Reservoir rock textural properties such as grain size are typically estimated by direct visual observation of the physical texture of core samples. Grain size is one of the important inputs to petrophysical characterization, sedimentological facies classification, identification of depositional environments, and saturation models. A continuous log of grain size distribution over targeted reservoir sections is usually required for these applications. Core descriptions are typically not available over an entire targeted reservoir section. Physical core data may also be damaged during retrieval or due to plugging. Alternative methods proposed in literature are not sustainable due to their limitations in terms of input data requirements and inflexibility to apply them in environments with different geological settings. This paper presents the preliminary results of our investigation of a new methodology based on machine learning technology to complement and enhance the traditional core description and the alternative methods. We developed and optimized supervised machine learning models comprising K-nearest neighbor (KNN), support vector machines (SVM), and decision tree (DT) to indirectly estimate reservoir rock grain size for a new well or targeted reservoir sections from historical wireline logs and archival core descriptions. We used anonymized datasets consisting of nine wells from a clastic reservoir. Seven of the wells were used to train and optimize the models while the remaining two were reserved for validation. The grain size types range from clay to pebbles. The performance of the models confirmed the feasibility of this approach. The KNN, SVM, and DT models demonstrated the capability to estimate the grain size for the test wells by matching actual data with a minimum of 60% and close to 80% accuracy. This is an accomplishment taking into account the uncertainties inherent in the core analysis data. Further analysis of the results showed that the KNN model is the most accurate in performance compared to the other models. For future studies, we will explore more advanced classification algorithms and implement new class labeling strategies to improve the accuracy of this methodology. The attainment of this objective will further help to handle the complexity in the grain size estimation challenge and reduce the current turnaround time for core description.
{"title":"Indirect Estimation of Clastic Reservoir Rock Grain Size from Wireline Logs Using a Supervised Nearest Neighbor Algorithm: Preliminary Results","authors":"F. Anifowose, M. Mezghani, Saeed Saad Shahrani","doi":"10.2118/205156-ms","DOIUrl":"https://doi.org/10.2118/205156-ms","url":null,"abstract":"\u0000 Reservoir rock textural properties such as grain size are typically estimated by direct visual observation of the physical texture of core samples. Grain size is one of the important inputs to petrophysical characterization, sedimentological facies classification, identification of depositional environments, and saturation models. A continuous log of grain size distribution over targeted reservoir sections is usually required for these applications. Core descriptions are typically not available over an entire targeted reservoir section. Physical core data may also be damaged during retrieval or due to plugging.\u0000 Alternative methods proposed in literature are not sustainable due to their limitations in terms of input data requirements and inflexibility to apply them in environments with different geological settings. This paper presents the preliminary results of our investigation of a new methodology based on machine learning technology to complement and enhance the traditional core description and the alternative methods. We developed and optimized supervised machine learning models comprising K-nearest neighbor (KNN), support vector machines (SVM), and decision tree (DT) to indirectly estimate reservoir rock grain size for a new well or targeted reservoir sections from historical wireline logs and archival core descriptions.\u0000 We used anonymized datasets consisting of nine wells from a clastic reservoir. Seven of the wells were used to train and optimize the models while the remaining two were reserved for validation. The grain size types range from clay to pebbles. The performance of the models confirmed the feasibility of this approach. The KNN, SVM, and DT models demonstrated the capability to estimate the grain size for the test wells by matching actual data with a minimum of 60% and close to 80% accuracy. This is an accomplishment taking into account the uncertainties inherent in the core analysis data. Further analysis of the results showed that the KNN model is the most accurate in performance compared to the other models.\u0000 For future studies, we will explore more advanced classification algorithms and implement new class labeling strategies to improve the accuracy of this methodology. The attainment of this objective will further help to handle the complexity in the grain size estimation challenge and reduce the current turnaround time for core description.","PeriodicalId":10904,"journal":{"name":"Day 2 Tue, October 19, 2021","volume":"346 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76156119","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}
K. Goridko, A. R. Shabonas, R. Khabibullin, V. Verbitsky, A. V. Gladkov
Oil wells in Western Siberia usually placed on artificial drilling pads, forming well clusters up to 30 wells. The flow rate of each well in the cluster measured by an automatic measuring unit one by one. Often flow rate measurement requires several hours and flow rate of a single well can be measured once a week or less. This led to situation then events affecting well rate can be invisible between measurements. Identifying such events can be extremely useful in many cases, for example for wells with unstable behavior or transient regimes. The same challenges are also faced at distant green fields during their development, there the flow rates can be measured once a month with a mobile unit. The objective of this paper is to develop a virtual flowmeter model based on indirect high-frequency data of well operation and ESP. In Gubkin University, at the Petroleum Reservoir and Production Engineering Department, bench tests of ESP5-50 (118 radial stages) on gas-liquid mixture in a wide range of volumetric gas content (βin = 0-60%), intake pressure (Pin = 0.6-2.1 MPa) and pump shaft speed (n= 2400-3600 rpm) were performed. Three vibration sensors were installed on the unit: on the ESP, at the ESP discharge, on the pipeline, which simulates the wellhead production tree. During the bench tests were recorded series of pressures at the intake, discharge and along the pump length, series of current and power consumption, as well as vibrations with frequency several times per second. Based on the bench test results, we investigated the possibility of indirect determination of well operation parameters during artificial lift modelling by machine learning. As a result, the approaches to modelling taking into account various sets of parameters (features) have been studied: based on hydraulic parameters – ESP intake and outlet pressure;based on hydraulic and electric parameters – current and power consumption;based on hydraulic, electric and vibrating parameters. The analysis of data series allowed to define the boundaries of stable ESP operation, namely the transition to surging and pump starvation. The novelty of the work is: –machine learning modeling of the gas-liquid mixture pumping process by electric submersible pump;–solving both direct and inverse issues: as virtual liquid flowmeter as, virtual gas content flowmeter at the pump intake.
