Dataset for Foundation model for composite microstructures: Reconstruction, stiffness, and nonlinear behavior prediction

This repository contains datasets generated for the publication "Foundation model for composite microstructures: Reconstruction, stiffness, and nonlinear behavior prediction". The datasets are provided to facilitate replication of results, further research, and development in the field of composite materials and machine learning. Contents: downstream_circular_inclusion.zip Description: This dataset consists of microstructure images and associated properties for circular inclusion composites used in the downstream tasks of the study. Structure: train/: Contains training data directories and files. valid/: Contains training data directories and files. descriptors.csv: A CSV file with descriptors and homogenized stiffness components for validation data. downstream_short_fiber.zip Description: This dataset consists of microstructure images and associated properties for short-fiber composites used in the downstream tasks of the study. Structure: train/: Contains training data directories and files. valid/: Contains training data directories and files. descriptors.csv: A CSV file with descriptors and homogenized stiffness components for validation data. inclusion_train_100k.zip Description: This dataset contains 100,000 microstructure images of short-fiber composites used for self-supervised pre-training of the Masked Material Autoencoder (MMAE). Structure: mesh0dir/, mesh1dir/, ... mesh99999dir/: : Folders containing microstructure images used for pre-training. descriptors.csv: A CSV file with descriptors related to the microstructures.