Xiaocui Li, Ligang Cao, Hui Cao, Tongbiao Wei, Lei Liu, Xingtao Yang
The cross-hole electromagnetic (EM) method, which is currently at the forefront of electric logging technology, fundamentally solves the problems of the lateral imaging ability of single well logging and the lack of detection of inter-well physical properties. However, due to the complexity of underground reservoir distribution and the non-uniqueness problem of geophysical inversion, there remains a lack of practical and effective cross-hole electromagnetic inversion methods. Our goal is to develop an efficient method to reduce the non-uniqueness of the physical property model recovered in the inversion. It is worth noting that the regularization algorithm (RA), as a means to approximately solve inversion problems, can obtain different solutions by changing the form of the regularization function, so as to ensure the stability of inversion results and conform to the smooth or non-smooth characteristics in known geology or geophysics. We adjust the features of the final inversion model in a defined framework by changing the values of the $alpha $coefficient in the regularization and using the Lawson norm as a ${l}_p$-norm approximation form for $p in [ {0,2} ]$. At the same time, the iteratively reweighted least squares method is used to solve the optimization problem, and the gradient in the Gauss-Newton solution is adjusted successively to ensure that every term in the regularization contributes to the final solution. Compared with the traditional ${l}_2$-norm inversion method, the sparse inversion method can make more effective use of information regarding known physical properties and obtain better inversion results. Then, the effectiveness of our inversion method is verified by model tests and inversion of measured data in a mining area.
{"title":"2-D cross-hole electromagnetic inversion algorithms based on regularization algorithms","authors":"Xiaocui Li, Ligang Cao, Hui Cao, Tongbiao Wei, Lei Liu, Xingtao Yang","doi":"10.1093/jge/gxad064","DOIUrl":"https://doi.org/10.1093/jge/gxad064","url":null,"abstract":"\u0000 The cross-hole electromagnetic (EM) method, which is currently at the forefront of electric logging technology, fundamentally solves the problems of the lateral imaging ability of single well logging and the lack of detection of inter-well physical properties. However, due to the complexity of underground reservoir distribution and the non-uniqueness problem of geophysical inversion, there remains a lack of practical and effective cross-hole electromagnetic inversion methods. Our goal is to develop an efficient method to reduce the non-uniqueness of the physical property model recovered in the inversion. It is worth noting that the regularization algorithm (RA), as a means to approximately solve inversion problems, can obtain different solutions by changing the form of the regularization function, so as to ensure the stability of inversion results and conform to the smooth or non-smooth characteristics in known geology or geophysics. We adjust the features of the final inversion model in a defined framework by changing the values of the $alpha $coefficient in the regularization and using the Lawson norm as a ${l}_p$-norm approximation form for $p in [ {0,2} ]$. At the same time, the iteratively reweighted least squares method is used to solve the optimization problem, and the gradient in the Gauss-Newton solution is adjusted successively to ensure that every term in the regularization contributes to the final solution. Compared with the traditional ${l}_2$-norm inversion method, the sparse inversion method can make more effective use of information regarding known physical properties and obtain better inversion results. Then, the effectiveness of our inversion method is verified by model tests and inversion of measured data in a mining area.","PeriodicalId":54820,"journal":{"name":"Journal of Geophysics and Engineering","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46253269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Deep hydrocarbon resources have become more and more important nowadays. However, owing to the affection of long-distance propagation and stratigraphic absorption, seismic data coming from deep beds generally suffer from weak energy, low resolution, and low signal-to-noise ratio (SNR), which seriously influence the reliability of seismic interpretation. Generally, inverse Q (quality factor) filtering (IQF) is used for absorption compensation, but it may amplify noise at the same time. Although compensation methods based on inversion overcomes the instability, it is still difficult to obtain high-SNR results. To address this issue, under the framework of sparse representation theory, we proposed a single-channel attenuation compensation method constrained by generalized minimax concave (GMC) penalty function. It takes the modified Kolsky model to describe seismic absorption and combines sparse representation theory to create objective function. Furthermore, a GMC penalty function is utilized to promote sparsity. It allows more accurate estimates of sparse coefficients from noise-contaminated seismic data. Although the GMC penalty itself is concave, the objective function remains strictly convex. Therefore, globally optimal sparse solutions can be obtained through an operator-splitting algorithm. Even in the presence of noise, this method can obtain stable and accurate compensation results through reconstruction. Synthetic data tests and field seismic data application showed that this method has high robustness to noise. It can stably and effectively compensate for the energy loss of seismic data, as well as maintain high SNR.
