Method for Predicting Transverse Wave Velocity Using a Gated Recurrent Unit Based on Spatiotemporal Attention Mechanism
Transverse wave velocity plays an important role in seismic exploration and reservoir assessment in the oil and gas industry. Due to the lack of transverse wave velocity data from actual production activities, it is necessary to predict transverse wave velocity based on longitudinal wave velocity an...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
GeoScienceWorld
2023-11-01
|
Series: | Lithosphere |
Online Access: | https://pubs.geoscienceworld.org/gsa/lithosphere/article-pdf/doi/10.2113/2023/lithosphere_2023_227/6014056/lithosphere_2023_227.pdf |
_version_ | 1797387349186838528 |
---|---|
author | Jiaxin Huang Gang Gao Xiaoming Li Yonggen Li Zhixian Gui |
author_facet | Jiaxin Huang Gang Gao Xiaoming Li Yonggen Li Zhixian Gui |
author_sort | Jiaxin Huang |
collection | DOAJ |
description | Transverse wave velocity plays an important role in seismic exploration and reservoir assessment in the oil and gas industry. Due to the lack of transverse wave velocity data from actual production activities, it is necessary to predict transverse wave velocity based on longitudinal wave velocity and other reservoir parameters. This paper proposes a fusion network based on spatiotemporal attention mechanism and gated recurrent unit (STAGRU) due to the significant correlation between the transverse wave velocity and reservoir parameters in the spatiotemporal domain. In the case of tight sandstone reservoirs in the Junggar Basin, the intersection plot technique is used to select four well logging parameters that are sensitive to transverse wave velocity: longitudinal wave velocity, density, natural gamma, and neutron porosity. The autocorrelation technique is employed to analyze the depth-related correlation of well logging curves. The relationship between the spatiotemporal characteristics of these well logging data and the network attention weights is also examined to validate the rationale behind incorporating the spatiotemporal attention mechanism. Finally, the actual measurement data from multiple wells are utilized to analyze the performance of the training set and test set separately. The results indicate that the predictive accuracy and generalization ability of the proposed STAGRU method are superior to the single-parameter fitting method, multiparameter fitting method, Xu-White model method, GRU network, and 2DCNN-GRU hybrid network. This demonstrates the feasibility of the transverse wave velocity prediction method based on the spatiotemporal attention mechanism in the study of rock physics modeling for tight sandstone reservoirs. |
first_indexed | 2024-03-08T22:22:54Z |
format | Article |
id | doaj.art-ba6691d39174445fbf0d24ff31539284 |
institution | Directory Open Access Journal |
issn | 1941-8264 1947-4253 |
language | English |
last_indexed | 2024-03-08T22:22:54Z |
publishDate | 2023-11-01 |
publisher | GeoScienceWorld |
record_format | Article |
series | Lithosphere |
spelling | doaj.art-ba6691d39174445fbf0d24ff315392842023-12-18T12:18:57ZengGeoScienceWorldLithosphere1941-82641947-42532023-11-012023110.2113/2023/lithosphere_2023_227Method for Predicting Transverse Wave Velocity Using a Gated Recurrent Unit Based on Spatiotemporal Attention MechanismJiaxin Huang0https://orcid.org/0009-0005-7012-0109Gang Gao1https://orcid.org/0000-0002-3560-0108Xiaoming Li2Yonggen Li3https://orcid.org/0000-0003-3099-6235Zhixian Gui4https://orcid.org/0000-0002-9858-7510Key Laboratory of Exploration Technologies for Oil and Gas Resources (Yangtze University), Ministry of Education, Wuhan 430100, ChinaKey Laboratory of Exploration Technologies for Oil and Gas Resources (Yangtze University), Ministry of Education, Wuhan 430100, ChinaResearch Institute of Petroleum Exploration and Development, CNPC, Beijing 100083, ChinaResearch Institute of Petroleum Exploration and Development, CNPC, Beijing 100083, ChinaKey Laboratory of Exploration Technologies for Oil and Gas Resources (Yangtze University), Ministry of Education, Wuhan 430100, ChinaTransverse wave velocity plays an important role in seismic exploration and reservoir assessment in the oil and gas industry. Due to the lack of transverse wave velocity data from actual production activities, it is necessary to predict transverse wave velocity based on longitudinal wave velocity and other reservoir parameters. This paper proposes a fusion network based on spatiotemporal attention mechanism and gated recurrent unit (STAGRU) due to the significant correlation between the transverse wave velocity and reservoir parameters in the spatiotemporal domain. In the case of tight sandstone reservoirs in the Junggar Basin, the intersection plot technique is used to select four well logging parameters that are sensitive to transverse wave velocity: longitudinal wave velocity, density, natural gamma, and neutron porosity. The autocorrelation technique is employed to analyze the depth-related correlation of well logging curves. The relationship between the spatiotemporal characteristics of these well logging data and the network attention weights is also examined to validate the rationale behind incorporating the spatiotemporal attention mechanism. Finally, the actual measurement data from multiple wells are utilized to analyze the performance of the training set and test set separately. The results indicate that the predictive accuracy and generalization ability of the proposed STAGRU method are superior to the single-parameter fitting method, multiparameter fitting method, Xu-White model method, GRU network, and 2DCNN-GRU hybrid network. This demonstrates the feasibility of the transverse wave velocity prediction method based on the spatiotemporal attention mechanism in the study of rock physics modeling for tight sandstone reservoirs.https://pubs.geoscienceworld.org/gsa/lithosphere/article-pdf/doi/10.2113/2023/lithosphere_2023_227/6014056/lithosphere_2023_227.pdf |
spellingShingle | Jiaxin Huang Gang Gao Xiaoming Li Yonggen Li Zhixian Gui Method for Predicting Transverse Wave Velocity Using a Gated Recurrent Unit Based on Spatiotemporal Attention Mechanism Lithosphere |
title | Method for Predicting Transverse Wave Velocity Using a Gated Recurrent Unit Based on Spatiotemporal Attention Mechanism |
title_full | Method for Predicting Transverse Wave Velocity Using a Gated Recurrent Unit Based on Spatiotemporal Attention Mechanism |
title_fullStr | Method for Predicting Transverse Wave Velocity Using a Gated Recurrent Unit Based on Spatiotemporal Attention Mechanism |
title_full_unstemmed | Method for Predicting Transverse Wave Velocity Using a Gated Recurrent Unit Based on Spatiotemporal Attention Mechanism |
title_short | Method for Predicting Transverse Wave Velocity Using a Gated Recurrent Unit Based on Spatiotemporal Attention Mechanism |
title_sort | method for predicting transverse wave velocity using a gated recurrent unit based on spatiotemporal attention mechanism |
url | https://pubs.geoscienceworld.org/gsa/lithosphere/article-pdf/doi/10.2113/2023/lithosphere_2023_227/6014056/lithosphere_2023_227.pdf |
work_keys_str_mv | AT jiaxinhuang methodforpredictingtransversewavevelocityusingagatedrecurrentunitbasedonspatiotemporalattentionmechanism AT ganggao methodforpredictingtransversewavevelocityusingagatedrecurrentunitbasedonspatiotemporalattentionmechanism AT xiaomingli methodforpredictingtransversewavevelocityusingagatedrecurrentunitbasedonspatiotemporalattentionmechanism AT yonggenli methodforpredictingtransversewavevelocityusingagatedrecurrentunitbasedonspatiotemporalattentionmechanism AT zhixiangui methodforpredictingtransversewavevelocityusingagatedrecurrentunitbasedonspatiotemporalattentionmechanism |