{"title":"Modelling of Electric Submersible Pump Work on Gas-Liquid Mixture by Machine Learning","authors":"K. Goridko, A. R. Shabonas, R. Khabibullin, V. Verbitsky, A. V. Gladkov","doi":"10.2118/208661-ms","DOIUrl":"https://doi.org/10.2118/208661-ms","url":null,"abstract":"\u0000 Oil wells in Western Siberia usually placed on artificial drilling pads, forming well clusters up to 30 wells. The flow rate of each well in the cluster measured by an automatic measuring unit one by one. Often flow rate measurement requires several hours and flow rate of a single well can be measured once a week or less. This led to situation then events affecting well rate can be invisible between measurements. Identifying such events can be extremely useful in many cases, for example for wells with unstable behavior or transient regimes. The same challenges are also faced at distant green fields during their development, there the flow rates can be measured once a month with a mobile unit. The objective of this paper is to develop a virtual flowmeter model based on indirect high-frequency data of well operation and ESP.\u0000 In Gubkin University, at the Petroleum Reservoir and Production Engineering Department, bench tests of ESP5-50 (118 radial stages) on gas-liquid mixture in a wide range of volumetric gas content (βin = 0-60%), intake pressure (Pin = 0.6-2.1 MPa) and pump shaft speed (n= 2400-3600 rpm) were performed. Three vibration sensors were installed on the unit: on the ESP, at the ESP discharge, on the pipeline, which simulates the wellhead production tree. During the bench tests were recorded series of pressures at the intake, discharge and along the pump length, series of current and power consumption, as well as vibrations with frequency several times per second.\u0000 Based on the bench test results, we investigated the possibility of indirect determination of well operation parameters during artificial lift modelling by machine learning. As a result, the approaches to modelling taking into account various sets of parameters (features) have been studied: based on hydraulic parameters – ESP intake and outlet pressure;based on hydraulic and electric parameters – current and power consumption;based on hydraulic, electric and vibrating parameters.\u0000 The analysis of data series allowed to define the boundaries of stable ESP operation, namely the transition to surging and pump starvation.\u0000 The novelty of the work is: –machine learning modeling of the gas-liquid mixture pumping process by electric submersible pump;–solving both direct and inverse issues: as virtual liquid flowmeter as, virtual gas content flowmeter at the pump intake.","PeriodicalId":10904,"journal":{"name":"Day 2 Tue, October 19, 2021","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81691531","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}
Oil & Gas extraction companies are using a vast amount of capital and expertise on production optimization. The scale and diversity of information required for analysis is massive and often leading to a prioritization between time and precision for the teams involved in the process. This paper provides a success story of how artificial intelligence (AI) is used to dynamically and effeciently optimize and predict production of gas wells. In particular, we focus on the application of unsupervised machine learning to identify under different potential constraints the optimal production parameter settings that can lead to maximum production. A machine learning model is supported by a decision support system that can enhance future drilling operations and also help answer important questions such as why a particular well or group of wells is producing differently than others of the same type or what kind of parameters that work on different wells in different conditions. The model can be advanced to optimize within field constraints such as facility handling capacity, quotas, budget or emmisions. The methods used were a combination of similarity measures and unsupervised machine learning techniques which were effective in identifying wells and clusters of wells that have similar production and behavioral profiles. The clusters of wells were then used to identify the process path (specific drilling and completion, choke size, chemicals, etc processes) most likely to result in optimal production and to identify the most impactful variables on production rate or cumulative production via an additional clustering of the principle charactersitics of the well. The data sets used to build these models include but are not limited to gas production data (daily volume), drilling data (well logs, fluid summary etc.), completion data (frac, cement bond logs), and pre-production testing data (choke, pressure etc.) Initial results indicate that this approach is a feasible approach, on target in terms of accuracy with traditional methods and represents a novel, data driven, method of identifying optimal parameter settings for desired production levels; with the ability to perform forecasts and optimization scenarios in run-time. The approach of using machine learning for production forecasting and production optimization in run-time has immense values in terms of the ability to augment domain expertise and create detailed studies in a fraction of the time that is typically required using traditional approaches. Building on same approach to optimise the field to deliver most reliable or most effeciently against a parameter will be an invaluable feature for overall asset optimisation.
