This paper proposes a data-driven proxy model to effectively forecast the production of horizontal wells with complex fracture networks in shales. With the multilayer gated recurrent unit (GRU) cell, the proxy model is coupled with newly developed deep learning methods include attention mechanism (Att-GRU), skip connection, and cross-validation to deal with time series analysis (TSA) issue of multivariate operating and physical parameters. In the formulation, the input variables include time, variable bottom hole pressure (BHP), horizontal well length, fracture number, fracture half-length, and fracture conductivity and the output variable refers to the production corresponding to the forecast time. The sample data generated by the boundary element method (BEM) is used in the proxy model learning process. The shuffled cross-validation method is utilized to improve the model accuracy and generalization capability. Results depict that the Att-GRU can accurately forecast the production for shale gas wells with complex fracture networks at a given time and variable BHP while maintaining a high calculation efficiency. The operating and physical parameters analysis indicates that the Att-GRU has learned the underlying physical features of complex fracture networks and variable BHP. Case study from Marcellus shale shows that the proposed Att-GRU is robust in both production forecast and reservoir evaluation, and it is a potential proxy model for transient analysis.
{"title":"A Deep-Learning-Based Approach for Production Forecast and Reservoir Evaluation for Shale Gas Wells with Complex Fracture Networks","authors":"Peng Dong, X. Liao","doi":"10.2118/209635-ms","DOIUrl":"https://doi.org/10.2118/209635-ms","url":null,"abstract":"\u0000 This paper proposes a data-driven proxy model to effectively forecast the production of horizontal wells with complex fracture networks in shales. With the multilayer gated recurrent unit (GRU) cell, the proxy model is coupled with newly developed deep learning methods include attention mechanism (Att-GRU), skip connection, and cross-validation to deal with time series analysis (TSA) issue of multivariate operating and physical parameters. In the formulation, the input variables include time, variable bottom hole pressure (BHP), horizontal well length, fracture number, fracture half-length, and fracture conductivity and the output variable refers to the production corresponding to the forecast time. The sample data generated by the boundary element method (BEM) is used in the proxy model learning process. The shuffled cross-validation method is utilized to improve the model accuracy and generalization capability. Results depict that the Att-GRU can accurately forecast the production for shale gas wells with complex fracture networks at a given time and variable BHP while maintaining a high calculation efficiency. The operating and physical parameters analysis indicates that the Att-GRU has learned the underlying physical features of complex fracture networks and variable BHP. Case study from Marcellus shale shows that the proposed Att-GRU is robust in both production forecast and reservoir evaluation, and it is a potential proxy model for transient analysis.","PeriodicalId":148855,"journal":{"name":"Day 4 Thu, June 09, 2022","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114969516","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}
P. Aslanidis, S. Strand, T. Puntervold, Kofi Kankam Yeboah, Iyad Souayeh
Smart Water or low salinity water injection are environmentally friendly methods for efficient hydrocarbon recovery. Wettability alteration towards more water-wet conditions and generation of positive capillary forces and spontaneous imbibition are responsible for the increased oil production. Spontaneous imbibition to expel oil from the low permeable matrix is a time-dependent process and both injection rate and oil viscosity are important factors affecting the contribution of capillary and viscous forces to the oil production. It is hypothesized that when capillary forces and spontaneous imbibition are important for oil production, low flooding rate must be applied in laboratory corefloods to allow for wettability alteration. In this study the effect of flooding rate on oil displacement from low permeable sandstone cores has been examined. Viscous forces have been varied by injection at two different rates and performing spontaneous imbibition experiments, in addition to varying the oil viscosity. Low permeable, water-wet Bandera Brown outcrop sandstone cores were used as the porous medium, and synthetic oil and formation water were used to avoid any wettability alteration during fluid restoration and oil displacement. The results showed only small differences in oil recovery by spontaneous imbibition and viscous flooding at high and low rate, proving that capillary forces and spontaneous imbibition were major contributors to the oil mobilization and production process. By varying the oil viscosity, the results indicated that capillary forces were especially important for oil displacement at higher oil viscosity, since the ultimate oil recovered by low-rate injection was higher than that from high-rate injection. As expected, capillary number calculations indicated that capillary forces were important for efficient oil displacement from the low permeable, water-wet cores used in this study. However, there was no direct link observed between generated pressure drops at high and low injection rate, including spontaneous imbibition, and the ultimate oil recovery. Thus, to simulate oil production in the middle of the reservoir it was concluded that low rate waterflooding is needed in laboratory tests to allow spontaneous imbibition into the matrix to displace oil by positive capillary forces. The combination of using oils that differ in viscosity in different injection rates could add some additional information in the literature on how to increase the efficiency of waterflooding by a low injection rate.
