Hyungjoo Lee, Alexander M. Mitkus, Andrew Pare, Kenneth McCarthy, Marc Willerth, Paul Reynerson, Tannor Ziehm, Timothy Gee
Triple-combo logs are important measurements for estimating geological, petrophysical, and geomechanical properties. Unfortunately, wireline and advanced logging-while-drilling (LWD) logs are typically dropped from the formation evaluation plan for unconventional wells due to economic constraints or borehole instability risks. Available measurements are typically measurement-while-drilling (MWD) gamma ray (GR) logs, along with surface measurements such as weight on bit (WOB), rate of penetration (ROP), torque, rotation per minute (RPM), and differential pressure. The development of a robust and rapid model for predicting reservoir properties using this limited data set would be of high value for geological evaluation. Estimating such properties is a challenging task due to the nonlinear relationship between the available log data and unknown reservoir properties. A novel workflow that combines two sequential models is presented. First is a machine-learning (ML) algorithm to predict triple-combo logs from drilling dynamics and GR logs. To train the ML algorithm, well logs obtained from multiple wells located in the Eagle Ford and Permian Basins are scrutinized to identify important features. This process includes depth shifting, outlier detection, and feature selection, which allows for strategic hyperparameter tuning. Several regression algorithms are investigated, and it is found that gradient boosting algorithms yield superior prediction performance. Unlike random forest methods, boosting algorithms train predictors sequentially, each trying to correct its predecessor. After triple-combo logs are predicted from MWD logs, a physics-based joint inversion model is applied to estimate various reservoir properties. The trained model is deployed on a blind test well, and the predicted logs show excellent agreement compared to the corresponding triple-combo measurements. The multimineral inversion using predicted triple-combo logs yields a geologic model that is validated with elemental capture spectroscopy (ECS) measurements. Additionally, reconstructed logs from the forward model closely match measured logs by minimizing the cost function. Therefore, real-time estimated geological, petrophysical, and geomechanical properties can reveal complex geologic information and be used to mitigate uncertainty related to drilling optimization, reservoir characterization, development planning, and reserve estimation. Using the MWD logs to predict triple-combo logs followed by a joint inversion is an innovative approach for geological evaluation with a limited data set. The developed workflow can successfully provide (1) geologic lithofacies identification and rock typing, (2) more confidence in real-time drilling operation, (3) reservoir properties prediction, (4) missing log imputations and pseudo-log generation with forward modeling, (5) guidance for future logging and perforation, (6) reference for seismic quantitative interpretation (QI) and well tie, and (
三重组合测井是估算地质、岩石物理和地质力学属性的重要测量手段。遗憾的是，由于经济限制或井眼不稳定风险，非常规油井的地层评估计划通常不包括有线和先进的随钻测井（LWD）测井。可用的测量方法通常是边钻井边测量（MWD）伽马射线（GR）测井，以及地面测量，如钻头重量（WOB）、穿透率（ROP）、扭矩、每分钟转速（RPM）和压差。利用这些有限的数据集，开发一个稳健、快速的储层属性预测模型，对地质评估具有很高的价值。由于可用测井数据与未知储层属性之间存在非线性关系，因此估算此类属性是一项极具挑战性的任务。本文介绍了一种结合两种连续模型的新型工作流程。首先是一种机器学习（ML）算法，用于根据钻井动态和 GR 测井曲线预测三重组合测井曲线。为了训练 ML 算法，对从位于鹰福特盆地和二叠纪盆地的多口油井获得的测井曲线进行了仔细检查，以确定重要特征。这一过程包括深度移动、离群点检测和特征选择，从而对超参数进行战略性调整。对几种回归算法进行了研究，发现梯度提升算法的预测性能更优越。与随机森林方法不同的是，提升算法是按顺序训练预测器，每个预测器都会尝试修正前一个预测器。从 MWD 测井曲线预测出三重组合测井曲线后，应用基于物理的联合反演模型来估计各种储层属性。将训练有素的模型应用于盲测井，预测的测井结果与相应的三重组合测井结果显示出极好的一致性。使用预测的三重组合测井结果进行多矿物反演，可以得到一个地质模型，该模型与元素捕获光谱（ECS）测量结果进行了验证。此外，通过最小化成本函数，前向模型重建的测井与测量测井非常匹配。因此，实时估算的地质、岩石物理和地质力学属性可以揭示复杂的地质信息，并用于减轻与钻井优化、储层特征描述、开发规划和储量估算相关的不确定性。利用 MWD 测井预测三重组合测井，然后进行联合反演，是利用有限数据集进行地质评估的一种创新方法。所开发的工作流程可成功提供：（1）地质岩性识别和岩石分型；（2）增强实时钻井操作的信心；（3）储层属性预测；（4）缺失测井推算和利用前向建模生成伪测井；（5）为未来测井和射孔提供指导；（6）为地震定量解释（QI）和井系提供参考；（7）可将大量计算时间从数天节省到数分钟。
{"title":"A New Workflow for Estimating Reservoir Properties With Gradient Boosting Model and Joint Inversion Using MWD Measurements","authors":"Hyungjoo Lee, Alexander M. Mitkus, Andrew Pare, Kenneth McCarthy, Marc Willerth, Paul Reynerson, Tannor Ziehm, Timothy Gee","doi":"10.30632/pjv65n2-2024a5","DOIUrl":"https://doi.org/10.30632/pjv65n2-2024a5","url":null,"abstract":"Triple-combo logs are important measurements for estimating geological, petrophysical, and geomechanical properties. Unfortunately, wireline and advanced logging-while-drilling (LWD) logs are typically dropped from the formation evaluation plan for unconventional wells due to economic constraints or borehole instability risks. Available measurements are typically measurement-while-drilling (MWD) gamma ray (GR) logs, along with surface measurements such