{"title":"AI for Production Forecasting and Optimization of Gas Wells: A Case Study on a Middle-East Gas Field","authors":"J. Thatcher, Abdul Rehman, Ivan Gee, M. Eldred","doi":"10.2118/208658-ms","DOIUrl":"https://doi.org/10.2118/208658-ms","url":null,"abstract":"\u0000 Oil & Gas extraction companies are using a vast amount of capital and expertise on production optimization. The scale and diversity of information required for analysis is massive and often leading to a prioritization between time and precision for the teams involved in the process. This paper provides a success story of how artificial intelligence (AI) is used to dynamically and effeciently optimize and predict production of gas wells. In particular, we focus on the application of unsupervised machine learning to identify under different potential constraints the optimal production parameter settings that can lead to maximum production. A machine learning model is supported by a decision support system that can enhance future drilling operations and also help answer important questions such as why a particular well or group of wells is producing differently than others of the same type or what kind of parameters that work on different wells in different conditions. The model can be advanced to optimize within field constraints such as facility handling capacity, quotas, budget or emmisions.\u0000 The methods used were a combination of similarity measures and unsupervised machine learning techniques which were effective in identifying wells and clusters of wells that have similar production and behavioral profiles. The clusters of wells were then used to identify the process path (specific drilling and completion, choke size, chemicals, etc processes) most likely to result in optimal production and to identify the most impactful variables on production rate or cumulative production via an additional clustering of the principle charactersitics of the well. The data sets used to build these models include but are not limited to gas production data (daily volume), drilling data (well logs, fluid summary etc.), completion data (frac, cement bond logs), and pre-production testing data (choke, pressure etc.)\u0000 Initial results indicate that this approach is a feasible approach, on target in terms of accuracy with traditional methods and represents a novel, data driven, method of identifying optimal parameter settings for desired production levels; with the ability to perform forecasts and optimization scenarios in run-time.\u0000 The approach of using machine learning for production forecasting and production optimization in run-time has immense values in terms of the ability to augment domain expertise and create detailed studies in a fraction of the time that is typically required using traditional approaches. Building on same approach to optimise the field to deliver most reliable or most effeciently against a parameter will be an invaluable feature for overall asset optimisation.","PeriodicalId":10904,"journal":{"name":"Day 2 Tue, October 19, 2021","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87602332","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}
A. Aslanyan, B. Ganiev, A. Lutfullin, Ildar Z. Farhutdinov, D. Gulyaev, R. Farakhova, L. Zinurov, Anastasiya Nikolaevna Nikonorova
Brown fields that are currently experiencing production decline can benefit a lot from production enhancement operations based on localization of residual reserves and geology clarification. The set of solutions includes targeted recommendations for additional well surveys followed by producers and injectors workovers, like whole wellbore or selective stimulation, polymer flow conformance, hydraulic fracturing and side tracking. As a result, previously poorly drained areas are involved in production, which increases current rates and ultimate recovery. The integrated technology of residual reserves localization and production increase includes: Primary analysis of the production history for reservoir blocks ranking by production increase potential. Advanced bottom-hole pressures and production history analysis by multiwell deconvolution for pressure maintenance system optimization and production enhancement. Advanced production logging for flow profile and production layer-by-layer allocation. Conducting pulse-code interference testing for average saturation between wells estimation. 3D reservoir dynamic model calibration on advanced tests findings. Multi-scenario development planning for the scenario with biggest NPV regarding surface infrastructure. The presented integrated technology is carried stage by stage. Based on the data analysis at the first stage (the Prime analysis) it is possible to get three types of results. The top-level assessment of the current development opportunities of the area, evaluation of current residual reserves on base of displacement sweep efficiency estimation, and evaluation of the potential production increase for various blocks of the field. Results of the second stage were obtained for the block deemed with the highest potential for production increase. Those results may reveal possible complications, and relevant workovers can be advised along with additional surveys that can further help to locate current reserves. The last stage of Prime analysis provides the most suitable choice was to perform an advanced logging and well-testing, as they include both single-well and multi-well tests. Pulse-code interference tests, multi-well retrospective tests and reservoir-oriented production logging make it possible to scan the reservoir laterally and vertically, which is especially important for multi-layered fields. The reservoir parameters obtained from the test results are used to calibrate the dynamic reservoir model. The effects of production enhancement operations are calculated from the 3D model. The set of possible activities is evaluated in terms of their financial efficiency based on the economic model of the operator company using multi-scenario approach on a specifically created digital twin of the field. The unique feature of this approach lies in an integrated usage of advanced production history analysis, advanced logging and well-testing technologies, as well as further calibration of the dy