{"title":"Oil Recovery by Low-Rate Waterflooding in Water-Wet Sandstone Cores","authors":"P. Aslanidis, S. Strand, T. Puntervold, Kofi Kankam Yeboah, Iyad Souayeh","doi":"10.2118/209688-ms","DOIUrl":"https://doi.org/10.2118/209688-ms","url":null,"abstract":"\u0000 Smart Water or low salinity water injection are environmentally friendly methods for efficient hydrocarbon recovery. Wettability alteration towards more water-wet conditions and generation of positive capillary forces and spontaneous imbibition are responsible for the increased oil production. Spontaneous imbibition to expel oil from the low permeable matrix is a time-dependent process and both injection rate and oil viscosity are important factors affecting the contribution of capillary and viscous forces to the oil production.\u0000 It is hypothesized that when capillary forces and spontaneous imbibition are important for oil production, low flooding rate must be applied in laboratory corefloods to allow for wettability alteration. In this study the effect of flooding rate on oil displacement from low permeable sandstone cores has been examined. Viscous forces have been varied by injection at two different rates and performing spontaneous imbibition experiments, in addition to varying the oil viscosity. Low permeable, water-wet Bandera Brown outcrop sandstone cores were used as the porous medium, and synthetic oil and formation water were used to avoid any wettability alteration during fluid restoration and oil displacement.\u0000 The results showed only small differences in oil recovery by spontaneous imbibition and viscous flooding at high and low rate, proving that capillary forces and spontaneous imbibition were major contributors to the oil mobilization and production process. By varying the oil viscosity, the results indicated that capillary forces were especially important for oil displacement at higher oil viscosity, since the ultimate oil recovered by low-rate injection was higher than that from high-rate injection. As expected, capillary number calculations indicated that capillary forces were important for efficient oil displacement from the low permeable, water-wet cores used in this study. However, there was no direct link observed between generated pressure drops at high and low injection rate, including spontaneous imbibition, and the ultimate oil recovery. Thus, to simulate oil production in the middle of the reservoir it was concluded that low rate waterflooding is needed in laboratory tests to allow spontaneous imbibition into the matrix to displace oil by positive capillary forces.\u0000 The combination of using oils that differ in viscosity in different injection rates could add some additional information in the literature on how to increase the efficiency of waterflooding by a low injection rate.","PeriodicalId":148855,"journal":{"name":"Day 4 Thu, June 09, 2022","volume":"208 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115079876","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}
S. Longinos, Lei Wang, A. Loskutova, Dichuan Zhang, R. Hazlett
In recent years liquid nitrogen (LN2) fracturing technology has been investigated as a promising stimulating technique in coalbed methane (CBM) development. Using the immersion method, this study experimentally examines and illustrates the efficacy of LN2 cryogenic fracturing for a CBM reservoir in the Karaganda Basin of East Kazakhstan. Coal core plugs were frozen with LN2 under different lab-controlled conditions like the length freezing time (FT) and the number of freezing thawing cycles (FTC). Then these treated core plugs were subjected to uniaxial compressive strength test and SEM analysis for comparisons. The results from SEM analysis showed that the LN2 freezing-thawing process can augment the cryogenic fracture and the fracture interconnectivity. Moreover, uniaxial compressive test indicated that compressive strength is kept decreasing with successively increasing the number of freezing-thawing cycles and the same decreasing trend was observed with freezing time experiments compared with the coal sample without liquid nitrogen case.
