Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Randomly generating three-dimensional realistic schistous sand particles using deep learning: Variational autoencoder implementation
Abstract Nanjing sand, a type of greenish-grey schistous sand, is rich in weathered mica fragments, making it anisotropic and significantly differ from the round-grained quartz sand in terms of composition, grading, and mechanical properties. In this paper, the variational-autoencoder (VAE), a generative deep-learning model, was used to randomly generate realistic three-dimensional (3D) schistous sand particles. A training set was developed based on a micro-computed tomography scanned image sequence of the specimens of Nanjing sand. A total of 30,000 particles were chosen as the training set. Two thousand realistic 3D schistous sand particles were randomly generated by the trained VAE model and statistically compared with all the natural sand particles. The agreement of the statistical distribution and parameters between the generated and natural schistous sand particles confirmed the generative fidelity of the trained VAE model. Also, the validity and controllability of the generation is testified by the addition of Gaussian random noise and conducting linear interpolation to the latent variables. This methodology not only can be used for the clump template of the DEM, but also holds the potential of generating other geological entities and modeling complicated engineering geological processes.
Highlights The variational autoencoder is used to generate 3D realistic schistous sand particles. The validity and fidelity of the generated particles is verified by statistical comparison. Gaussian random noises and linear interpolation can approach expected micromorphology. Statistical assumption and parameter estimation can be avoided when using the VAE model.
Randomly generating three-dimensional realistic schistous sand particles using deep learning: Variational autoencoder implementation
Abstract Nanjing sand, a type of greenish-grey schistous sand, is rich in weathered mica fragments, making it anisotropic and significantly differ from the round-grained quartz sand in terms of composition, grading, and mechanical properties. In this paper, the variational-autoencoder (VAE), a generative deep-learning model, was used to randomly generate realistic three-dimensional (3D) schistous sand particles. A training set was developed based on a micro-computed tomography scanned image sequence of the specimens of Nanjing sand. A total of 30,000 particles were chosen as the training set. Two thousand realistic 3D schistous sand particles were randomly generated by the trained VAE model and statistically compared with all the natural sand particles. The agreement of the statistical distribution and parameters between the generated and natural schistous sand particles confirmed the generative fidelity of the trained VAE model. Also, the validity and controllability of the generation is testified by the addition of Gaussian random noise and conducting linear interpolation to the latent variables. This methodology not only can be used for the clump template of the DEM, but also holds the potential of generating other geological entities and modeling complicated engineering geological processes.
Highlights The variational autoencoder is used to generate 3D realistic schistous sand particles. The validity and fidelity of the generated particles is verified by statistical comparison. Gaussian random noises and linear interpolation can approach expected micromorphology. Statistical assumption and parameter estimation can be avoided when using the VAE model.
Randomly generating three-dimensional realistic schistous sand particles using deep learning: Variational autoencoder implementation
Shi, Jia-jie (Autor:in) / Zhang, Wei (Autor:in) / Wang, Wei (Autor:in) / Sun, Yun-han (Autor:in) / Xu, Chuan-yi (Autor:in) / Zhu, Hong-hu (Autor:in) / Sun, Zheng-xing (Autor:in)
Engineering Geology ; 291
09.06.2021
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Structural Dynamics Feature Learning Using a Supervised Variational Autoencoder
| ASCE | 2025
A noise‐based framework for randomly generating soil particle with realistic geometry
| Wiley | 2025