{"title":"Robust Seismic Attenuation Compensation Based on Generalized Minimax Concave Penalty Sparse Representation","authors":"Chengxiang Duan, Fanchang Zhang","doi":"10.1093/jge/gxad066","DOIUrl":"https://doi.org/10.1093/jge/gxad066","url":null,"abstract":"Abstract Deep hydrocarbon resources have become more and more important nowadays. However, owing to the affection of long-distance propagation and stratigraphic absorption, seismic data coming from deep beds generally suffer from weak energy, low resolution, and low signal-to-noise ratio (SNR), which seriously influence the reliability of seismic interpretation. Generally, inverse Q (quality factor) filtering (IQF) is used for absorption compensation, but it may amplify noise at the same time. Although compensation methods based on inversion overcomes the instability, it is still difficult to obtain high-SNR results. To address this issue, under the framework of sparse representation theory, we proposed a single-channel attenuation compensation method constrained by generalized minimax concave (GMC) penalty function. It takes the modified Kolsky model to describe seismic absorption and combines sparse representation theory to create objective function. Furthermore, a GMC penalty function is utilized to promote sparsity. It allows more accurate estimates of sparse coefficients from noise-contaminated seismic data. Although the GMC penalty itself is concave, the objective function remains strictly convex. Therefore, globally optimal sparse solutions can be obtained through an operator-splitting algorithm. Even in the presence of noise, this method can obtain stable and accurate compensation results through reconstruction. Synthetic data tests and field seismic data application showed that this method has high robustness to noise. It can stably and effectively compensate for the energy loss of seismic data, as well as maintain high SNR.","PeriodicalId":54820,"journal":{"name":"Journal of Geophysics and Engineering","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134950892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Numerical modeling of the direct current (DC) potential field for the mise-a-la-masse (MALM) method traditionally depends on the specific source under loss-free dielectric consideration. In this paper, we propose a numerical technique for modeling DC potential fields in charged lossy dielectric media. A numerical solver of charged current transportation is first presented using finite different method, then the DC potential is integrated from all unit current elements with the Legendre function polynomial. A new preconditioner is also proposed for MALM surveying to reduce the condition number to accurately solve the equation. This new technique is verified through comparisons with numerical cases and field surveys. The basic problem formulation is general, but it is directly applicable in MALM surveying as a geophysical technique where the DC potential produced by charged lossy dielectric media is of interest.
{"title":"A method for modeling DC potential fields in charged lossy dielectric media","authors":"Jinghe Li, Zhanxiang He, Hanying Bai","doi":"10.1093/jge/gxad065","DOIUrl":"https://doi.org/10.1093/jge/gxad065","url":null,"abstract":"Abstract Numerical modeling of the direct current (DC) potential field for the mise-a-la-masse (MALM) method traditionally depends on the specific source under loss-free dielectric consideration. In this paper, we propose a numerical technique for modeling DC potential fields in charged lossy dielectric media. A numerical solver of charged current transportation is first presented using finite different method, then the DC potential is integrated from all unit current elements with the Legendre function polynomial. A new preconditioner is also proposed for MALM surveying to reduce the condition number to accurately solve the equation. This new technique is verified through comparisons with numerical cases and field surveys. The basic problem formulation is general, but it is directly applicable in MALM surveying as a geophysical technique where the DC potential produced by charged lossy dielectric media is of interest.","PeriodicalId":54820,"journal":{"name":"Journal of Geophysics and Engineering","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134950885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Despite over twenty years of research, assisted seismic history matching (ASHM) remains a challenging problem for the energy industry. ASHM is an optimisation problem to find the best subsurface reservoir model for robust predictions of field performance. The results are typically assessed by a decreasing misfit between simulated and observed data, but the optimised models are often inaccurate, uncertain, and non-unique. In this paper, we take a fresh look at ASHM and view it from the perspective of the fitness landscape, or search space. We propose that characterising the fitness landscape will lead to a deeper understanding of the problem, greater confidence in the optimised models, and a better appreciation of the uncertainties. Fitness landscape analysis (FLA) is established in other fields, but has mostly been applied to combinatorial problems or continuous problems with analytical solutions. In contrast, ASHM is a real-world, ill-posed, inverse problem, which is computationally expensive and contains data errors and model uncertainties. We introduce a new method for FLA that provides intuitive information on the setup of the problem. It uses multidimensional clustering and visualisation to explore the structure of the landscape and detects the presence and relative magnitude of data errors, which are typical of real data. It is applied to a synthetic, full-field, reservoir model and the results are compared with another more-established method. We found that the fitness landscapes of ASHM problems are low-lying plateaus with many minima, which makes it difficult to solve ASHM problems for real-world datasets.
