École Polytechnique Fédérale de Lausanne

Deep learning-based surrogate model for generation of wood microstructures

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 imag...

Accelerated carbonation of recycled concrete aggregates: Binding of CO2 and decalcification of calcium-silicate-hydrate

Recycled concrete aggregates (RCA) are a valuable resource for reuse as aggregates in concrete and asphalt. However, the porous mortar adhering to the original aggregates and microcracks both in the mortar and at the interfaces result in increased water absorption and reduced mec...