{"title":"The Integrated Technology of Residual Reserves Localization and Profit Increase on Brownfields","authors":"A. Aslanyan, B. Ganiev, A. Lutfullin, Ildar Z. Farhutdinov, D. Gulyaev, R. Farakhova, L. Zinurov, Anastasiya Nikolaevna Nikonorova","doi":"10.2118/205172-ms","DOIUrl":"https://doi.org/10.2118/205172-ms","url":null,"abstract":"\u0000 Brown fields that are currently experiencing production decline can benefit a lot from production enhancement operations based on localization of residual reserves and geology clarification.\u0000 The set of solutions includes targeted recommendations for additional well surveys followed by producers and injectors workovers, like whole wellbore or selective stimulation, polymer flow conformance, hydraulic fracturing and side tracking. As a result, previously poorly drained areas are involved in production, which increases current rates and ultimate recovery.\u0000 The integrated technology of residual reserves localization and production increase includes:\u0000 Primary analysis of the production history for reservoir blocks ranking by production increase potential. Advanced bottom-hole pressures and production history analysis by multiwell deconvolution for pressure maintenance system optimization and production enhancement. Advanced production logging for flow profile and production layer-by-layer allocation. Conducting pulse-code interference testing for average saturation between wells estimation. 3D reservoir dynamic model calibration on advanced tests findings. Multi-scenario development planning for the scenario with biggest NPV regarding surface infrastructure.\u0000 The presented integrated technology is carried stage by stage.\u0000 Based on the data analysis at the first stage (the Prime analysis) it is possible to get three types of results. The top-level assessment of the current development opportunities of the area, evaluation of current residual reserves on base of displacement sweep efficiency estimation, and evaluation of the potential production increase for various blocks of the field.\u0000 Results of the second stage were obtained for the block deemed with the highest potential for production increase. Those results may reveal possible complications, and relevant workovers can be advised along with additional surveys that can further help to locate current reserves.\u0000 The last stage of Prime analysis provides the most suitable choice was to perform an advanced logging and well-testing, as they include both single-well and multi-well tests.\u0000 Pulse-code interference tests, multi-well retrospective tests and reservoir-oriented production logging make it possible to scan the reservoir laterally and vertically, which is especially important for multi-layered fields.\u0000 The reservoir parameters obtained from the test results are used to calibrate the dynamic reservoir model. The effects of production enhancement operations are calculated from the 3D model. The set of possible activities is evaluated in terms of their financial efficiency based on the economic model of the operator company using multi-scenario approach on a specifically created digital twin of the field.\u0000 The unique feature of this approach lies in an integrated usage of advanced production history analysis, advanced logging and well-testing technologies, as well as further calibration of the dy","PeriodicalId":10904,"journal":{"name":"Day 2 Tue, October 19, 2021","volume":"38 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75165246","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}
Graciela Eva Naveda, F. D. Louie, Corinna Locatelli, Julien Davard, Sara Fragassi, Alessio Basile, Emanuele Delon
Natural gas has become one of the major sources of energy for homes, public buildings and businesses, therefore gas storage is particularly important to ensure continuous provision compensating the differences between supply and demand. Stogit, part of Snam group, has been carrying out gas storage activities since early 1960's. Natural gas is usually stored underground, in large storage reservoirs. The gas is injected into the porous rock of depleted reservoirs bringing the reservoir nearby to its original condition. Injected gas can be withdrawn depending on the need. Gas market demands for industries and homes in Italy are mostly guaranteed from those Stogit reservoirs even in periods when imports are in crisis. Typically, from April to October, the gas is injected in these natural reservoirs that are "geologically tested"; while from November to March, gas is extracted from the same reservoirs and pumped into the distribution networks to meet the higher consumer demand. Thirty-eight (38) wells, across nine (9) depleted fields, are completed with downhole quartz gauges and some of them with fiber-optics gauges. Downhole gauges are installed to continuously measure and record temperature and pressure from multiple reservoirs. The Real Time data system installed for 29 wells is used to collect, transmit and make available downhole data to Stogit (Snam) headquarter office. Data is automatically collected from remote terminal units (RTUs) and transferred over Stogit (Snam) network. The entire system works autonomously and has the capability of being remotely managed from anywhere over the corporate Stogit (Snam) IT network. Historical trends, including fiber optics gauges ones, are visualized and data sets could be retrieved using a fast and user-friendly software that enables data import into interpretation and reservoir modeling software. The use of this data collection and transmission system, versus the traditional manual download, brought timely data delivery to multiple users, coupled with improved personnel safety since land travels were eliminated. The following pages describe the case study, lessons learned, and integrated new practices used to improve the current and future data transmission deployments.