{"title":"Fitness landscape analysis for seismic history matching problems of subsurface reservoirs","authors":"Paul Mitchell, Romain Chassagne","doi":"10.1093/jge/gxad062","DOIUrl":"https://doi.org/10.1093/jge/gxad062","url":null,"abstract":"Abstract Despite over twenty years of research, assisted seismic history matching (ASHM) remains a challenging problem for the energy industry. ASHM is an optimisation problem to find the best subsurface reservoir model for robust predictions of field performance. The results are typically assessed by a decreasing misfit between simulated and observed data, but the optimised models are often inaccurate, uncertain, and non-unique. In this paper, we take a fresh look at ASHM and view it from the perspective of the fitness landscape, or search space. We propose that characterising the fitness landscape will lead to a deeper understanding of the problem, greater confidence in the optimised models, and a better appreciation of the uncertainties. Fitness landscape analysis (FLA) is established in other fields, but has mostly been applied to combinatorial problems or continuous problems with analytical solutions. In contrast, ASHM is a real-world, ill-posed, inverse problem, which is computationally expensive and contains data errors and model uncertainties. We introduce a new method for FLA that provides intuitive information on the setup of the problem. It uses multidimensional clustering and visualisation to explore the structure of the landscape and detects the presence and relative magnitude of data errors, which are typical of real data. It is applied to a synthetic, full-field, reservoir model and the results are compared with another more-established method. We found that the fitness landscapes of ASHM problems are low-lying plateaus with many minima, which makes it difficult to solve ASHM problems for real-world datasets.","PeriodicalId":54820,"journal":{"name":"Journal of Geophysics and Engineering","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135098288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Porosity prediction from seismic data is of considerable importance in reservoir quality assessment, geological model building, and flow unit delineation. Deep learning approaches have demonstrated great potential in reservoir characterization due to their strong feature extraction and nonlinear relationship mapping abilities. However, the reliability of porosity prediction is often compromised by the lack of low-frequency information in bandlimited seismic data. To address this issue, we propose incorporating a low-frequency porosity model based on geostatistical methodology, into the supervised convolutional neural network to predict porosity from prestack seismic angle gather and seismic inversion results. Our study demonstrates that the inclusion of the low-frequency porosity model significantly improves the reliability of porosity predictions in a heterogeneous carbonate reservoir. The low-frequency information can be compensated to enhance the network's capabilities of capturing the background porosity trend. Additionally, the blind well tests validate that considering the low-frequency constraint leads to stronger model prediction and generalization abilities, with the root mean square error (RMSE) of the two blind wells reduced by up to 34%. The incorporation of the low-frequency reservoir model in network training also remarkably enhances the geological continuity of seismic porosity prediction, providing more geologically reasonable results for reservoir characterization.
{"title":"Porosity prediction from prestack seismic data via deep learning: Incorporating low-frequency porosity model","authors":"Jingyu Liu, Luanxiao Zhao, Minghui Xu, Xiangyuan Zhao, Yuchun You, J. Geng","doi":"10.1093/jge/gxad063","DOIUrl":"https://doi.org/10.1093/jge/gxad063","url":null,"abstract":"\u0000 Porosity prediction from seismic data is of considerable importance in reservoir quality assessment, geological model building, and flow unit delineation. Deep learning approaches have demonstrated great potential in reservoir characterization due to their strong feature extraction and nonlinear relationship mapping abilities. However, the reliability of porosity prediction is often compromised by the lack of low-frequency information in bandlimited seismic data. To address this issue, we propose incorporating a low-frequency porosity model based on geostatistical methodology, into the supervised convolutional neural network to predict porosity from prestack seismic angle gather and seismic inversion results. Our study demonstrates that the inclusion of the low-frequency porosity model significantly improves the reliability of porosity predictions in a heterogeneous carbonate reservoir. The low-frequency information can be compensated to enhance the network's capabilities of capturing the background porosity trend. Additionally, the blind well tests validate that considering the low-frequency constraint leads to stronger model prediction and generalization abilities, with the root mean square error (RMSE) of the two blind wells reduced by up to 34%. The incorporation of the low-frequency reservoir model in network training also remarkably enhances the geological continuity of seismic porosity prediction, providing more geologically reasonable results for reservoir characterization.","PeriodicalId":54820,"journal":{"name":"Journal of Geophysics and Engineering","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46506568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kai Zhan, Xiaotao Wen, Xuben Wang, Ping Song, Chao Kong, Atao Li
Accurate temporal resolution of the eikonal equation forms the cornerstone of seismological studies, including microseismic source localization and traveltime tomography. Physics Informed Neural Networks (PINNs) has gained significant attention as an efficient approximation technique for numerical computations. In this study, we put forth a novel model named Eiko-PIGCNet, a Graph Convolutional Neural Network that incorporates physical constraints. We demonstrate the effectiveness of our proposed model in solving the 3D eikonal equation for travel time estimation. In our approach, the discretized grid points are converted into a graph data structure, where every grid point is regarded as a node, and the neighboring nodes are interconnected via edges. The node characteristics are defined by incorporating the velocity and spatial coordinates of the respective grid points. Ultimately, the efficacy of the Eiko-PIGCNet and PINNs is evaluated and compared under various velocity models. The results reveal that Eiko-PIGCNet outshines PINNs in terms of solution accuracy and computational efficiency.
