Skip to main content
ConductScienceScienceDex
zenodoopen

MicrographBank: Interfacial Intermetallics

<p><em>A high-throughput synthetic dataset of heterogeneous microstructure morphologies generated via multi-phase-field simulations and machine learning analysis</em></p> <p><strong>Description:</strong></p> <p>This <span><strong>Interfacial Microstructure Atlas</strong></span> is a curated dataset consisting of <em>1672x25 or 41800</em> <span><strong>microstructure images</strong></span> derived from multi-phase-field simulations designed to explore the effects of uncertain interfacial energies on intermetallic compound (IMC) morphologies. Developed within the framework of Integrated Computational Materials Engineering (ICME), this dataset systematically samples the <span><strong>3D interface energy space</strong></span> (&sigma;SI, &sigma;SL, &sigma;IL) using Sobol sequences and captures the transient evolution of the Cu6Sn5 phase during heterogeneous solidification in Cu/Sn systems.</p> <p>Each image encodes the phase-field order parameter of the IMC and has been analyzed using <span><strong>Fourier Descriptors</strong></span>, <span><strong>semi-supervised learning (label spreading)</strong></span>, and <span><strong>variational autoencoders (VAE)</strong></span> to classify the shapes into <span><strong>wetting</strong></span>, <span><strong>invariant</strong></span>, and <span><strong>dewetting</strong></span> regimes. The dataset enables studies on:</p> <ul> <li>Microstructure classification</li> <li>Uncertainty propagation in PDE-based models</li> <li>Process-Structure-Property (PSP) linkages</li> <li>Deep learning applications in synthetic materials data</li> </ul> <p>&nbsp;</p> <p><strong>Key Features:</strong></p> <ul> <li>1,672 phase-field simulations with distinct interfacial energy parameters, <em>1672 x 25 or 41800</em> <span><strong>microstructure images</strong></span></li> <li>388&times;343 px&sup2; raw images, preprocessed to 64&times;64 px&sup2;</li> <li>Corresponding Fourier Descriptors and interface energy labels</li> <li>Label spreading&ndash;based shape classification and VAE latent embeddings</li> </ul> <p>&nbsp;</p> <p>The data was interpreted in the following article:</p> <p><a href="https://materialstheory.springeropen.com/articles/10.1186/s41313-021-00038-0">Machine Learning-Assisted High-Throughput Exploration of Interface Energy Space in Multi-Phase-FieldModel with CALPHAD potential</a></p> <p>Vahid Attari, Raymundo Arroyave</p> <p>Texas A&amp;M University</p> <p>Link to article:&nbsp;https://doi.org/10.1186/s41313-021-00038-0&nbsp;</p> <p>For more information please refer to Open Phase-field Microstructure Database (OPMD) curated at&nbsp;<a href="https://microstructures.net">https://microstructures.net</a>.&nbsp;</p> <p>&nbsp;</p>

ShareScore

40/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
8
Harmonization
4
Access
16
Reuse readiness
8
Engagement
4

Topics

Dataset details

Repository
zenodo
Published
July 10, 2021
License
cc-by-4.0
DOI
10.5281/zenodo.5090287

Scored with release 0.9.0

ScienceDex for faculty

Your academic CV and NIH biosketch

Make your CV in your school's format and your NIH biosketch from it, then download both as Word files.