as weight on bit (WOB), rate of penetration (ROP), torque, rotation per minute (RPM), and differential pressure. The development of a robust and rapid model for predicting reservoir properties using this limited data set would be of high value for geological evaluation. Estimating such properties is a challenging task due to the nonlinear relationship between the available log data and unknown reservoir properties. A novel workflow that combines two sequential models is presented. First is a machine-learning (ML) algorithm to predict triple-combo logs from drilling dynamics and GR logs. To train the ML algorithm, well logs obtained from multiple wells located in the Eagle Ford and Permian Basins are scrutinized to identify important features. This process includes depth shifting, outlier detection, and feature selection, which allows for strategic hyperparameter tuning. Several regression algorithms are investigated, and it is found that gradient boosting algorithms yield superior prediction performance. Unlike random forest methods, boosting algorithms train predictors sequentially, each trying to correct its predecessor. After triple-combo logs are predicted from MWD logs, a physics-based joint inversion model is applied to estimate various reservoir properties. The trained model is deployed on a blind test well, and the predicted logs show excellent agreement compared to the corresponding triple-combo measurements. The multimineral inversion using predicted triple-combo logs yields a geologic model that is validated with elemental capture spectroscopy (ECS) measurements. Additionally, reconstructed logs from the forward model closely match measured logs by minimizing the cost function. Therefore, real-time estimated geological, petrophysical, and geomechanical properties can reveal complex geologic information and be used to mitigate uncertainty related to drilling optimization, reservoir characterization, development planning, and reserve estimation. Using the MWD logs to predict triple-combo logs followed by a joint inversion is an innovative approach for geological evaluation with a limited data set. The developed workflow can successfully provide (1) geologic lithofacies identification and rock typing, (2) more confidence in real-time drilling operation, (3) reservoir properties prediction, (4) missing log imputations and pseudo-log generation with forward modeling, (5) guidance for future logging and perforation, (6) reference for seismic quantitative interpretation (QI) and well tie, and (","PeriodicalId":170688,"journal":{"name":"Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description","volume":"504 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140773492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Due to the micro/nanoscale and intricate pore structure, poor connectivity, complex pathways, the presence of microfractures, and the coexistence of organic and inorganic pores, shale and other tight reservoirs exhibit increasingly complex conductive characteristics. This paper mainly studied the electrical properties of shale based on experimental test data, including scanning electron microscope (SEM) thin-section and microtomography CT (μ-CT) images, and analyzed the shale pore type, pore structure characteristics, and development of fracture. Then, the distribution of pyrite, content, and graphitization of organics and their influence on the electrical properties are discussed. Furthermore, the double electrical layer and zeta potential in the shale zone were discussed in depth. The results revealed that, within the content of pyrite, organics, and its graphitization, the vitrinite maturity are inversely proportional to shale resistivity. It was also found that in the presence of an external electromagnetic field, the fluid in shale pores is subjected to the combined strength of pore pressure and external field potential difference. Thus, its response equation should be an improved Navier-Stokes equation, which considers pore pressure, zeta potential, and Coulomb force. When shale is subjected to an external electromagnetic field, due to the complex pores structure and organic and inorganic minerals, it will represent more of a dielectric-like property than electricity. So, it will form special microscopic ionic capacitors, which are different from common plate capacitors. There are three special kinds of microscopic ionic capacitors, they are (I) the intergranular pore microscopic ionic capacitor model, (II) the particle with isolated pore microscopic ionic capacitor model, and (III) the pyrite or graphite or other organics microscopic ionic capacitor model. Finally, the characteristics of microscopic ion capacitors are summarized: irregular polar area and varying distance between poles, varying charges with time, and salinity of the formation water.
