A Deep Learning Approach for Stochastic Structural Plane Generation Based on Denoising Diffusion Probabilistic Models
The stochastic structural plane of a rock mass is the key factor controlling the stability of rock mass. Obtaining the distribution of stochastic structural planes within a rock mass is crucial for analyzing rock mass stability and supporting rock slopes effectively. The conventional Monte Carlo met...
Published in: | Mathematics |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2024
|
Subjects: | |
Online Access: | https://doi.org/10.3390/math12131997 https://doaj.org/article/0b08ca1d879f45eaaeca8bf71a9d563b |
id |
ftdoajarticles:oai:doaj.org/article:0b08ca1d879f45eaaeca8bf71a9d563b |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:0b08ca1d879f45eaaeca8bf71a9d563b 2024-09-15T18:20:33+00:00 A Deep Learning Approach for Stochastic Structural Plane Generation Based on Denoising Diffusion Probabilistic Models Han Meng Xiaoyu Qi Gang Mei 2024-06-01T00:00:00Z https://doi.org/10.3390/math12131997 https://doaj.org/article/0b08ca1d879f45eaaeca8bf71a9d563b EN eng MDPI AG https://www.mdpi.com/2227-7390/12/13/1997 https://doaj.org/toc/2227-7390 doi:10.3390/math12131997 2227-7390 https://doaj.org/article/0b08ca1d879f45eaaeca8bf71a9d563b Mathematics, Vol 12, Iss 13, p 1997 (2024) rock mass stochastic structural planes Monte Carlo method deep learning denoising diffusion probabilistic model (DDPM) Mathematics QA1-939 article 2024 ftdoajarticles https://doi.org/10.3390/math12131997 2024-08-05T17:48:57Z The stochastic structural plane of a rock mass is the key factor controlling the stability of rock mass. Obtaining the distribution of stochastic structural planes within a rock mass is crucial for analyzing rock mass stability and supporting rock slopes effectively. The conventional Monte Carlo method generates each parameter of stochastic structural planes separately without considering the correlation between the parameters. To address the above problem, this study novelly uses the denoising diffusion probabilistic model (DDPM) to generate stochastic structural planes. DDPM belongs to the deep generative model, which can generate stochastic structural planes without assuming the probability distribution of stochastic structural planes in advance. It takes structural plane parameters as an integral input into the model and can automatically capture the correlations between structural plane parameters during generation. This idea has been used for stochastic structural plane generation of the Oernlia slope in the eastern part of Straumsvatnet Lake, Nordland County, north-central Norway. The accuracy was verified by descriptive statistics (i.e., histogram, box plot, cumulative distribution curve), similarity measures (i.e., mean square error, KL divergence, JS divergence, Wasserstein distance, Euclidean distance), error analysis, and the linear regression plot. Moreover, the linear regression plots between the dip direction and the dip angle verified that DDPM can effectively and automatically capture the correlation between parameters. Article in Journal/Newspaper Nordland Nordland Nordland Directory of Open Access Journals: DOAJ Articles Mathematics 12 13 1997 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
rock mass stochastic structural planes Monte Carlo method deep learning denoising diffusion probabilistic model (DDPM) Mathematics QA1-939 |
spellingShingle |
rock mass stochastic structural planes Monte Carlo method deep learning denoising diffusion probabilistic model (DDPM) Mathematics QA1-939 Han Meng Xiaoyu Qi Gang Mei A Deep Learning Approach for Stochastic Structural Plane Generation Based on Denoising Diffusion Probabilistic Models |
topic_facet |
rock mass stochastic structural planes Monte Carlo method deep learning denoising diffusion probabilistic model (DDPM) Mathematics QA1-939 |
description |
The stochastic structural plane of a rock mass is the key factor controlling the stability of rock mass. Obtaining the distribution of stochastic structural planes within a rock mass is crucial for analyzing rock mass stability and supporting rock slopes effectively. The conventional Monte Carlo method generates each parameter of stochastic structural planes separately without considering the correlation between the parameters. To address the above problem, this study novelly uses the denoising diffusion probabilistic model (DDPM) to generate stochastic structural planes. DDPM belongs to the deep generative model, which can generate stochastic structural planes without assuming the probability distribution of stochastic structural planes in advance. It takes structural plane parameters as an integral input into the model and can automatically capture the correlations between structural plane parameters during generation. This idea has been used for stochastic structural plane generation of the Oernlia slope in the eastern part of Straumsvatnet Lake, Nordland County, north-central Norway. The accuracy was verified by descriptive statistics (i.e., histogram, box plot, cumulative distribution curve), similarity measures (i.e., mean square error, KL divergence, JS divergence, Wasserstein distance, Euclidean distance), error analysis, and the linear regression plot. Moreover, the linear regression plots between the dip direction and the dip angle verified that DDPM can effectively and automatically capture the correlation between parameters. |
format |
Article in Journal/Newspaper |
author |
Han Meng Xiaoyu Qi Gang Mei |
author_facet |
Han Meng Xiaoyu Qi Gang Mei |
author_sort |
Han Meng |
title |
A Deep Learning Approach for Stochastic Structural Plane Generation Based on Denoising Diffusion Probabilistic Models |
title_short |
A Deep Learning Approach for Stochastic Structural Plane Generation Based on Denoising Diffusion Probabilistic Models |
title_full |
A Deep Learning Approach for Stochastic Structural Plane Generation Based on Denoising Diffusion Probabilistic Models |
title_fullStr |
A Deep Learning Approach for Stochastic Structural Plane Generation Based on Denoising Diffusion Probabilistic Models |
title_full_unstemmed |
A Deep Learning Approach for Stochastic Structural Plane Generation Based on Denoising Diffusion Probabilistic Models |
title_sort |
deep learning approach for stochastic structural plane generation based on denoising diffusion probabilistic models |
publisher |
MDPI AG |
publishDate |
2024 |
url |
https://doi.org/10.3390/math12131997 https://doaj.org/article/0b08ca1d879f45eaaeca8bf71a9d563b |
genre |
Nordland Nordland Nordland |
genre_facet |
Nordland Nordland Nordland |
op_source |
Mathematics, Vol 12, Iss 13, p 1997 (2024) |
op_relation |
https://www.mdpi.com/2227-7390/12/13/1997 https://doaj.org/toc/2227-7390 doi:10.3390/math12131997 2227-7390 https://doaj.org/article/0b08ca1d879f45eaaeca8bf71a9d563b |
op_doi |
https://doi.org/10.3390/math12131997 |
container_title |
Mathematics |
container_volume |
12 |
container_issue |
13 |
container_start_page |
1997 |
_version_ |
1810458932700774400 |