Shear-Wave Velocity Prediction Method via a Gate Recurrent Unit Fusion Network Based on the Spatiotemporal Attention Mechanism
AbstractCompression-wave velocity and shear-wave velocity are important elastic parameters describing deeply tight sandstone. Limited by cost and technical reasons, the conventional logging data generally lack shear-wave velocity. In addition, the existing rock physics theory is diff...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
GeoScienceWorld
2022-12-01
|
| Series: | Lithosphere |
| Online Access: | https://pubs.geoscienceworld.org/lithosphere/article/2022/Special%2012/4701851/619658/Shear-Wave-Velocity-Prediction-Method-via-a-Gate |
| _version_ | 1797820241205526528 |
|---|---|
| author | Tengfei Chen Gang Gao Yonggen Li Peng Wang Bin Zhao Zhixian Gui Xiaoyan Zhai |
| author_facet | Tengfei Chen Gang Gao Yonggen Li Peng Wang Bin Zhao Zhixian Gui Xiaoyan Zhai |
| author_sort | Tengfei Chen |
| collection | DOAJ |
| description |
AbstractCompression-wave velocity and shear-wave velocity are important elastic parameters describing deeply tight sandstone. Limited by cost and technical reasons, the conventional logging data generally lack shear-wave velocity. In addition, the existing rock physics theory is difficult to accurately establish the rock physics models due to the complex pore structure of tight sandstone reservoir. With the rapid development of the artificial intelligence, the attention mechanism that can increase the sensitivity of the network to important characteristics has been widely used in machine translation, image processing, and other fields, but it is rarely used to predict shear-wave velocity. Based on the correlation between the shear-wave velocity and the conventional logging data in the spatiotemporal direction, a gate recurrent unit (GRU) fusion network based on the spatiotemporal attention mechanism (STAGRU) is proposed. Compared with the convolutional neural network (CNN) and gate recurrent unit (GRU), the network proposed can improve the sensitivity of the network to important spatiotemporal characteristics using the spatiotemporal attention mechanism. It is analyzed that the relationship between the spatiotemporal characteristics of the conventional logging data and the attention weights of the network proposed to verify the rationality of adding the spatiotemporal attention mechanism. Finally, the training and testing results of the STAGRU, CNN, and GRU networks show that the prediction accuracy and generalization of the network proposed are better than those of the other two networks. |
| first_indexed | 2024-03-13T09:35:33Z |
| format | Article |
| id | doaj.art-8ae54d2b7b1143d488e532b160283410 |
| institution | Directory Open Access Journal |
| issn | 1941-8264 1947-4253 |
| language | English |
| last_indexed | 2024-03-13T09:35:33Z |
| publishDate | 2022-12-01 |
| publisher | GeoScienceWorld |
| record_format | Article |
| series | Lithosphere |
| spelling | doaj.art-8ae54d2b7b1143d488e532b1602834102023-05-25T14:42:51ZengGeoScienceWorldLithosphere1941-82641947-42532022-12-012022Special 1210.2113/2022/4701851Shear-Wave Velocity Prediction Method via a Gate Recurrent Unit Fusion Network Based on the Spatiotemporal Attention MechanismTengfei Chen0http://orcid.org/0000-0003-4918-1028Gang Gao1http://orcid.org/0000-0002-3560-0108Yonggen Li2http://orcid.org/0000-0003-3099-6235Peng Wang3http://orcid.org/0000-0002-7554-522XBin Zhao4http://orcid.org/0000-0002-0925-2445Zhixian Gui5http://orcid.org/0000-0002-9858-7510Xiaoyan Zhai6http://orcid.org/0000-0002-3810-60921 Key Laboratory of Exploration Technologies for Oil and Gas Resources (Yangtze University) Ministry of Education Wuhan 430100 China meb.gov.tr1 Key Laboratory of Exploration Technologies for Oil and Gas Resources (Yangtze University) Ministry of Education Wuhan 430100 China meb.gov.tr2 Research Institute of Petroleum Exploration and Development CNPC Beijing 100083 China cnpc.com.cn1 Key Laboratory of Exploration Technologies for Oil and Gas Resources (Yangtze University) Ministry of Education Wuhan 430100 China meb.gov.tr1 Key Laboratory of Exploration Technologies for Oil and Gas Resources (Yangtze University) Ministry of