{"title":"Study on Electrical Characteristics and Formation Mechanism of Micro-Ion Capacitor in Shale Pore and Fracture Structure","authors":"Hongqi Liu, Haibo Liao, Zhanshan Xiao, Shanjun Li, Liquan Ran, Dong Chen","doi":"10.30632/pjv65n2-2024a2","DOIUrl":"https://doi.org/10.30632/pjv65n2-2024a2","url":null,"abstract":"Due to the micro/nanoscale and intricate pore structure, poor connectivity, complex pathways, the presence of microfractures, and the coexistence of organic and inorganic pores, shale and other tight reservoirs exhibit increasingly complex conductive characteristics. This paper mainly studied the electrical properties of shale based on experimental test data, including scanning electron microscope (SEM) thin-section and microtomography CT (μ-CT) images, and analyzed the shale pore type, pore structure characteristics, and development of fracture. Then, the distribution of pyrite, content, and graphitization of organics and their influence on the electrical properties are discussed. Furthermore, the double electrical layer and zeta potential in the shale zone were discussed in depth. The results revealed that, within the content of pyrite, organics, and its graphitization, the vitrinite maturity are inversely proportional to shale resistivity. It was also found that in the presence of an external electromagnetic field, the fluid in shale pores is subjected to the combined strength of pore pressure and external field potential difference. Thus, its response equation should be an improved Navier-Stokes equation, which considers pore pressure, zeta potential, and Coulomb force. When shale is subjected to an external electromagnetic field, due to the complex pores structure and organic and inorganic minerals, it will represent more of a dielectric-like property than electricity. So, it will form special microscopic ionic capacitors, which are different from common plate capacitors. There are three special kinds of microscopic ionic capacitors, they are (I) the intergranular pore microscopic ionic capacitor model, (II) the particle with isolated pore microscopic ionic capacitor model, and (III) the pyrite or graphite or other organics microscopic ionic capacitor model. Finally, the characteristics of microscopic ion capacitors are summarized: irregular polar area and varying distance between poles, varying charges with time, and salinity of the formation water.","PeriodicalId":170688,"journal":{"name":"Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description","volume":"28 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140765945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yan Zhang, Yiqiao Song, Sihui Luo, Tingting Lin, Huabing Liu
Core analysis is critical for oil and gas exploration and recovery. Nuclear magnetic resonance (NMR) has been widely applied to the petroleum industry for many years, and NMR core analysis plays an important role in supporting borehole NMR formation evaluation and understanding the mechanisms of petrophysics and petrochemistry. It’s unfortunate, however, that there has been a lack of commented descriptions of the basic procedures for NMR rock core analysis in the literature, which has led to issues of comparability and repeatability of NMR measurements between different laboratories. In this paper, we present a brief guideline for NMR rock core analysis of conventional T2, T1, T1-T2, and D-T2 measurements. As an established procedure in daily laboratory work, NMR core analysis includes three sophisticated steps: rock sample preparation, an NMR experiment, and data analysis. The acquisition and saturation of rock samples are described, and corresponding solutions are also considered. Detailed NMR experimental measurements, data setting, and calibration are addressed. Laplace inversion for different NMR experiments and models for estimation of porosity, irreducible water, permeability, pore structure, and oil saturation are included. The aim of this paper is to try to standardize general NMR experiments for rock core analysis.
{"title":"Core Analysis Using Nuclear Magnetic Resonance","authors":"Yan Zhang, Yiqiao Song, Sihui Luo, Tingting Lin, Huabing Liu","doi":"10.30632/pjv65n2-2024a3","DOIUrl":"https://doi.org/10.30632/pjv65n2-2024a3","url":null,"abstract":"Core analysis is critical for oil and gas exploration and recovery. Nuclear magnetic resonance (NMR) has been widely applied to the petroleum industry for many years, and NMR core analysis plays an important role in supporting borehole NMR formation evaluation and understanding the mechanisms of petrophysics and petrochemistry. It’s unfortunate, however, that there has been a lack of commented descriptions of the basic procedures for NMR rock core analysis in the literature, which has led to issues of comparability and repeatability of NMR measurements between different laboratories. In this paper, we present a brief guideline for NMR rock core analysis of conventional T2, T1, T1-T2, and D-T2 measurements. As an established procedure in daily laboratory work, NMR core analysis includes three sophisticated steps: rock sample preparation, an NMR experiment, and data analysis. The acquisition and saturation of rock samples are described, and corresponding solutions are also considered. Detailed NMR experimental measurements, data setting, and calibration are addressed. Laplace inversion for different NMR experiments and models for estimation of porosity, irreducible water, permeability, pore structure, and oil saturation are included. The aim of this paper is to try to standardize general NMR experiments for rock core analysis.","PeriodicalId":170688,"journal":{"name":"Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description","volume":"23 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140765989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, through the permeability test of granite under different temperature cycles, the change law of porosity and permeability of rock samples after different temperature cycles was studied, and the relationship between the P-wave velocity and porosity and permeability was established by regression analysis. The results show that the porosity and permeability of the granite samples decreased significantly in one to three high-temperature cycles, showing a logarithmic change, and with the increase of the number of cycles, the decreasing rate gradually decreased after five to 10 thermal cycles, which is beneficial to the long-term development of deep geothermal resources. Under thermal cycles at different temperatures, the P-wave velocity of granite has a logarithmic correlation with permeability and porosity. As the number of cycles increases, the relationship between permeability, porosity, and P-wave velocity changes from a logarithmic relationship between one to three cycles to a linear relationship between five to 10 cycles. After thermal cycle treatment at different temperatures, there is an excellent logarithmic relationship between the P-wave velocity and porosity and permeability, and it has a high correlation. The porosity and permeability of granite can be estimated nondestructively by measuring the wave velocity. Using a scanning electron microscope (SEM) to observe the granite at 450℃, trivial particles appeared between the pore structure, and the internal structure of the rock sample was destroyed under the action of the thermal cycle. The change mechanism of physical property deterioration in deep geothermal energy mining is revealed, guiding deep geothermal energy mining.
