Intelligent characterization of ultra-deep carbonate strike-slip fault zones based on 3DResNeSt-UNet: a case study of the YueMan Block in the Tarim Basin
Abstract The strike-slip fault zones (SSFZ) in the ultra-deep carbonate rocks of the Tarim Basin provide crucial space for the migration and accumulation of oil and gas. Traditional 3D seismic interpretation methods have limitations in identifying SSFZ. This study proposes a seismic interpretation m...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | Journal of Petroleum Exploration and Production Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s13202-025-01942-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823863305941286912 |
|---|---|
| author | Jin Hu Shouyu Xu |
| author_facet | Jin Hu Shouyu Xu |
| author_sort | Jin Hu |
| collection | DOAJ |
| description | Abstract The strike-slip fault zones (SSFZ) in the ultra-deep carbonate rocks of the Tarim Basin provide crucial space for the migration and accumulation of oil and gas. Traditional 3D seismic interpretation methods have limitations in identifying SSFZ. This study proposes a seismic interpretation method based on the 3DResNeSt-UNet to identify SSFZ more effectively. This network integrates the 3DUNet and ResNeSt modules, using synthetic 3D seismic data and its corresponding label data as inputs for training. The synthetic seismic data incorporates geological knowledge and geological body parameters. Initially, by combining field outcrop observations, logging, and seismic data, the geological patterns of SSFZ are summarized. Guided by these geological patterns and based on the geological body parameters extracted from logging and seismic data, synthetic 3D seismic data and its corresponding label data are generated. The results indicate that the accuracy of the 3DResNeSt-UNet model on the training data exceeds 98%. The trained model achieves good recognition results on the seismic data of the YueMan block. Compared with traditional seismic interpretation results, the model’s recognition accuracy is significantly improved and more aligned with geological understanding. Overall, the 3DResNeSt-UNet provides a new effective method for identifying SSFZ and has great potential for application in similar seismic interpretation scenarios. |
| format | Article |
| id | doaj-art-cc137286885847289776932c5530911f |
| institution | Kabale University |
| issn | 2190-0558 2190-0566 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Petroleum Exploration and Production Technology |
| spelling | doaj-art-cc137286885847289776932c5530911f2025-02-09T12:13:17ZengSpringerOpenJournal of Petroleum Exploration and Production Technology2190-05582190-05662025-01-0115111910.1007/s13202-025-01942-8Intelligent characterization of ultra-deep carbonate strike-slip fault zones based on 3DResNeSt-UNet: a case study of the YueMan Block in the Tarim BasinJin Hu0Shouyu Xu1School of Geosciences, China University of Petroleum (East China)School of Geosciences, China University of Petroleum (East China)Abstract The strike-slip fault zones (SSFZ) in the ultra-deep carbonate rocks of the Tarim Basin provide crucial space for the migration and accumulation of oil and gas. Traditional 3D seismic interpretation methods have limitations in identifying SSFZ. This study proposes a seismic interpretation method based on the 3DResNeSt-UNet to identify SSFZ more effectively. This network integrates the 3DUNet and ResNeSt modules, using synthetic 3D seismic data and its corresponding label data as inputs for training. The synthetic seismic data incorporates geological knowledge and geological body parameters. Initially, by combining field outcrop observations, logging, and seismic data, the geological patterns of SSFZ are summarized. Guided by these geological patterns and based on the geological body parameters extracted from logging and seismic data, synthetic 3D seismic data and its corresponding label data are generated. The results indicate that the accuracy of the 3DResNeSt-UNet model on the training data exceeds 98%. The trained model achieves good recognition results on the seismic data of the YueMan block. Compared with traditional seismic interpretation results, the model’s recognition accuracy is significantly improved and more aligned with geological understanding. Overall, the 3DResNeSt-UNet provides a new effective method for identifying SSFZ and has great potential for application in similar seismic interpretation scenarios.https://doi.org/10.1007/s13202-025-01942-8Tarim BasinUltra-deep carbonate rocksStrike-slip fault zones (SSFZ)3DResNeSt-UNetSeismic data |
| spellingShingle | Jin Hu Shouyu Xu Intelligent characterization of ultra-deep carbonate strike-slip fault zones based on 3DResNeSt-UNet: a case study of the YueMan Block in the Tarim Basin Journal of Petroleum Exploration and Production Technology Tarim Basin Ultra-deep carbonate rocks Strike-slip fault zones (SSFZ) 3DResNeSt-UNet Seismic data |
| title | Intelligent characterization of ultra-deep carbonate strike-slip fault zones based on 3DResNeSt-UNet: a case study of the YueMan Block in the Tarim Basin |
| title_full | Intelligent characterization of ultra-deep carbonate strike-slip fault zones based on 3DResNeSt-UNet: a case study of the YueMan Block in the Tarim Basin |
| title_fullStr | Intelligent characterization of ultra-deep carbonate strike-slip fault zones based on 3DResNeSt-UNet: a case study of the YueMan Block in the Tarim Basin |
| title_full_unstemmed | Intelligent characterization of ultra-deep carbonate strike-slip fault zones based on 3DResNeSt-UNet: a case study of the YueMan Block in the Tarim Basin |
| title_short | Intelligent characterization of ultra-deep carbonate strike-slip fault zones based on 3DResNeSt-UNet: a case study of the YueMan Block in the Tarim Basin |
| title_sort | intelligent characterization of ultra deep carbonate strike slip fault zones based on 3dresnest unet a case study of the yueman block in the tarim basin |
| topic | Tarim Basin Ultra-deep carbonate rocks Strike-slip fault zones (SSFZ) 3DResNeSt-UNet Seismic data |
| url | https://doi.org/10.1007/s13202-025-01942-8 |
| work_keys_str_mv | AT jinhu intelligentcharacterizationofultradeepcarbonatestrikeslipfaultzonesbasedon3dresnestunetacasestudyoftheyuemanblockinthetarimbasin AT shouyuxu intelligentcharacterizationofultradeepcarbonatestrikeslipfaultzonesbasedon3dresnestunetacasestudyoftheyuemanblockinthetarimbasin |