Improving patch-based simulation using Generative Adversial Networks
Multiple-Point Simulation (MPS) is a geostatistical simulation technique commonly used to model complex geological patterns and subsurface heterogeneity. There have been a great variety of implementation methods developed within MPS, of which Patch-Based Simulation is a more recently developed class...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co. Ltd.
2023-12-01
|
| Series: | Artificial Intelligence in Geosciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666544123000229 |
| _version_ | 1797347742373117952 |
|---|---|
| author | Xiaojin Tan Eldad Haber |
| author_facet | Xiaojin Tan Eldad Haber |
| author_sort | Xiaojin Tan |
| collection | DOAJ |
| description | Multiple-Point Simulation (MPS) is a geostatistical simulation technique commonly used to model complex geological patterns and subsurface heterogeneity. There have been a great variety of implementation methods developed within MPS, of which Patch-Based Simulation is a more recently developed class. While we have witnessed great progress in Patch-Based algorithms lately, they are still faced with two challenges: conditioning to point data and the occurrence of verbatim copy. Both of them are partly due to finite size of Training image, from which a limited size of pattern database is constructed. To address these questions, we propose a novel approach that we call Generative-Patched-Simulation (GPSim), which is based on Generative Adversarial Networks (GAN). With this method, we are able to generate sufficient (in theory an infinite) number of new patches based on the current pattern database. As demonstrated by the results on a simple 2D binary image, this approach shows its potential to address the two issues and thus improve Patch-based Simulation methods. |
| first_indexed | 2024-03-08T11:53:10Z |
| format | Article |
| id | doaj.art-46be48b283724c86a8aa54cfa30cd33d |
| institution | Directory Open Access Journal |
| issn | 2666-5441 |
| language | English |
| last_indexed | 2024-03-08T11:53:10Z |
| publishDate | 2023-12-01 |
| publisher | KeAi Communications Co. Ltd. |
| record_format | Article |
| series | Artificial Intelligence in Geosciences |
| spelling | doaj.art-46be48b283724c86a8aa54cfa30cd33d2024-01-24T05:21:58ZengKeAi Communications Co. Ltd.Artificial Intelligence in Geosciences2666-54412023-12-0147683Improving patch-based simulation using Generative Adversial NetworksXiaojin Tan0Eldad Haber1Corresponding author.; Department of Earth and Ocean Science, The University of British Columbia, Vancouver, BC, CanadaDepartment of Earth and Ocean Science, The University of British Columbia, Vancouver, BC, CanadaMultiple-Point Simulation (MPS) is a geostatistical simulation technique commonly used to model complex geological patterns and subsurface heterogeneity. There have been a great variety of implementation methods developed within MPS, of which Patch-Based Simulation is a more recently developed class. While we have witnessed great progress in Patch-Based algorithms lately, they are still faced with two challenges: conditioning to point data and the occurrence of verbatim copy. Both of them are partly due to finite size of Training image, from which a limited size of pattern database is constructed. To address these questions, we propose a novel approach that we call Generative-Patched-Simulation (GPSim), which is based on Generative Adversarial Networks (GAN). With this method, we are able to generate sufficient (in theory an infinite) number of new patches based on the current pattern database. As demonstrated by the results on a simple 2D binary image, this approach shows its potential to address the two issues and thus improve Patch-based Simulation methods.http://www.sciencedirect.com/science/article/pii/S2666544123000229Generative Adversial NetworksPatch-based simulation |
| spellingShingle | Xiaojin Tan Eldad Haber Improving patch-based simulation using Generative Adversial Networks Artificial Intelligence in Geosciences Generative Adversial Networks Patch-based simulation |
| title | Improving patch-based simulation using Generative Adversial Networks |
| title_full | Improving patch-based simulation using Generative Adversial Networks |
| title_fullStr | Improving patch-based simulation using Generative Adversial Networks |
| title_full_unstemmed | Improving patch-based simulation using Generative Adversial Networks |
| title_short | Improving patch-based simulation using Generative Adversial Networks |
| title_sort | improving patch based simulation using generative adversial networks |
| topic | Generative Adversial Networks Patch-based simulation |
| url | http://www.sciencedirect.com/science/article/pii/S2666544123000229 |
| work_keys_str_mv | AT xiaojintan improvingpatchbasedsimulationusinggenerativeadversialnetworks AT eldadhaber improvingpatchbasedsimulationusinggenerativeadversialnetworks |