Previous research demonstrated that combining scratch testing with image-based techniques is a powerful approach for investigating scratch-induced damage mechanisms in untreated and PEG-impregnated wood.

A machine learning-based surrogate model for efficient wood microstructure generation compatible with a physics-based model is developed. The model is based on the U-Net neural network, a variant of convolutional neural network which, due to its architecture, is suitable for image-to-image…

This research presents an analysis of Transparent Wood (TW), a material currently under development, focusing on its perceptual and sensory aspects, specifically through sight, hearing, and touch. The objective of this study is to examine TW’s current perception to propose clear and effective…

Realistic 3D microstructure models of wood fiber networks (WFNs, e.g., paper, molded fibers, hot-pressed fibers, etc.) are of interest for numerical modeling of mechanical, optical, and other physical properties. One challenge is to numerically describe 3D high-density WFN (HD-WFN) models with…

Accurate characterization of transmittance and haze of transparent composites, such as transparent wood (TW), is challenging due to strong light-scattering effects. Reported TW data in the literature, particularly haze values, show substantial variability, which can be largely attributed to…

Welcome on board! This is the first newsletter of AI-TranspWood project, specifically devoted to a periodical update of the project outcomes, aiming to disseminate them to a wider public. Each newsletter develops a particular topic that will be developed and implemented in the upcoming three-years, providing the readers with fresh and smart information and using a multidisciplinary approach.