{"title":"Season Cycling Gas Storage in Stogit Fields. A Real-Time Data Transmission System","authors":"Graciela Eva Naveda, F. D. Louie, Corinna Locatelli, Julien Davard, Sara Fragassi, Alessio Basile, Emanuele Delon","doi":"10.2118/205206-ms","DOIUrl":"https://doi.org/10.2118/205206-ms","url":null,"abstract":"\u0000 Natural gas has become one of the major sources of energy for homes, public buildings and businesses, therefore gas storage is particularly important to ensure continuous provision compensating the differences between supply and demand.\u0000 Stogit, part of Snam group, has been carrying out gas storage activities since early 1960's. Natural gas is usually stored underground, in large storage reservoirs. The gas is injected into the porous rock of depleted reservoirs bringing the reservoir nearby to its original condition. Injected gas can be withdrawn depending on the need. Gas market demands for industries and homes in Italy are mostly guaranteed from those Stogit reservoirs even in periods when imports are in crisis.\u0000 Typically, from April to October, the gas is injected in these natural reservoirs that are \"geologically tested\"; while from November to March, gas is extracted from the same reservoirs and pumped into the distribution networks to meet the higher consumer demand. \u0000 Thirty-eight (38) wells, across nine (9) depleted fields, are completed with downhole quartz gauges and some of them with fiber-optics gauges. Downhole gauges are installed to continuously measure and record temperature and pressure from multiple reservoirs.\u0000 The Real Time data system installed for 29 wells is used to collect, transmit and make available downhole data to Stogit (Snam) headquarter office. Data is automatically collected from remote terminal units (RTUs) and transferred over Stogit (Snam) network. The entire system works autonomously and has the capability of being remotely managed from anywhere over the corporate Stogit (Snam) IT network.\u0000 Historical trends, including fiber optics gauges ones, are visualized and data sets could be retrieved using a fast and user-friendly software that enables data import into interpretation and reservoir modeling software. The use of this data collection and transmission system, versus the traditional manual download, brought timely data delivery to multiple users, coupled with improved personnel safety since land travels were eliminated. The following pages describe the case study, lessons learned, and integrated new practices used to improve the current and future data transmission deployments.","PeriodicalId":10904,"journal":{"name":"Day 2 Tue, October 19, 2021","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76141166","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}
Wettability is an essential component of reservoir characterization and plays a crucial role in understanding the dominant mechanisms in enhancing recovery from oil reservoirs. Wettability affects oil recovery by changing (drainage and imbibition) capillary pressure and relative permeability curves. This paper aims to investigate the role of wettability in matrix-fracture fluid transfer and oil recovery in naturally fractured reservoirs. Two experimental micromodels and one geological outcrop model were selected for this study. Three relative permeability and capillary pressure curves were assigned to study the role of matrix wettability. Linear relative permeability curves were given to the fractures. A complex system modelling platform (CSMP++) has been used to simulate water and polymer flooding in different wettability conditions. Comparing the micromodel data, CSMP++ and Eclipse validated and verified CSMP++. Based on the results, the effect of wettability alteration during water flooding is stronger than in polymer flooding. In addition, higher matrix-to-fracture permeability ratio makes wettability alteration more effective. The results of this study revealed that although an increase in flow rate decreases oil recovery in water-wet medium, it is independent of flow rate in the oil-wet system. Visualized data indicated that displacement mechanisms are different in oil-wet, mixed-wet and water-wet media. Earlier fracture breakthrough, later matrix breakthrough and generation and swelling of displacing phase at locations with high horizontal permeability contrast are the most important features of enhanced oil recovery in naturally fractured oil-wet rocks.
{"title":"Numerical Investigation of Wettability Effects on Two-Phase Flow in Naturally Fractured Reservoirs Using Complex System Modelling Platform","authors":"M. Sedaghat, H. Dashti","doi":"10.2118/205203-ms","DOIUrl":"https://doi.org/10.2118/205203-ms","url":null,"abstract":"\u0000 Wettability is an essential component of reservoir characterization and plays a crucial role in understanding the dominant mechanisms in enhancing recovery from oil reservoirs. Wettability affects oil recovery by changing (drainage and imbibition) capillary pressure and relative permeability curves. This paper aims to investigate the role of wettability in matrix-fracture fluid transfer and oil recovery in naturally fractured reservoirs. Two experimental micromodels and one geological outcrop model were selected for this study. Three relative permeability and capillary pressure curves were assigned to study the role of matrix wettability. Linear relative permeability curves were given to the fractures. A complex system modelling platform (CSMP++) has been used to simulate water and polymer flooding in different wettability conditions. Comparing the micromodel data, CSMP++ and Eclipse validated and verified CSMP++. Based on the results, the effect of wettability alteration during water flooding is stronger than in polymer flooding. In addition, higher matrix-to-fracture permeability ratio makes wettability alteration more effective. The results of this study revealed that although an increase in flow rate decreases oil recovery in water-wet medium, it is independent of flow rate in the oil-wet system. Visualized data indicated that displacement mechanisms are different in oil-wet, mixed-wet and water-wet media. Earlier fracture breakthrough, later matrix breakthrough and generation and swelling of displacing phase at locations with high horizontal permeability contrast are the most important features of enhanced oil recovery in naturally fractured oil-wet rocks.","PeriodicalId":10904,"journal":{"name":"Day 2 Tue, October 19, 2021","volume":"2014 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86791925","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}
Lilibeth Chiquinquira Perdomo, C. Alvarez, Maria Edith Gracia, Guillermo Danilo Salomone, Gilberto Ventuirini, Gustavo Adolfo Selva
As other companies registered in the US stock market, the company reports oil and gas reserves, in compliance with the definitions of the Securities and Exchange Commission (SEC). In addition, it complies internally with the guidelines established by the Petroleum Resources Management System to certify its resources. The PRMS focuses on supporting consistent evaluation of oil resources based on technically sound industry practices, providing fundamental principles for the assessment and classification of oil reserves and resources, but does not provide specific guidance for the classification and categorization of quantities associated with IOR projects. Recently, the company has implemented EOR pilot projects, and their results seem to show commerciality for future development or expansion to new areas, displaying multiple opportunities and proposals to incorporate reserves and resources. So far, the pilot projects and their expansions have been addressed only from the point of view of incremental projects, as an improvement over the previous secondary recovery. The company does not have sufficient track record in booking reserves or resources from EOR projects, their quantities have been incorporated following bibliographic references and results of EOR projects with proven commerciality around the world. For this reason, the need arose to have a tool that provides the company with methodological criteria to evaluate the resources and reserves inherent in this type of project, that incorporate the "best practices" of the industry and that respect the guidelines and definitions of PRMS for incremental projects. That was how, the need to meet this challenging goal led company to develop its "EOR Resources and Reserves Assessment Guide" with the advice of a renowned consulting company. Although the Guide is not intended to be a review of the large body of existing IOR literature, it contains several useful references that serve as a starting point for understanding the IOR project for assessment process of resources and reserves. This document shows the process of development and implementation of the EOR guide, complementing the existing guides within the corporation and providing the company with a positive result within the internal processes of Audit, reserves and resources for this type of projects.