{"title":"Graphical neural networks based on physical information constraints for solving the eikonal equation","authors":"Kai Zhan, Xiaotao Wen, Xuben Wang, Ping Song, Chao Kong, Atao Li","doi":"10.1093/jge/gxad061","DOIUrl":"https://doi.org/10.1093/jge/gxad061","url":null,"abstract":"\u0000 Accurate temporal resolution of the eikonal equation forms the cornerstone of seismological studies, including microseismic source localization and traveltime tomography. Physics Informed Neural Networks (PINNs) has gained significant attention as an efficient approximation technique for numerical computations. In this study, we put forth a novel model named Eiko-PIGCNet, a Graph Convolutional Neural Network that incorporates physical constraints. We demonstrate the effectiveness of our proposed model in solving the 3D eikonal equation for travel time estimation. In our approach, the discretized grid points are converted into a graph data structure, where every grid point is regarded as a node, and the neighboring nodes are interconnected via edges. The node characteristics are defined by incorporating the velocity and spatial coordinates of the respective grid points. Ultimately, the efficacy of the Eiko-PIGCNet and PINNs is evaluated and compared under various velocity models. The results reveal that Eiko-PIGCNet outshines PINNs in terms of solution accuracy and computational efficiency.","PeriodicalId":54820,"journal":{"name":"Journal of Geophysics and Engineering","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42267719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bin Wang, Jie Zhang, Xiao Hua Qi, Tong Li, Shou Shi Gao, Li Wang
Here, we analyze the instability characteristics of the overlying strata structure that characterize shallow-depth seams under insufficient goaf in Yushenfu mining area. To simulate the No. 20107 longwall interval working face situated in Nanliang Coal Mine, physical simulation, an acoustic emission (AE) monitoring system, a stress acquisition system and a total station were used. The results indicate that during interval goaf formation, which is correlated with mining, the immediate roof collapses, and the main roof strata remains stable. Gradually, the stress that acts on the temporary coal pillar (TCP) gradually exhibits the ‘uniform increase–accelerated increase catastrophe instability’ change characteristics. Due to the concentrated load of the overlying strata, the bearing capacity of the TCP gradually deteriorates until the catastrophic instability occurs, and the unstable roof strata forms a ‘W-shaped voussoir beam’ structure. The research results provide evidence for the strata control that is associated with shallow-seam mining.