本文通过花岗岩在不同温度循环下的渗透性试验，研究了岩石样品在不同温度循环后孔隙率和渗透率的变化规律，并通过回归分析建立了P波速度与孔隙率和渗透率之间的关系。结果表明，花岗岩样品的孔隙度和渗透率在一至三次高温循环中明显下降，呈对数变化，随着循环次数的增加，在五至十次热循环后下降速度逐渐减小，有利于深部地热资源的长期开发。在不同温度的热循环下，花岗岩的 P 波速度与渗透率和孔隙度呈对数相关。随着循环次数的增加，渗透率、孔隙率和 P 波速度之间的关系从 1 至 3 次循环之间的对数关系变为 5 至 10 次循环之间的线性关系。在不同温度下进行热循环处理后，P 波速度与孔隙度和渗透率之间存在很好的对数关系，并且具有很高的相关性。花岗岩的孔隙度和渗透率可以通过测量波速进行无损估算。使用扫描电子显微镜（SEM）在 450℃下观察花岗岩，孔隙结构之间出现微小颗粒，岩石样品的内部结构在热循环作用下遭到破坏。揭示了深部地热能开采中物理性质劣化的变化机理，对深部地热能开采具有指导意义。
{"title":"Experimental Research on the Permeability of Granite Under Different Temperature Cycles","authors":"Li Yu, Haonan Li, Yue Wu, Weihao Wang, Xinyuan Zhang, Yongchuan Zhao","doi":"10.30632/pjv65n1-2024a5","DOIUrl":"https://doi.org/10.30632/pjv65n1-2024a5","url":null,"abstract":"In this paper, through the permeability test of granite under different temperature cycles, the change law of porosity and permeability of rock samples after different temperature cycles was studied, and the relationship between the P-wave velocity and porosity and permeability was established by regression analysis. The results show that the porosity and permeability of the granite samples decreased significantly in one to three high-temperature cycles, showing a logarithmic change, and with the increase of the number of cycles, the decreasing rate gradually decreased after five to 10 thermal cycles, which is beneficial to the long-term development of deep geothermal resources. Under thermal cycles at different temperatures, the P-wave velocity of granite has a logarithmic correlation with permeability and porosity. As the number of cycles increases, the relationship between permeability, porosity, and P-wave velocity changes from a logarithmic relationship between one to three cycles to a linear relationship between five to 10 cycles. After thermal cycle treatment at different temperatures, there is an excellent logarithmic relationship between the P-wave velocity and porosity and permeability, and it has a high correlation. The porosity and permeability of granite can be estimated nondestructively by measuring the wave velocity. Using a scanning electron microscope (SEM) to observe the granite at 450℃, trivial particles appeared between the pore structure, and the internal structure of the rock sample was destroyed under the action of the thermal cycle. The change mechanism of physical property deterioration in deep geothermal energy mining is revealed, guiding deep geothermal energy mining.","PeriodicalId":170688,"journal":{"name":"Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description","volume":"108 5-6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139880067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lei Fu, Yanxiang Yu, Chicheng Xu, Michael Ashby, Andrew McDonald, Wen Pan, Tianqi Deng, István Szabó, Pál P. Hanzelik, Csilla Kalmár, Saleh Alatwah, Jaehyuk Lee
Well logs are processed and interpreted to estimate in-situ reservoir properties, which are essential for reservoir modeling, reserve estimation, and production forecasting. While the traditional methods are mostly based on multimineral physics or empirical formulae, machine learning provides an alternative data-driven approach that requires much less a-priori geological or petrophysical information. From October 2021 to March 2022, the Petrophysical Data-Driven Analytics Special Interest Group (PDDA SIG) of the Society of Petrophysicists and Well Log Analysts (SPWLA) hosted a machine-learning contest aiming to develop data-driven models for estimating reservoir properties, including shale volume, porosity, and fluid saturation, based on a common set of well logs, including gamma ray, bulk density, neutron porosity, resistivity, and sonic. Log data from nine wells from the same field, together with the interpreted reservoir properties by petrophysicists, were provided as training data, and five additional wells were provided as blind test data. During the contest, various data-driven models were developed by the contestants to predict the three reservoir properties with the provided training data set. The top five performing models from the contest, on average, beat the performance of the benchmarked Random Forest model by 45% in the root-mean-square error (RMSE) score. In the paper, we will review these top-performing solutions, including their preprocessing techniques, feature engineering, and machine-learning models, and summarize their advantages and conditions.
{"title":"Well-Log-Based Reservoir Property Estimation With Machine Learning: A Contest Summary","authors":"Lei Fu, Yanxiang Yu, Chicheng Xu, Michael Ashby, Andrew McDonald, Wen Pan, Tianqi Deng, István Szabó, Pál P. Hanzelik, Csilla Kalmár, Saleh Alatwah, Jaehyuk Lee","doi":"10.30632/pjv65n1-2024a6","DOIUrl":"https://doi.org/10.30632/pjv65n1-2024a6","url":null,"abstract":"Well logs are processed and interpreted to estimate in-situ reservoir properties, which are essential for reservoir modeling, reserve estimation, and production forecasting. While the traditional methods are mostly based on multimineral physics or empirical formulae, machine learning provides an alternative data-driven approach that requires much less a-priori geological or petrophysical information. From October 2021 to March 2022, the Petrophysical Data-Driven Analytics Special Interest Group (PDDA SIG) of the Society of Petrophysicists and Well Log Analysts (SPWLA) hosted a machine-learning contest aiming to develop data-driven models for estimating reservoir properties, including shale volume, porosity, and fluid saturation, based on a common set of well logs, including gamma ray, bulk density, neutron porosity, resistivity, and sonic. Log data from nine wells from the same field, together with the interpreted reservoir properties by petrophysicists, were provided as training data, and five additional wells were provided as blind test data. During the contest, various data-driven models were developed by the contestants to predict the three reservoir properties with the provided training data set. The top five performing models from the contest, on average, beat the performance of the benchmarked Random Forest model by 45% in the root-mean-square error (RMSE) score. In the paper, we will review these top-performing solutions, including their preprocessing techniques, feature engineering, and machine-learning models, and summarize their advantages and conditions.","PeriodicalId":170688,"journal":{"name":"Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description","volume":"21 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139686603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper is to update the information provided in the author’s previous papers on evaluating the uncertainty in least squares results. It is prompted by new information that shows that the usefulness of any least squares result cannot be guaranteed by conventional statistics (such as R-squared, F-statistic, or standard error of the regression, sigma). A new method based on the singular value decomposition (SVD) of a matrix, when accompanied by a Relative Error Bound (REB) on the estimated parameters, provides the user with a tool that can better assess the usefulness of any least squares result. Another important aspect of the REB is that it provides the user of the SVD method with a powerful tool for judging which is the best among several candidate solutions. In addition, it provides the user with a numerically stable method of computing the data ordinarily provided by principal component regression by eliminating the need to perform an eigenvector-eigenvalue analysis of an ATA matrix. This is of particular interest because forming the ATA matrix is often accompanied by a loss of data. The new method also provides the user with an improved method for selection of which principal components should be retained for a given problem.