{"title":"Cyclic LN2 Treatment of Coal Samples from Coal Basin in Kazakhstan","authors":"S. Longinos, Lei Wang, A. Loskutova, Dichuan Zhang, R. Hazlett","doi":"10.2118/209697-ms","DOIUrl":"https://doi.org/10.2118/209697-ms","url":null,"abstract":"\u0000 In recent years liquid nitrogen (LN2) fracturing technology has been investigated as a promising stimulating technique in coalbed methane (CBM) development. Using the immersion method, this study experimentally examines and illustrates the efficacy of LN2 cryogenic fracturing for a CBM reservoir in the Karaganda Basin of East Kazakhstan. Coal core plugs were frozen with LN2 under different lab-controlled conditions like the length freezing time (FT) and the number of freezing thawing cycles (FTC). Then these treated core plugs were subjected to uniaxial compressive strength test and SEM analysis for comparisons. The results from SEM analysis showed that the LN2 freezing-thawing process can augment the cryogenic fracture and the fracture interconnectivity. Moreover, uniaxial compressive test indicated that compressive strength is kept decreasing with successively increasing the number of freezing-thawing cycles and the same decreasing trend was observed with freezing time experiments compared with the coal sample without liquid nitrogen case.","PeriodicalId":148855,"journal":{"name":"Day 4 Thu, June 09, 2022","volume":"610 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125722181","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}
During water-flooding development, severe water breakthrough has been observed in fractured wells. It is essential that determine the reason for water-breakthrough to improve the performance of production wells. However, the conventional pressure-transient analysis model hardly characterizes fracture-induced pressure response and fracture half-length, leading to erroneous results. This paper aimed at present an approach to estimate the half-length of non-simultaneous fracture induced in a relatively economical way. The non-simultaneous fracture closure flow (NFCF) model was proposed to characterize flow in induced fracture. To better characterize pressure response in induced fracture, we first modeled fluid flow in fracture with variable conductivity by two-part, variable-conductivity-linear flow and low-conductivity-linear flow. At the same time, fracture closure was considered to occur twice according to the pressure response of water injection wells, and its condiction followed experimental results. As a result, a semi-analytical solution was developed. We compared it with the finite-conductivity model to certify the accuracy. A new flow regime (the non-simultaneous fracture close linear flow) was discovered and behaved as two peaks on the pressure derivative curve. It will shorten the half-length of induced fracture if the new flow regime is ignored. Case studies showed that the NFCF model matched well with field data, which validated the practicability of the proposed approach. Our results might help accurately understand the reason for the water breakthrough - enormous the half-length of induced fracture was ignored in the past. In addition, the results also have provided significant insight for the operators could make reasonable decisions, reasonable well spacing and water-flooding rate, to improve production and water injection wells performance.
{"title":"Estimation of the Half-Length of Non-Simultaneous-Closed Fracture Through Pressure Transient Analysis: Model and Case Study","authors":"Zhipeng Wang, Z. Ning, Zejiang Jia, Qidi Cheng, Yuanxin Zhang, Wen-ming Guo, Qingyuan Zhu","doi":"10.2118/209716-ms","DOIUrl":"https://doi.org/10.2118/209716-ms","url":null,"abstract":"\u0000 During water-flooding development, severe water breakthrough has been observed in fractured wells. It is essential that determine the reason for water-breakthrough to improve the performance of production wells. However, the conventional pressure-transient analysis model hardly characterizes fracture-induced pressure response and fracture half-length, leading to erroneous results. This paper aimed at present an approach to estimate the half-length of non-simultaneous fracture induced in a relatively economical way. The non-simultaneous fracture closure flow (NFCF) model was proposed to characterize flow in induced fracture. To better characterize pressure response in induced fracture, we first modeled fluid flow in fracture with variable conductivity by two-part, variable-conductivity-linear flow and low-conductivity-linear flow. At the same time, fracture closure was considered to occur twice according to the pressure response of water injection wells, and its condiction followed experimental results. As a result, a semi-analytical solution was developed. We compared it with the finite-conductivity model to certify the accuracy. A new flow regime (the non-simultaneous fracture close linear flow) was discovered and behaved as two peaks on the pressure derivative curve. It will shorten the half-length of induced fracture if the new flow regime is ignored. Case studies showed that the NFCF model matched well with field data, which validated the practicability of the proposed approach. Our results might help accurately understand the reason for the water breakthrough - enormous the half-length of induced fracture was ignored in the past. In addition, the results also have provided significant insight for the operators could make reasonable decisions, reasonable well spacing and water-flooding rate, to improve production and water injection wells performance.","PeriodicalId":148855,"journal":{"name":"Day 4 Thu, June 09, 2022","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117191887","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}