{"title":"Adapted Methodology for Evaluating EOR Reserves and Resources, Incorporated and Applied at an Oil and Gas Company","authors":"Lilibeth Chiquinquira Perdomo, C. Alvarez, Maria Edith Gracia, Guillermo Danilo Salomone, Gilberto Ventuirini, Gustavo Adolfo Selva","doi":"10.2118/205215-ms","DOIUrl":"https://doi.org/10.2118/205215-ms","url":null,"abstract":"\u0000 As other companies registered in the US stock market, the company reports oil and gas reserves, in compliance with the definitions of the Securities and Exchange Commission (SEC). In addition, it complies internally with the guidelines established by the Petroleum Resources Management System to certify its resources.\u0000 The PRMS focuses on supporting consistent evaluation of oil resources based on technically sound industry practices, providing fundamental principles for the assessment and classification of oil reserves and resources, but does not provide specific guidance for the classification and categorization of quantities associated with IOR projects.\u0000 Recently, the company has implemented EOR pilot projects, and their results seem to show commerciality for future development or expansion to new areas, displaying multiple opportunities and proposals to incorporate reserves and resources.\u0000 So far, the pilot projects and their expansions have been addressed only from the point of view of incremental projects, as an improvement over the previous secondary recovery.\u0000 The company does not have sufficient track record in booking reserves or resources from EOR projects, their quantities have been incorporated following bibliographic references and results of EOR projects with proven commerciality around the world.\u0000 For this reason, the need arose to have a tool that provides the company with methodological criteria to evaluate the resources and reserves inherent in this type of project, that incorporate the \"best practices\" of the industry and that respect the guidelines and definitions of PRMS for incremental projects.\u0000 That was how, the need to meet this challenging goal led company to develop its \"EOR Resources and Reserves Assessment Guide\" with the advice of a renowned consulting company.\u0000 Although the Guide is not intended to be a review of the large body of existing IOR literature, it contains several useful references that serve as a starting point for understanding the IOR project for assessment process of resources and reserves.\u0000 This document shows the process of development and implementation of the EOR guide, complementing the existing guides within the corporation and providing the company with a positive result within the internal processes of Audit, reserves and resources for this type of projects.","PeriodicalId":10904,"journal":{"name":"Day 2 Tue, October 19, 2021","volume":"495 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78839514","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}
The discrimination of shale vs. non-shale layers significantly influences the quality of reservoir geological model. In this study, a novel approach was implemented to enhance the model by creating Pseudo Corrected Gamma Ray (CGR) logs using Artificial Intelligence methods to identify the thin shale beds within the reservoir. The lithology of the carbonate reservoir understudy is mostly composed of dolomite and limestone rock with minor amounts of anhydrite and thin shale layers. The identification of shale layers is challenging because of the nature of such reservoirs. The high organic content of the shales and the presence of dolomites, particularly the floatstones and rudstones, can adversely affect the log quality and interpretation and may result in inaccurate log correlations, overestimating/ underestimating Original Oil In Place (OOIP) and reservoir net pays. In such cases, Corrected Gamma Ray (CGR) curves are typically used to identify shale layers. The CGR curve response is due to the combination of thorium and potassium that is associated with the clay content. The difference between the total GR and the CGR is essentially the amount of uranium-associated organic matter. Because of the very limited number of CGR logs in this reservoir, Artificial Intelligence (AI) approach was used to identify shale volume across the entire reservoir. Synthetic CGR curves were generated for the wells lacking CGR logs using AI methods. Resistivity, Density, Neutron and total GR logs were used as inputs while CGR was set as the target. Five wells that have CGR logs were used to train the model. The created pseudo logs were then used to identify shale layers and could also be used to correct effective porosity logs. After statistical analysis of the data, two different Artificial Intelligence Techniques were tested to predict CGR logs; Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN). A Sugeno-type FIS structure using subtractive clustering demonstrated the best prediction with correlation coefficient of 0.96 and mean absolute percentage error (MAPE) of 20%. The resulting synthetic CGR curves helped identify shale layers that do not extend over the entire reservoir area and ultimately correct the effective porosity logs in the reservoir model. Porosity was primarily obtained from the neutron-density logs which results in very high porosity measurements across the shale layers. This study shows a new workflow to predict shale layers in Carbonate reservoirs. The created pseudo CGR logs would help predict shale and is an added-value data that could be incorporated into the Earth model.