本文旨在更新作者以前关于评估最小二乘法结果不确定性的论文中提供的信息。新信息表明，任何最小二乘法结果的有用性都无法通过常规统计（如 R 方、F 统计或回归标准误差 sigma）来保证。一种基于矩阵奇异值分解（SVD）的新方法，配合估计参数的相对误差约束（REB），为用户提供了一种可以更好地评估任何最小二乘法结果有用性的工具。REB 的另一个重要方面是，它为 SVD 方法的用户提供了一个强大的工具，用于判断几个候选方案中哪个是最佳方案。此外，由于无需对 ATA 矩阵进行特征向量-特征值分析，它还为用户提供了一种数值稳定的方法，用于计算主成分回归通常提供的数据。这一点尤为重要，因为形成 ATA 矩阵往往会导致数据丢失。新方法还为用户提供了一种改进的方法，用于选择在特定问题中应保留哪些主成分。
{"title":"Evaluating the Usefulness of Least Squares Regression in Petrophysics Interpretation","authors":"Lee Etnyre","doi":"10.30632/pjv65n1-2024a4","DOIUrl":"https://doi.org/10.30632/pjv65n1-2024a4","url":null,"abstract":"This paper is to update the information provided in the author’s previous papers on evaluating the uncertainty in least squares results. It is prompted by new information that shows that the usefulness of any least squares result cannot be guaranteed by conventional statistics (such as R-squared, F-statistic, or standard error of the regression, sigma). A new method based on the singular value decomposition (SVD) of a matrix, when accompanied by a Relative Error Bound (REB) on the estimated parameters, provides the user with a tool that can better assess the usefulness of any least squares result. Another important aspect of the REB is that it provides the user of the SVD method with a powerful tool for judging which is the best among several candidate solutions. In addition, it provides the user with a numerically stable method of computing the data ordinarily provided by principal component regression by eliminating the need to perform an eigenvector-eigenvalue analysis of an ATA matrix. This is of particular interest because forming the ATA matrix is often accompanied by a loss of data. The new method also provides the user with an improved method for selection of which principal components should be retained for a given problem.","PeriodicalId":170688,"journal":{"name":"Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description","volume":"85 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139823030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rock mechanics parameters are crucial factors for predicting rock behavior in oil and gas reservoirs, optimizing extraction strategies, and ensuring drilling safety. In this study, we propose a random forest (RF)-convolutional neural network (CNN)-long-term short-term memory network (LSTM) fusion model based on the dynamic time warping (DTW) algorithm to construct intelligent prediction models for elastic modulus, Poisson’s ratio, and compressive strength using real-time drilling engineering data. An autoencoder with a sliding window is employed to automatically identify abnormal points or segments in the calculated values of elastic modulus, Poisson’s ratio, and compressive strength obtained from drilled wells. These abnormal values are then corrected using a backpropagation (BP) neural network. Compared to single CNN-LSTM or single RF models, the RF-CNN-LSTM fusion model performs better. It achieves this by effectively combining the strengths of different algorithms in predicting outcomes. The accuracy of the RF-CNN-LSTM fusion model is over 94% when compared to the actual values. Furthermore, the analysis of the relative importance of input parameters reveals that weight on bit (WOB), temperature, displacement, equivalent circulation density (ECD), and mud density are the primary input features for predicting elastic modulus. For predicting Poisson’s ratio, the main input features include WOB, mud density, ECD, temperature, pumping pressure, displacement, and rate of penetration (ROP). Similarly, for predicting compressive strength, the main input features consist of WOB, temperature, displacement, ECD, and mud density. The research findings demonstrate that the rock mechanics parameter prediction models based on the RF-CNN-LSTM algorithm using DTW exhibit high computational accuracy in the B oil field of China. These results are significant for gaining a deeper understanding of the variations in rock mechanics parameters and optimizing drilling decisions.
