The study presents a proof-of-concept methodology for characterizing the evolution of internal damage in fresh cement mortar during the hydration process using in-situ time-lapse X-ray micro-computed tomography (μXCT) imaging.
Deep learning-based semantic segmentation models can accurately extract key features of interest, including diamond top, diamond side, and pocket holder, from in-situ images of single crystal diamond growth, enabling automated monitoring and optimization of the growth process.
Deep learning-based algorithms can accurately detect and classify defects in single crystal diamond growth, enabling improved process control and quality.
AlphaCrystal-II, a novel deep learning model, can accurately predict the crystal structure of materials solely from their chemical compositions by exploiting the abundant inter-atomic interaction patterns found in known crystal structures.
A newly developed "metafluid" material exhibits properties that challenge the traditional boundaries between solid, liquid, and gaseous states of matter.
AlloyBERT, a transformer-based model, can accurately predict essential alloy properties like elastic modulus and yield strength using textual descriptions of alloy composition and processing, outperforming traditional shallow machine learning models.
Efficiently homogenizing aerogel-like materials using neural network surrogate models on the microscale.
Kombination von VAE und Regression ermöglicht Vorwärts- und Rückwärtsinferenz für Materialmikrostrukturen.