{"title":"Discriminating Shale Layers by Pseudo CGR Logs Created Using Artificial Intelligence","authors":"Saud Aldajani, S. Alotaibi, A. Abdulraheem","doi":"10.2118/208663-ms","DOIUrl":"https://doi.org/10.2118/208663-ms","url":null,"abstract":"\u0000 The discrimination of shale vs. non-shale layers significantly influences the quality of reservoir geological model. In this study, a novel approach was implemented to enhance the model by creating Pseudo Corrected Gamma Ray (CGR) logs using Artificial Intelligence methods to identify the thin shale beds within the reservoir.\u0000 The lithology of the carbonate reservoir understudy is mostly composed of dolomite and limestone rock with minor amounts of anhydrite and thin shale layers. The identification of shale layers is challenging because of the nature of such reservoirs. The high organic content of the shales and the presence of dolomites, particularly the floatstones and rudstones, can adversely affect the log quality and interpretation and may result in inaccurate log correlations, overestimating/ underestimating Original Oil In Place (OOIP) and reservoir net pays.\u0000 In such cases, Corrected Gamma Ray (CGR) curves are typically used to identify shale layers. The CGR curve response is due to the combination of thorium and potassium that is associated with the clay content. The difference between the total GR and the CGR is essentially the amount of uranium-associated organic matter. Because of the very limited number of CGR logs in this reservoir, Artificial Intelligence (AI) approach was used to identify shale volume across the entire reservoir.\u0000 Synthetic CGR curves were generated for the wells lacking CGR logs using AI methods. Resistivity, Density, Neutron and total GR logs were used as inputs while CGR was set as the target. Five wells that have CGR logs were used to train the model. The created pseudo logs were then used to identify shale layers and could also be used to correct effective porosity logs.\u0000 After statistical analysis of the data, two different Artificial Intelligence Techniques were tested to predict CGR logs; Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN).\u0000 A Sugeno-type FIS structure using subtractive clustering demonstrated the best prediction with correlation coefficient of 0.96 and mean absolute percentage error (MAPE) of 20%. The resulting synthetic CGR curves helped identify shale layers that do not extend over the entire reservoir area and ultimately correct the effective porosity logs in the reservoir model. Porosity was primarily obtained from the neutron-density logs which results in very high porosity measurements across the shale layers.\u0000 This study shows a new workflow to predict shale layers in Carbonate reservoirs. The created pseudo CGR logs would help predict shale and is an added-value data that could be incorporated into the Earth model.","PeriodicalId":10904,"journal":{"name":"Day 2 Tue, October 19, 2021","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87139435","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}
Klemens Katterbauer, A. Marsala, V. Schoepf, Linda Abbassi
Logging hydrocarbon production potential of wells has been at the forefront of enhancing oil and gas exploration and maximize productivity from oil and gas reservoirs. A major challenge is accurate downhole fluid phases flow velocity measurements in production logging due to the criticality of mechanical spinner-based sensor devices. Ultrasonic Doppler based sensors are more robust and deployable either in wireline or logging while drilling (LWD) conditions; however, due to the different sensing physics, the measurement results may not be equivalent. We present in this work an innovative deep learning framework to estimate spinner phase velocities from Doppler based sensor velocities. Tests of the framework on a benchmark dataset displayed strong estimation results. This allows for the real-time automatic interpretative framework implementation and flow velocity estimations either in conventional wireline production logging technologies (PLTs) and potentially also in LWD conditions, when the well is flowing in underbalanced conditions.