{"title":"Study on Rock Mechanics Parameter Prediction Method Based on DTW Similarity and Machine-Learning Algorithms","authors":"Wenjun Cai, Jianqi Ding, Zhong Li, Zhiming Yin, Yongcun Feng","doi":"10.30632/pjv65n1-2024a7","DOIUrl":"https://doi.org/10.30632/pjv65n1-2024a7","url":null,"abstract":"Rock mechanics parameters are crucial factors for predicting rock behavior in oil and gas reservoirs, optimizing extraction strategies, and ensuring drilling safety. In this study, we propose a random forest (RF)-convolutional neural network (CNN)-long-term short-term memory network (LSTM) fusion model based on the dynamic time warping (DTW) algorithm to construct intelligent prediction models for elastic modulus, Poisson’s ratio, and compressive strength using real-time drilling engineering data. An autoencoder with a sliding window is employed to automatically identify abnormal points or segments in the calculated values of elastic modulus, Poisson’s ratio, and compressive strength obtained from drilled wells. These abnormal values are then corrected using a backpropagation (BP) neural network. Compared to single CNN-LSTM or single RF models, the RF-CNN-LSTM fusion model performs better. It achieves this by effectively combining the strengths of different algorithms in predicting outcomes. The accuracy of the RF-CNN-LSTM fusion model is over 94% when compared to the actual values. Furthermore, the analysis of the relative importance of input parameters reveals that weight on bit (WOB), temperature, displacement, equivalent circulation density (ECD), and mud density are the primary input features for predicting elastic modulus. For predicting Poisson’s ratio, the main input features include WOB, mud density, ECD, temperature, pumping pressure, displacement, and rate of penetration (ROP). Similarly, for predicting compressive strength, the main input features consist of WOB, temperature, displacement, ECD, and mud density. The research findings demonstrate that the rock mechanics parameter prediction models based on the RF-CNN-LSTM algorithm using DTW exhibit high computational accuracy in the B oil field of China. These results are significant for gaining a deeper understanding of the variations in rock mechanics parameters and optimizing drilling decisions.","PeriodicalId":170688,"journal":{"name":"Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description","volume":"23 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139879659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, through the permeability test of granite under different temperature cycles, the change law of porosity and permeability of rock samples after different temperature cycles was studied, and the relationship between the P-wave velocity and porosity and permeability was established by regression analysis. The results show that the porosity and permeability of the granite samples decreased significantly in one to three high-temperature cycles, showing a logarithmic change, and with the increase of the number of cycles, the decreasing rate gradually decreased after five to 10 thermal cycles, which is beneficial to the long-term development of deep geothermal resources. Under thermal cycles at different temperatures, the P-wave velocity of granite has a logarithmic correlation with permeability and porosity. As the number of cycles increases, the relationship between permeability, porosity, and P-wave velocity changes from a logarithmic relationship between one to three cycles to a linear relationship between five to 10 cycles. After thermal cycle treatment at different temperatures, there is an excellent logarithmic relationship between the P-wave velocity and porosity and permeability, and it has a high correlation. The porosity and permeability of granite can be estimated nondestructively by measuring the wave velocity. Using a scanning electron microscope (SEM) to observe the granite at 450℃, trivial particles appeared between the pore structure, and the internal structure of the rock sample was destroyed under the action of the thermal cycle. The change mechanism of physical property deterioration in deep geothermal energy mining is revealed, guiding deep geothermal energy mining.
本文通过花岗岩在不同温度循环下的渗透性试验，研究了岩石样品在不同温度循环后孔隙率和渗透率的变化规律，并通过回归分析建立了P波速度与孔隙率和渗透率之间的关系。结果表明，花岗岩样品的孔隙度和渗透率在一至三次高温循环中明显下降，呈对数变化，随着循环次数的增加，在五至十次热循环后下降速度逐渐减小，有利于深部地热资源的长期开发。在不同温度的热循环下，花岗岩的 P 波速度与渗透率和孔隙度呈对数相关。随着循环次数的增加，渗透率、孔隙率和 P 波速度之间的关系从 1 至 3 次循环之间的对数关系变为 5 至 10 次循环之间的线性关系。在不同温度下进行热循环处理后，P 波速度与孔隙度和渗透率之间存在很好的对数关系，并且具有很高的相关性。花岗岩的孔隙度和渗透率可以通过测量波速进行无损估算。使用扫描电子显微镜（SEM）在 450℃下观察花岗岩，孔隙结构之间出现微小颗粒，岩石样品的内部结构在热循环作用下遭到破坏。揭示了深部地热能开采中物理性质劣化的变化机理，对深部地热能开采具有指导意义。
{"title":"Experimental Research on the Permeability of Granite Under Different Temperature Cycles","authors":"Li Yu, Haonan Li, Yue Wu, Weihao Wang, Xinyuan Zhang, Yongchuan Zhao","doi":"10.30632/pjv65n1-2024a5","DOIUrl":"https://doi.org/10.30632/pjv65n1-2024a5","url":null,"abstract":"In this paper, through the permeability test of granite under different temperature cycles, the change law of porosity and permeability of rock samples after different temperature cycles was studied, and the relationship between the P-wave velocity and porosity and permeability was established by regression analysis. The results show that the porosity and permeability of the granite samples decreased significantly in one to three high-temperature cycles, showing a logarithmic change, and with the increase of the number of cycles, the decreasing rate gradually decreased after five to 10 thermal cycles, which is beneficial to the long-term development of deep geothermal resources. Under thermal cycles at different temperatures, the P-wave velocity of granite has a logarithmic correlation with permeability and porosity. As the number of cycles increases, the relationship between permeability, porosity, and P-wave velocity changes from a logarithmic relationship between one to three cycles to a linear relationship between five to 10 cycles. After thermal cycle treatment at different temperatures, there is an excellent logarithmic relationship between the P-wave velocity and porosity and permeability, and it has a high correlation. The porosity and permeability of granite can be estimated nondestructively by measuring the wave velocity. Using a scanning electron microscope (SEM) to observe the granite at 450℃, trivial particles appeared between the pore structure, and the internal structure of the rock sample was destroyed under the action of the thermal cycle. The change mechanism of physical property deterioration