Dong Feng, Zhangxin Chen, Zenghua Zhang, Peihuan Li, Yu Chen, Keliu Wu, Jing Li
The minimum miscible pressure (Pm) of CO2-hydrocarbon mixtures in nanopores is a key parameter for CO2-enhanced shale oil recovery. Although the miscible behaviors of CO2-hydrocarbon mixtures in nanopores have been widely investigated through the simulations and calculations, the heterogeneity of shale components with different affinity to hydrocarbons results in the deviation of traditional predictions and motivates us to investigate how the surface properties influence the CO2-hydrocarbon miscible behaviors in nanopores. In this work, we established a model and framework to determine the wettability-dependent physical phenomena and its impact on the Pm of CO2-hydrocarbon in shale nanopores. First, a generalized scaling rule is established to clarify the potential correlation between critical properties shift and wettability based on the analysis of microscopic interactions (fluid-surface interactions and fluid-fluid interactions). Second, a wettability-dependent SKR EOS is structured and a generalized and practical framework for confined phase behavior with different surface wettability is constructed. Subsequently, the Pm of CO2-hydrocarbon mixtures in confined space with various wettability is evaluated with our model. The calculated results demonstrate that the nanoconfined effects on Pm not only relate to the pore dimension but also depend on the contact angle. In an intermediate-wet nanopore, the minimum miscible pressure approaches the bulk value. In an oil-wet nanopore with a width smaller than 100nm, the minimum miscible pressure is suppressed by the confined effects, and the reduction is further strengthened with a reduction in pore dimension and increase of wall-hydrocarbon affinity. Our work uses a macroscopically measurable parameter (contact angle) to characterize the shift of critical properties derived from the microscopic interactions, and further construct a generalized and practical framework for phase behavior and minimum miscible pressure determination in nanopores with different surface properties. The method and framework can make a significant contribution in the area of upscaling a molecular or nanoscale understanding to a reservoir scale simulation in shale gas/oil research.
{"title":"Effect of Surface Wettability on the Miscible Behaviors Of Co2-Hydrocarbon in Shale Nanopores","authors":"Dong Feng, Zhangxin Chen, Zenghua Zhang, Peihuan Li, Yu Chen, Keliu Wu, Jing Li","doi":"10.2118/209708-ms","DOIUrl":"https://doi.org/10.2118/209708-ms","url":null,"abstract":"The minimum miscible pressure (Pm) of CO2-hydrocarbon mixtures in nanopores is a key parameter for CO2-enhanced shale oil recovery. Although the miscible behaviors of CO2-hydrocarbon mixtures in nanopores have been widely investigated through the simulations and calculations, the heterogeneity of shale components with different affinity to hydrocarbons results in the deviation of traditional predictions and motivates us to investigate how the surface properties influence the CO2-hydrocarbon miscible behaviors in nanopores. In this work, we established a model and framework to determine the wettability-dependent physical phenomena and its impact on the Pm of CO2-hydrocarbon in shale nanopores. First, a generalized scaling rule is established to clarify the potential correlation between critical properties shift and wettability based on the analysis of microscopic interactions (fluid-surface interactions and fluid-fluid interactions). Second, a wettability-dependent SKR EOS is structured and a generalized and practical framework for confined phase behavior with different surface wettability is constructed. Subsequently, the Pm of CO2-hydrocarbon mixtures in confined space with various wettability is evaluated with our model. The calculated results demonstrate that the nanoconfined effects on Pm not only relate to the pore dimension but also depend on the contact angle. In an intermediate-wet nanopore, the minimum miscible pressure approaches the bulk value. In an oil-wet nanopore with a width smaller than 100nm, the minimum miscible pressure is suppressed by the confined effects, and the reduction is further strengthened with a reduction in pore dimension and increase of wall-hydrocarbon affinity. Our work uses a macroscopically measurable parameter (contact angle) to characterize the shift of critical properties derived from the microscopic interactions, and further construct a generalized and practical framework for phase behavior and minimum miscible pressure determination in nanopores with different surface properties. The method and framework can make a significant contribution in the area of upscaling a molecular or nanoscale understanding to a reservoir scale simulation in shale gas/oil research.","PeriodicalId":148855,"journal":{"name":"Day 4 Thu, June 09, 2022","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129699507","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. Mustafa, Zeeshan Tariq, M. Mahmoud, A. Abdulraheem