{"title":"Deep Learning Assisted Doppler Sensing for Hydrocarbon Downhole Flow Velocity Estimation","authors":"Klemens Katterbauer, A. Marsala, V. Schoepf, Linda Abbassi","doi":"10.2118/205183-ms","DOIUrl":"https://doi.org/10.2118/205183-ms","url":null,"abstract":"\u0000 Logging hydrocarbon production potential of wells has been at the forefront of enhancing oil and gas exploration and maximize productivity from oil and gas reservoirs. A major challenge is accurate downhole fluid phases flow velocity measurements in production logging due to the criticality of mechanical spinner-based sensor devices. Ultrasonic Doppler based sensors are more robust and deployable either in wireline or logging while drilling (LWD) conditions; however, due to the different sensing physics, the measurement results may not be equivalent. We present in this work an innovative deep learning framework to estimate spinner phase velocities from Doppler based sensor velocities. Tests of the framework on a benchmark dataset displayed strong estimation results. This allows for the real-time automatic interpretative framework implementation and flow velocity estimations either in conventional wireline production logging technologies (PLTs) and potentially also in LWD conditions, when the well is flowing in underbalanced conditions.","PeriodicalId":10904,"journal":{"name":"Day 2 Tue, October 19, 2021","volume":"39 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76286412","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}
Dielectric log is a specialized tool with proprietary procedures to predict oil saturation independent of water salinity. Conventional resistivity logging is more routinely used but dependent on water salinity and Archie's parameters, leading to high measurement uncertainty in mixed salinity environments. This paper presents a novel machine learning approach of propagating the coverage of dielectric-based oil saturation driven by features extracted from commonly available reservoir information, petrophysical properties and conventional log data. More than 20 features were extracted from several sources. Based on sampling frequency, extracted features are divided into well-based discrete features and petrophysical-based continuous features. Examples of well-based features include well location with respect to flank (east or west), fluid viscosities and densities, total dissolved solids from surface water, distance to nearest water injector and injection volume. Petrophysical-based features include height above free water level (HAFWL), porosity, modelled permeability, initial water saturation, resistivity-based saturation, rock-type and caliper. In addition, we engineered two new depth-related and continuous features, we call them Height-Below-Crest (HBC) and Height-Above-Top-Injector-Zone (HATIZ). Initial data exploration was performed using Pearson's correlation heat map. Fluid densities and viscosities show strong correlation (60-80%) to the engineered features (HBC and HATIZ), which helped to capture the viscous and gravity forces effect across the well's vertical depth. The heat map also shows weak correlation between the features and the target variable, the oil saturation from dielectric log. The dataset, with 5000 samples, was randomly split into 80% training and 20% testing. A robust scaling technique to outliers is used to scale the features prior to modeling. The preliminary performance of various supervised machine learning models, including decision trees, ensemble methods, neural network and support vector machines, were benchmarked using K-Fold cross-validation on the training data prior to testing. Ensemble-based methods, random forest and gradient boosting, produced the least mean absolute error compared to other methods and thus were selected for further hyper-parameter tuning. Exhaustive grid search was performed on both models to find the best-fit parameters, achieving a correlation coefficient of 70% on the testing dataset. Features analysis indicate that the engineered features, HBC and HATIZ, along with the porosity, HAFWL and resistivity-based saturation are the most importance features for predicting the oil saturation from dielectric log. Dielectric log provides an edge over resistivity-based logging technique in mixed salinity formations, but with more elaborate interpretation procedures. In this paper, we present a soft-computing and economical alternative of using ensemble machine learning models to predict oil sa
{"title":"A Novel Approach of Using Feature-Based Machine Learning Models to Expand Coverage of Oil Saturation from Dielectric Logs","authors":"Mohammed Alghazal, Dimitrios Krinis","doi":"10.2118/205162-ms","DOIUrl":"https://doi.org/10.2118/205162-ms","url":null,"abstract":"\u0000 Dielectric log is a specialized tool with proprietary procedures to predict oil saturation independent of water salinity. Conventional resistivity logging is more routinely used but dependent on water salinity and Archie's parameters, leading to high measurement uncertainty in mixed salinity environments. This paper presents a novel machine learning approach of propagating the coverage of dielectric-based oil saturation driven by features extracted from commonly available reservoir information, petrophysical properties and conventional log data.\u0000 More than 20 features were extracted from several sources. Based on sampling frequency, extracted features are divided into well-based discrete features and petrophysical-based continuous features. Examples of well-based features include well location with respect to flank (east or west), fluid viscosities and densities, total dissolved solids from surface water, distance to nearest water injector and injection volume. Petrophysical-based features include height above free water level (HAFWL), porosity, modelled permeability, initial water saturation, resistivity-based saturation, rock-type and caliper. In addition, we engineered two new depth-related and continuous features, we call them Height-Below-Crest (HBC) and Height-Above-Top-Injector-Zone (HATIZ).\u0000 Initial data exploration was performed using Pearson's correlation heat map. Fluid densities and viscosities show strong correlation (60-80%) to the engineered features (HBC and HATIZ), which helped to capture the viscous and gravity forces effect across the well's vertical depth. The heat map also shows weak correlation between the features and the target variable, the oil saturation from dielectric log. The dataset, with 5000 samples, was randomly split into 80% training and 20% testing. A robust scaling technique to outliers is used to scale the features prior to modeling. The preliminary performance of various supervised machine learning models, including decision trees, ensemble methods, neural network and support vector machines, were benchmarked using K-Fold cross-validation on the training data prior to testing. Ensemble-based methods, random forest and gradient boosting, produced the least mean absolute error compared to other methods and thus were selected for further hyper-parameter tuning. Exhaustive grid search was performed on both models to find the best-fit parameters, achieving a correlation coefficient of 70% on the testing dataset. Features analysis indicate that the engineered features, HBC and HATIZ, along with the porosity, HAFWL and resistivity-based saturation are the most importance features for predicting the oil saturation from dielectric log.\u0000 Dielectric log provides an edge over resistivity-based logging technique in mixed salinity formations, but with more elaborate interpretation procedures. In this paper, we present a soft-computing and economical alternative of using ensemble machine learning models to predict oil sa","PeriodicalId":10904,"journal":{"name":"Day 2 Tue, October 19, 2021","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89610664","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：