in deep geothermal energy mining is revealed, guiding deep geothermal energy mining.","PeriodicalId":170688,"journal":{"name":"Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description","volume":"162 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139820140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Successful in-situ fluid cleanup and sampling operations are commonly driven by a fast and reliable analysis of pressure, rate, and fluid contamination measurements. Techniques such as pressure transient analysis (PTA) provide important information to quantify reservoir complexity, while fluid contamination measurements are commonly overlooked for reservoir description purposes. We introduce a new interpretation technique to relate fluid contamination measurements with near-wellbore fluid-transport properties by identifying early- and late-time flow regimes in fluid contamination and its derivative function. The derivative methods used in PTA inspired the development of the new fluid contamination interpretation method. Contamination transient analysis (CTA) evaluates transient measurements acquired during cleanup of mud-filtrate invasion to infer important reservoir flow conditions. Center-point derivative methods are applied to the fluid pumpout volume and time evolution of fluid contamination to identify flow regimes in cases of water-based mud invading either water- or hydrocarbon-bearing formations. We document synthetic examples of the new interpretation method for seven reservoir cases, numerically simulated to obtain contamination data, namely, homogeneous isotropic reservoir, radial boundaries, vertical boundaries, thin-laminated formations, mud-filtrate invasion radius, petrophysical properties, and permeability anisotropy. Single-phase flow and multiphase flow cases are also compared in the analysis. Reservoir boundaries and features are identified in the flow regimes obtained from the combined interpretation of the fluid contamination derivative (FCD) and the log-log plot of the contamination transform. The seven reservoir cases assume fixed reservoir and operational parameters, such as reservoir geometry, rock properties, fluid properties, invasion radius, time of invasion, maximum pumpout rate, and maximum drawdown pressure, to allow for a controlled sensitivity analysis enabling the identification of cleanup trends. It is emphasized that real-time field conditions could trigger certain limitations of the transient techniques developed in this work, such as noisy downhole formation testing measurements, active mud-filtrate invasion, or tool failure. To validate the assumptions, observations, and results of the numerical simulations, a field case is examined to (a) highlight the value of CTA in real-time fluid sampling operations and (b) further investigate its limitations. An alternative validation of the method is performed by applying the derivative directly to the formation testing measurements during fluid cleanup, reducing the uncertainty in the contamination estimation and the interpretation of transient trends. The new approach of the FCD is an alternative to improve fluid cleanup efficiency and to detect the spatial complexity of the reservoir during real-time downhole fluid sampling. Using log-log plots of fluid contaminati
{"title":"Fluid Contamination Transient Analysis","authors":"Camilo Gelvez, C. Torres‐Verdín","doi":"10.30632/pjv65n1-2024a2","DOIUrl":"https://doi.org/10.30632/pjv65n1-2024a2","url":null,"abstract":"Successful in-situ fluid cleanup and sampling operations are commonly driven by a fast and reliable analysis of pressure, rate, and fluid contamination measurements. Techniques such as pressure transient analysis (PTA) provide important information to quantify reservoir complexity, while fluid contamination measurements are commonly overlooked for reservoir description purposes. We introduce a new interpretation technique to relate fluid contamination measurements with near-wellbore fluid-transport properties by identifying early- and late-time flow regimes in fluid contamination and its derivative function. The derivative methods used in PTA inspired the development of the new fluid contamination interpretation method. Contamination transient analysis (CTA) evaluates transient measurements acquired during cleanup of mud-filtrate invasion to infer important reservoir flow conditions. Center-point derivative methods are applied to the fluid pumpout volume and time evolution of fluid contamination to identify flow regimes in cases of water-based mud invading either water- or hydrocarbon-bearing formations. We document synthetic examples of the new interpretation method for seven reservoir cases, numerically simulated to obtain contamination data, namely, homogeneous isotropic reservoir, radial boundaries, vertical boundaries, thin-laminated formations, mud-filtrate invasion radius, petrophysical properties, and permeability anisotropy. Single-phase flow and multiphase flow cases are also compared in the analysis. Reservoir boundaries and features are identified in the flow regimes obtained from the combined interpretation of the fluid contamination derivative (FCD) and the log-log plot of the contamination transform. The seven reservoir cases assume fixed reservoir and operational parameters, such as reservoir geometry, rock properties, fluid properties, invasion radius, time of invasion, maximum pumpout rate, and maximum drawdown pressure, to allow for a controlled sensitivity analysis enabling the identification of cleanup trends. It is emphasized that real-time field conditions could trigger certain limitations of the transient techniques developed in this work, such as noisy downhole formation testing measurements, active mud-filtrate invasion, or tool failure. To validate the assumptions, observations, and results of the numerical simulations, a field case is examined to (a) highlight the value of CTA in real-time fluid sampling operations and (b) further investigate its limitations. An alternative validation of the method is performed by applying the derivative directly to the formation testing measurements during fluid cleanup, reducing the uncertainty in the contamination estimation and the interpretation of transient trends. The new approach of the FCD is an alternative to improve fluid cleanup efficiency and to detect the spatial complexity of the reservoir during real-time downhole fluid sampling. Using log-log plots of fluid contaminati","PeriodicalId":170688,"journal":{"name":"Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description","volume":"23 