute to the subsequent research on pore-scale multiphase flow and uncertainty quantification.

show abstract

Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion

Cited by 170 publications

References 19 publications

The ARTISTIC Online Calculator: Exploring the Impact of Lithium‐Ion Battery Electrode Manufacturing Parameters Interactively Through Your Browser

The ARTISTIC Online Calculator: Exploring the Impact of Lithium‐Ion Battery Electrode Manufacturing Parameters Interactively Through Your Browser

Kintsugi Imaging of Battery Electrodes: Unambiguously Distinguishing Pores from the Carbon Binder Domain using Pt Deposition

Digital Rock Reconstruction with User-Defined Properties Using Conditional Generative Adversarial Networks

Contact Info

Product

Resources

About