About this document

Randomly Generating Realistic Calcareous Sand For Directional Seepage Simulation Using Deep Convolutional Generative Adversarial Networks by shakerxxoo is a document available to read on EtoBox.

This study presents a novel framework using deep convolutional generative adversarial networks (DCGAN) to randomly generate realistic calcareous sand particles for improved seepage simulation. The model was trained on a dataset of 11,625 real particles, resulting in 3,800 generated particles that accurately reflect the morphological characteristics of calcareous sands. The findings indicate that this approach enhances the accuracy of permeability modeling in geotechnical applications involving calcareous sa

Author

shakerxxoo

Language

EN