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139886030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Successful in-situ fluid cleanup and sampling operations are commonly driven by a fast and reliable analysis of pressure, rate, and fluid contamination measurements. Techniques such as pressure transient analysis (PTA) provide important information to quantify reservoir complexity, while fluid contamination measurements are commonly overlooked for reservoir description purposes. We introduce a new interpretation technique to relate fluid contamination measurements with near-wellbore fluid-transport properties by identifying early- and late-time flow regimes in fluid contamination and its derivative function. The derivative methods used in PTA inspired the development of the new fluid contamination interpretation method. Contamination transient analysis (CTA) evaluates transient measurements acquired during cleanup of mud-filtrate invasion to infer important reservoir flow conditions. Center-point derivative methods are applied to the fluid pumpout volume and time evolution of fluid contamination to identify flow regimes in cases of water-based mud invading either water- or hydrocarbon-bearing formations. We document synthetic examples of the new interpretation method for seven reservoir cases, numerically simulated to obtain contamination data, namely, homogeneous isotropic reservoir, radial boundaries, vertical boundaries, thin-laminated formations, mud-filtrate invasion radius, petrophysical properties, and permeability anisotropy. Single-phase flow and multiphase flow cases are also compared in the analysis. Reservoir boundaries and features are identified in the flow regimes obtained from the combined interpretation of the fluid contamination derivative (FCD) and the log-log plot of the contamination transform. The seven reservoir cases assume fixed reservoir and operational parameters, such as reservoir geometry, rock properties, fluid properties, invasion radius, time of invasion, maximum pumpout rate, and maximum drawdown pressure, to allow for a controlled sensitivity analysis enabling the identification of cleanup trends. It is emphasized that real-time field conditions could trigger certain limitations of the transient techniques developed in this work, such as noisy downhole formation testing measurements, active mud-filtrate invasion, or tool failure. To validate the assumptions, observations, and results of the numerical simulations, a field case is examined to (a) highlight the value of CTA in real-time fluid sampling operations and (b) further investigate its limitations. An alternative validation of the method is performed by applying the derivative directly to the formation testing measurements during fluid cleanup, reducing the uncertainty in the contamination estimation and the interpretation of transient trends. The new approach of the FCD is an alternative to improve fluid cleanup efficiency and to detect the spatial complexity of the reservoir during real-time downhole fluid sampling. Using log-log plots of fluid contaminati
{"title":"Fluid Contamination Transient Analysis","authors":"Camilo Gelvez, C. Torres‐Verdín","doi":"10.30632/pjv65n1-2024a2","DOIUrl":"https://doi.org/10.30632/pjv65n1-2024a2","url":null,"abstract":"Successful in-situ fluid cleanup and sampling operations are commonly driven by a fast and reliable analysis of pressure, rate, and fluid contamination measurements. Techniques such as pressure transient analysis (PTA) provide important information to quantify reservoir complexity, while fluid contamination measurements are commonly overlooked for reservoir description purposes. We introduce a new interpretation technique to relate fluid contamination measurements with near-wellbore fluid-transport properties by identifying early- and late-time flow regimes in fluid contamination and its derivative function. The derivative methods used in PTA inspired the development of the new fluid contamination interpretation method. Contamination transient analysis (CTA) evaluates transient measurements acquired during cleanup of mud-filtrate invasion to infer important reservoir flow conditions. Center-point derivative methods are applied to the fluid pumpout volume and time evolution of fluid contamination to identify flow regimes in cases of water-based mud invading either water- or hydrocarbon-bearing formations. We document synthetic examples of the new interpretation method for seven reservoir cases, numerically simulated to obtain contamination data, namely, homogeneous isotropic reservoir, radial boundaries, vertical boundaries, thin-laminated formations, mud-filtrate invasion radius, petrophysical properties, and permeability anisotropy. Single-phase flow and multiphase flow cases are also compared in the analysis. Reservoir boundaries and features are identified in the flow regimes obtained from the combined interpretation of the fluid contamination derivative (FCD) and the log-log plot of the contamination transform. The seven reservoir cases assume fixed reservoir and operational parameters, such as reservoir geometry, rock properties, fluid properties, invasion radius, time of invasion, maximum pumpout rate, and maximum drawdown pressure, to allow for a controlled sensitivity analysis enabling the identification of cleanup trends. It is emphasized that real-time field conditions could trigger certain limitations of the transient techniques developed in this work, such as noisy downhole formation testing measurements, active mud-filtrate invasion, or tool failure. To validate the assumptions, observations, and results of the numerical simulations, a field case is examined to (a) highlight the value of CTA in real-time fluid sampling operations and (b) further investigate its limitations. An alternative validation of the method is performed by applying the derivative directly to the formation testing measurements during fluid cleanup, reducing the uncertainty in the contamination estimation and the interpretation of transient trends. The new approach of the FCD is an alternative to improve fluid cleanup efficiency and to detect the spatial complexity of the reservoir during real-time downhole fluid sampling. Using log-log plots of fluid contaminati","PeriodicalId":170688,"journal":{"name":"Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description","volume":"180 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139825854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：