{"title":"Experimental research on the instability characteristics of the overlying strata structure that characterizes shallow interval goaf mining","authors":"Bin Wang, Jie Zhang, Xiao Hua Qi, Tong Li, Shou Shi Gao, Li Wang","doi":"10.1093/jge/gxad048","DOIUrl":"https://doi.org/10.1093/jge/gxad048","url":null,"abstract":"Here, we analyze the instability characteristics of the overlying strata structure that characterize shallow-depth seams under insufficient goaf in Yushenfu mining area. To simulate the No. 20107 longwall interval working face situated in Nanliang Coal Mine, physical simulation, an acoustic emission (AE) monitoring system, a stress acquisition system and a total station were used. The results indicate that during interval goaf formation, which is correlated with mining, the immediate roof collapses, and the main roof strata remains stable. Gradually, the stress that acts on the temporary coal pillar (TCP) gradually exhibits the ‘uniform increase–accelerated increase catastrophe instability’ change characteristics. Due to the concentrated load of the overlying strata, the bearing capacity of the TCP gradually deteriorates until the catastrophic instability occurs, and the unstable roof strata forms a ‘W-shaped voussoir beam’ structure. The research results provide evidence for the strata control that is associated with shallow-seam mining.","PeriodicalId":54820,"journal":{"name":"Journal of Geophysics and Engineering","volume":"106 3","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138525521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chunyang Pei, Shi Linge, Shiheng Li, Xiaohua Zhou, Long Yun, Zubin Chen
Reverse-time migration (RTM) is a well-established imaging technique that utilizes the two-way wave equation to achieve high-resolution imaging of complex subsurface media. However, when using RTM for reverse time extrapolation, a source wavefield needs to be stored for cross-correlation with the backward wavefield. This requirement results in a significant storage burden on computer memory. This paper introduces a wavefield reconstruction method that combines sparse representation to compress a substantial amount of crucial information in the source wavefield. The method utilizes the K-SVD algorithm to train an adaptive dictionary, learned from a training dataset consisting of wavefield image patches. For each timestep, the source wavefield is divided into image patches, which are then transformed into a series of sparse coefficients using the trained dictionary via the batch-OMP algorithm, known for its accelerated sparse coding process. This novel method essentially attempts to transform the wavefield domain into the sparse domain to reduce the storage burden. We utilized several evaluation metrics to explore the impact of parameters on performance. We conducted numerical experiments using acoustic RTM and compared two RTM methods employing checkpointing techniques with two strategies from our proposed method. Additionally, we extended the application of our method to elastic RTM. The conducted tests demonstrate that the method proposed in this paper can efficiently compress wavefield data, while considering both computational efficiency and reconstruction accuracy.
{"title":"A novel wavefield reconstruction method using sparse representation and dictionary learning for RTM","authors":"Chunyang Pei, Shi Linge, Shiheng Li, Xiaohua Zhou, Long Yun, Zubin Chen","doi":"10.1093/jge/gxad059","DOIUrl":"https://doi.org/10.1093/jge/gxad059","url":null,"abstract":"\u0000 Reverse-time migration (RTM) is a well-established imaging technique that utilizes the two-way wave equation to achieve high-resolution imaging of complex subsurface media. However, when using RTM for reverse time extrapolation, a source wavefield needs to be stored for cross-correlation with the backward wavefield. This requirement results in a significant storage burden on computer memory. This paper introduces a wavefield reconstruction method that combines sparse representation to compress a substantial amount of crucial information in the source wavefield. The method utilizes the K-SVD algorithm to train an adaptive dictionary, learned from a training dataset consisting of wavefield image patches. For each timestep, the source wavefield is divided into image patches, which are then transformed into a series of sparse coefficients using the trained dictionary via the batch-OMP algorithm, known for its accelerated sparse coding process. This novel method essentially attempts to transform the wavefield domain into the sparse domain to reduce the storage burden. We utilized several evaluation metrics to explore the impact of parameters on performance. We conducted numerical experiments using acoustic RTM and compared two RTM methods employing checkpointing techniques with two strategies from our proposed method. Additionally, we extended the application of our method to elastic RTM. The conducted tests demonstrate that the method proposed in this paper can efficiently compress wavefield data, while considering both computational efficiency and reconstruction accuracy.","PeriodicalId":54820,"journal":{"name":"Journal of Geophysics and Engineering","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46987239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Acoustic wave features, including the velocity dispersion and attenuation, induced by fluid flow in porous media have attracted significant attention in reservoir exploration. To enhance the quantitative understanding of these features, various wave propagation mechanisms have been developed. It has been discovered that wave dispersion and attenuation are associated with multiple reservoir parameters, each with different sensitivity. It is difficult to distinguish the impacts of individual physical parameter on acoustic features by the traditional wave equations. Considering the ability of deep neural networks (DNNs) in establishing the relationships between two datasets, a fully connected DNN has been employed as a surrogate rock physics model, and the Shapley Additive exPlanations model (SHAP) based on this DNN has been introduced to evaluate the contributions of different parameters. In this study, the classic White model is utilized to generate datasets for training the DNN. Datasets include seven parameters (bulk modulus, shear modulus, and density of the solid matrix, frequency, porosity, fluid saturation, and permeability), along with velocity dispersion and attenuation. By embedding SHAP into the trained DNN, the presented ShaRock algorithm allows for a clear quantification of the contributions of various reservoir parameters to acoustic features. Furthermore, we analyse the underlying interactions between two parameters by utilizing their combined quantified contributions to the features. The application of this proposed algorithm, which is based on wave propagation mechanisms, demonstrates its potential in providing valuable insights for parameter inversions in hydrocarbon exploration.
