SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism
Abstract Increased availability and quality of surface and subsurface observations provide the chance to improve the perception of hydrological phenomena. An important factor that hinders our understanding of hydrological structures is the characterization of heterogeneous patterns with continuous a...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Water Resources Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2023WR035932 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850115846571032576 |
|---|---|
| author | Zhesi Cui Qiyu Chen Gang Liu Lei Xun |
| author_facet | Zhesi Cui Qiyu Chen Gang Liu Lei Xun |
| author_sort | Zhesi Cui |
| collection | DOAJ |
| description | Abstract Increased availability and quality of surface and subsurface observations provide the chance to improve the perception of hydrological phenomena. An important factor that hinders our understanding of hydrological structures is the characterization of heterogeneous patterns with continuous attributes inside the structures (e.g., porosity, permeability, fluid saturation, etc.). Unlike categorical attributes, continuous attributes convey more realistic characteristics but require more computational resources to characterize such complex earth systems. In this work, we propose a novel deep learning approach for the characterization of complex hydrological realism with continuous attributes based on generative adversarial networks (GANs) and self‐attention mechanism, named SA‐RelayGANs. To address the complexity of heterogeneous hydrological structures, we divide the modeling process into two stages: facies construction stage and property reconstruction stage. In the first stage, we employ an improved GAN with self‐attention mechanism to construct the heterogeneous structures while adhering to hard conditioning constraints. In the second stage, we utilize another GAN with an attribute enhancement term to reconstruct realizations based on the constructed structures and observations. SA‐RelayGANs can successfully predict the statistical distributions of heterogeneous structures with continuous attributes by using limited observations. This study highlights the effectiveness of using GANs to characterize the heterogeneous patterns of hydrological realism and the application over large geoscience fields. |
| format | Article |
| id | doaj-art-7bc948d83d9e427092ecd56b5c55e083 |
| institution | OA Journals |
| issn | 0043-1397 1944-7973 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Water Resources Research |
| spelling | doaj-art-7bc948d83d9e427092ecd56b5c55e0832025-08-20T02:36:28ZengWileyWater Resources Research0043-13971944-79732024-01-01601n/an/a10.1029/2023WR035932SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention MechanismZhesi Cui0Qiyu Chen1Gang Liu2Lei Xun3School of Computer Science China University of Geosciences Wuhan ChinaSchool of Computer Science China University of Geosciences Wuhan ChinaSchool of Computer Science China University of Geosciences Wuhan ChinaSchool of Computer Science China University of Geosciences Wuhan ChinaAbstract Increased availability and quality of surface and subsurface observations provide the chance to improve the perception of hydrological phenomena. An important factor that hinders our understanding of hydrological structures is the characterization of heterogeneous patterns with continuous attributes inside the structures (e.g., porosity, permeability, fluid saturation, etc.). Unlike categorical attributes, continuous attributes convey more realistic characteristics but require more computational resources to characterize such complex earth systems. In this work, we propose a novel deep learning approach for the characterization of complex hydrological realism with continuous attributes based on generative adversarial networks (GANs) and self‐attention mechanism, named SA‐RelayGANs. To address the complexity of heterogeneous hydrological structures, we divide the modeling process into two stages: facies construction stage and property reconstruction stage. In the first stage, we employ an improved GAN with self‐attention mechanism to construct the heterogeneous structures while adhering to hard conditioning constraints. In the second stage, we utilize another GAN with an attribute enhancement term to reconstruct realizations based on the constructed structures and observations. SA‐RelayGANs can successfully predict the statistical distributions of heterogeneous structures with continuous attributes by using limited observations. This study highlights the effectiveness of using GANs to characterize the heterogeneous patterns of hydrological realism and the application over large geoscience fields.https://doi.org/10.1029/2023WR035932hydrogeological modelingdeep learninggenerative adversarial networksconditional simulation |
| spellingShingle | Zhesi Cui Qiyu Chen Gang Liu Lei Xun SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism Water Resources Research hydrogeological modeling deep learning generative adversarial networks conditional simulation |
| title | SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism |
| title_full | SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism |
| title_fullStr | SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism |
| title_full_unstemmed | SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism |
| title_short | SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism |
| title_sort | sa relaygans a novel framework for the characterization of complex hydrological structures based on gans and self attention mechanism |
| topic | hydrogeological modeling deep learning generative adversarial networks conditional simulation |
| url | https://doi.org/10.1029/2023WR035932 |
| work_keys_str_mv | AT zhesicui sarelaygansanovelframeworkforthecharacterizationofcomplexhydrologicalstructuresbasedongansandselfattentionmechanism AT qiyuchen sarelaygansanovelframeworkforthecharacterizationofcomplexhydrologicalstructuresbasedongansandselfattentionmechanism AT gangliu sarelaygansanovelframeworkforthecharacterizationofcomplexhydrologicalstructuresbasedongansandselfattentionmechanism AT leixun sarelaygansanovelframeworkforthecharacterizationofcomplexhydrologicalstructuresbasedongansandselfattentionmechanism |