Education Wuhan 430100 China meb.gov.tr1 Key Laboratory of Exploration Technologies for Oil and Gas Resources (Yangtze University) Ministry of Education Wuhan 430100 China meb.gov.tr1 Key Laboratory of Exploration Technologies for Oil and Gas Resources (Yangtze University) Ministry of Education Wuhan 430100 China meb.gov.tr AbstractCompression-wave velocity and shear-wave velocity are important elastic parameters describing deeply tight sandstone. Limited by cost and technical reasons, the conventional logging data generally lack shear-wave velocity. In addition, the existing rock physics theory is difficult to accurately establish the rock physics models due to the complex pore structure of tight sandstone reservoir. With the rapid development of the artificial intelligence, the attention mechanism that can increase the sensitivity of the network to important characteristics has been widely used in machine translation, image processing, and other fields, but it is rarely used to predict shear-wave velocity. Based on the correlation between the shear-wave velocity and the conventional logging data in the spatiotemporal direction, a gate recurrent unit (GRU) fusion network based on the spatiotemporal attention mechanism (STAGRU) is proposed. Compared with the convolutional neural network (CNN) and gate recurrent unit (GRU), the network proposed can improve the sensitivity of the network to important spatiotemporal characteristics using the spatiotemporal attention mechanism. It is analyzed that the relationship between the spatiotemporal characteristics of the conventional logging data and the attention weights of the network proposed to verify the rationality of adding the spatiotemporal attention mechanism. Finally, the training and testing results of the STAGRU, CNN, and GRU networks show that the prediction accuracy and generalization of the network proposed are better than those of the other two networks.https://pubs.geoscienceworld.org/lithosphere/article/2022/Special%2012/4701851/619658/Shear-Wave-Velocity-Prediction-Method-via-a-Gate |
| spellingShingle | Tengfei Chen Gang Gao Yonggen Li Peng Wang Bin Zhao Zhixian Gui Xiaoyan Zhai Shear-Wave Velocity Prediction Method via a Gate Recurrent Unit Fusion Network Based on the Spatiotemporal Attention Mechanism Lithosphere |
| title | Shear-Wave Velocity Prediction Method via a Gate Recurrent Unit Fusion Network Based on the Spatiotemporal Attention Mechanism |
| title_full | Shear-Wave Velocity Prediction Method via a Gate Recurrent Unit Fusion Network Based on the Spatiotemporal Attention Mechanism |
| title_fullStr | Shear-Wave Velocity Prediction Method via a Gate Recurrent Unit Fusion Network Based on the Spatiotemporal Attention Mechanism |
| title_full_unstemmed | Shear-Wave Velocity Prediction Method via a Gate Recurrent Unit Fusion Network Based on the Spatiotemporal Attention Mechanism |
| title_short | Shear-Wave Velocity Prediction Method via a Gate Recurrent Unit Fusion Network Based on the Spatiotemporal Attention Mechanism |
| title_sort | shear wave velocity prediction method via a gate recurrent unit fusion network based on the spatiotemporal attention mechanism |
| url | https://pubs.geoscienceworld.org/lithosphere/article/2022/Special%2012/4701851/619658/Shear-Wave-Velocity-Prediction-Method-via-a-Gate |
| work_keys_str_mv | AT tengfeichen shearwavevelocitypredictionmethodviaagaterecurrentunitfusionnetworkbasedonthespatiotemporalattentionmechanism AT ganggao shearwavevelocitypredictionmethodviaagaterecurrentunitfusionnetworkbasedonthespatiotemporalattentionmechanism AT yonggenli shearwavevelocitypredictionmethodviaagaterecurrentunitfusionnetworkbasedonthespatiotemporalattentionmechanism AT pengwang shearwavevelocitypredictionmethodviaagaterecurrentunitfusionnetworkbasedonthespatiotemporalattentionmechanism AT binzhao shearwavevelocitypredictionmethodviaagaterecurrentunitfusionnetworkbasedonthespatiotemporalattentionmechanism AT zhixiangui shearwavevelocitypredictionmethodviaagaterecurrentunitfusionnetworkbasedonthespatiotemporalattentionmechanism AT xiaoyanzhai shearwavevelocitypredictionmethodviaagaterecurrentunitfusionnetworkbasedonthespatiotemporalattentionmechanism |