{"title":"Parameter interpretations of wave dispersion and attenuation in rock physics based on deep neural network","authors":"Bochen Wang, Jiawei Liu, Zhenwei Guo","doi":"10.1093/jge/gxad058","DOIUrl":"https://doi.org/10.1093/jge/gxad058","url":null,"abstract":"\u0000 Acoustic wave features, including the velocity dispersion and attenuation, induced by fluid flow in porous media have attracted significant attention in reservoir exploration. To enhance the quantitative understanding of these features, various wave propagation mechanisms have been developed. It has been discovered that wave dispersion and attenuation are associated with multiple reservoir parameters, each with different sensitivity. It is difficult to distinguish the impacts of individual physical parameter on acoustic features by the traditional wave equations. Considering the ability of deep neural networks (DNNs) in establishing the relationships between two datasets, a fully connected DNN has been employed as a surrogate rock physics model, and the Shapley Additive exPlanations model (SHAP) based on this DNN has been introduced to evaluate the contributions of different parameters. In this study, the classic White model is utilized to generate datasets for training the DNN. Datasets include seven parameters (bulk modulus, shear modulus, and density of the solid matrix, frequency, porosity, fluid saturation, and permeability), along with velocity dispersion and attenuation. By embedding SHAP into the trained DNN, the presented ShaRock algorithm allows for a clear quantification of the contributions of various reservoir parameters to acoustic features. Furthermore, we analyse the underlying interactions between two parameters by utilizing their combined quantified contributions to the features. The application of this proposed algorithm, which is based on wave propagation mechanisms, demonstrates its potential in providing valuable insights for parameter inversions in hydrocarbon exploration.","PeriodicalId":54820,"journal":{"name":"Journal of Geophysics and Engineering","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45545371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiaohui Yang, Zhengliang Lin, Xinchao Yang, Zhanguo Chen, Wenpeng Si
Traditional ground micro-seismic monitoring is performed by laying long survey lines. This is expensive and difficult to implement in complex mountainous areas and deep marine shale gas reservoirs in China. To address these challenges, this study has proposed a ground micro-seismic monitoring method using a sparse planar array that offers greater flexibility in implementation. This study has presented a weak signal enhancement method based on a broadband array adaptive beamforming algorithm to improve the signal-to-noise ratio (SNR) of micro-seismic data collected by sparse planar arrays and to suppress coherent noise. The proposed method involves establishing a signal model for a broadband planar array, estimating the direction of arrival (DOA) of broadband signals using a grid search method, and setting constraint conditions and objective functions based on the DOA results. The optimal weight vector is then calculated by solving the objective function to obtain the desired signal and suppress noise. This study has demonstrated that the proposed method effectively improved the SNR and suppressed coherent noise in synthetic and real data. It has also highlighted the effectiveness of the sparse planar array as a ground micro-seismic monitoring method and the adaptive broadband beamforming method as a practical weak signal enhancement technology.
{"title":"Micro-seismic monitoring using sparse planar array and a weak signal enhancement method","authors":"Xiaohui Yang, Zhengliang Lin, Xinchao Yang, Zhanguo Chen, Wenpeng Si","doi":"10.1093/jge/gxad060","DOIUrl":"https://doi.org/10.1093/jge/gxad060","url":null,"abstract":"\u0000 Traditional ground micro-seismic monitoring is performed by laying long survey lines. This is expensive and difficult to implement in complex mountainous areas and deep marine shale gas reservoirs in China. To address these challenges, this study has proposed a ground micro-seismic monitoring method using a sparse planar array that offers greater flexibility in implementation. This study has presented a weak signal enhancement method based on a broadband array adaptive beamforming algorithm to improve the signal-to-noise ratio (SNR) of micro-seismic data collected by sparse planar arrays and to suppress coherent noise. The proposed method involves establishing a signal model for a broadband planar array, estimating the direction of arrival (DOA) of broadband signals using a grid search method, and setting constraint conditions and objective functions based on the DOA results. The optimal weight vector is then calculated by solving the objective function to obtain the desired signal and suppress noise. This study has demonstrated that the proposed method effectively improved the SNR and suppressed coherent noise in synthetic and real data. It has also highlighted the effectiveness of the sparse planar array as a ground micro-seismic monitoring method and the adaptive broadband beamforming method as a practical weak signal enhancement technology.","PeriodicalId":54820,"journal":{"name":"Journal of Geophysics and Engineering","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42029814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：