GANSim-3D for Conditional Geomodeling: Theory and Field Application

Song, Suihong1,2; Mukerji, Tapan3; Hou, Jiagen1,4; Zhang, Dongxiao5; Lyu, Xinrui6

2022-07-01

10.1029/2021WR031865

WATER RESOURCES RESEARCH   Impact Factor & Quartile

0043-1397

1944-7973

We present a Generative Adversarial Network (GAN)-based 3D reservoir simulation framework, GANSim-3D, where the generator is progressively trained to capture geological patterns and relationships between various input conditioning data and output earth models, and is thus able to directly produce multiple 3D realistic and conditional earth models from given conditioning data. Conditioning data can include 3D sparse well facies data, probability maps, and global features, such as facies proportion. The generator only includes 3D convolutional layers, and once trained on a data set consisting of small-size data cubes, it can be used for geomodeling of 3D reservoirs of large arbitrary sizes by simply extending the inputs. To illustrate how GANSim-3D is practically used and to verify GANSim-3D, a field karst cave reservoir in Tahe area of China is used as an example. The 3D well facies data and 3D probability map of caves obtained from geophysical interpretation are taken as conditioning data. First, we create training, validation, and test datasets consisting of 64 x 64 x 64-size 3D cave facies models integrating field geological patterns, 3D well facies data, and 3D probability maps. Then, the 3D generator is trained and evaluated with various metrics. Next, we apply the pretrained generator for conditional geomodeling of two field cave reservoirs of size 64 x 64 x 64 and 336 x 256 x 96, respectively. The produced reservoir realizations prove to be diverse, consistent with field geological patterns and field conditioning data, and robust to noise in the 3D probability maps. Each realization with 336 x 256 x 96 cells only takes 0.988 s using 1 GPU.

facies modeling geological reservoir GANs karst cave process-mimicking geomodeling

SCI ; EI

English

Corresponding

National Natural Science Foundation of China[42072146]

Environmental Sciences & Ecology ; Marine & Freshwater Biology ; Water Resources

Environmental Sciences ; Limnology ; Water Resources

WOS:000828782900001

AMER GEOPHYSICAL UNION

20223112453655

Generative adversarial networks ; Geology ; Probability ; Three dimensional computer graphics

Geology:481.1 ; Data Processing and Image Processing:723.2 ; Artificial Intelligence:723.4 ; Computer Applications:723.5 ; Probability Theory:922.1

ENVIRONMENT/ECOLOGY

Web of Science

1.China Univ Petr, Coll Geosci, Beijing, Peoples R China
2.Peng Cheng Lab, Dept Math & Theories, Shenzhen, Peoples R China
3.Stanford Univ, Dept Energy Resources Engn & Geol Sci, Stanford, CA 94305 USA
4.China Univ Petr, State Key Lab Petr Resources & Prospecting, Beijing, Peoples R China
5.Southern Univ Sci & Technol, Sch Environm Sci & Engn, Shenzhen, Peoples R China
6.Sinopec, Petr Explorat & Prod Res Inst, Beijing, Peoples R China

Song, Suihong,Mukerji, Tapan,Hou, Jiagen,et al. GANSim-3D for Conditional Geomodeling: Theory and Field Application[J]. WATER RESOURCES RESEARCH,2022,58(7).

Song, Suihong,Mukerji, Tapan,Hou, Jiagen,Zhang, Dongxiao,&Lyu, Xinrui.(2022).GANSim-3D for Conditional Geomodeling: Theory and Field Application.WATER RESOURCES RESEARCH,58(7).

Song, Suihong,et al."GANSim-3D for Conditional Geomodeling: Theory and Field Application".WATER RESOURCES RESEARCH 58.7(2022).