Brittleness Index (BI) of rocks can help target the most suitable formation for the hydraulic fracturing stimulation in the tight shale reservoirs. The two most widely used approaches in the petroleum industry are based on mineralogical composition and elastic parameters for the BI estimation. However, these approaches may not be applied for all wells for BI determination due to the scarcity of mineralogical-composition and shear wave slowness data. This paper presents a machine learning (ML) approach to predict the BI using readily available well logs. Well log data were collected from three different wells that encompass a total of 2000 ft thick interval of potential shale gas formation in one of the middle eastern basins. Mineralogical composition of shale formation revealed that the shale intervals are comprising of alternate high brittle and low brittle zones and mainly composed of quartz, clay, feldspar, and mica. Feed-forward artificial neural network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were employed to develop the predictive model for the BI. The proposed model was tested and validated to check the consistency of the model. The reliability of the proposed AI model was reflected by the correlation coefficient (CC) ‘0.97’ between predicted and actual brittleness indices. The root mean squared ‘RMSE’ and average absolute percentage error ‘AAPE’ of the predicted brittleness were observed as 3.78 percent and 1.98 respectively for the ANN model. AAPE and RMSE for ANFIS predictive model were 3.51 and 1.81 respectively. The coefficient of determinations (R2) for ANN and ANFIS models were 0.945 and 0.951 respectively.ANN was found to be better than ANFIS by giving high accuracy. The proposed model was then compared with widely used models in the industry such as Jarvie et al., (2007) and Rybacki et al., (2016) on a blind dataset. The predictive model was also validated by comparing with two widely used mineralogy-based approaches. The developed approach can be applied to identify the brittle layers/zones within the shale gas reservoirs to optimize the hydraulic fracturing stimulation treatment. Results showed that the proposed model outperformed previous models by giving less error.
{"title":"Artificial Intelligence Approach for Predicting the Shale Brittleness Index - A Middle East Basin Case Study","authors":"A. Mustafa, Zeeshan Tariq, M. Mahmoud, A. Abdulraheem","doi":"10.2118/209707-ms","DOIUrl":"https://doi.org/10.2118/209707-ms","url":null,"abstract":"\u0000 Brittleness Index (BI) of rocks can help target the most suitable formation for the hydraulic fracturing stimulation in the tight shale reservoirs. The two most widely used approaches in the petroleum industry are based on mineralogical composition and elastic parameters for the BI estimation. However, these approaches may not be applied for all wells for BI determination due to the scarcity of mineralogical-composition and shear wave slowness data.\u0000 This paper presents a machine learning (ML) approach to predict the BI using readily available well logs. Well log data were collected from three different wells that encompass a total of 2000 ft thick interval of potential shale gas formation in one of the middle eastern basins. Mineralogical composition of shale formation revealed that the shale intervals are comprising of alternate high brittle and low brittle zones and mainly composed of quartz, clay, feldspar, and mica. Feed-forward artificial neural network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were employed to develop the predictive model for the BI.\u0000 The proposed model was tested and validated to check the consistency of the model. The reliability of the proposed AI model was reflected by the correlation coefficient (CC) ‘0.97’ between predicted and actual brittleness indices. The root mean squared ‘RMSE’ and average absolute percentage error ‘AAPE’ of the predicted brittleness were observed as 3.78 percent and 1.98 respectively for the ANN model. AAPE and RMSE for ANFIS predictive model were 3.51 and 1.81 respectively. The coefficient of determinations (R2) for ANN and ANFIS models were 0.945 and 0.951 respectively.ANN was found to be better than ANFIS by giving high accuracy. The proposed model was then compared with widely used models in the industry such as Jarvie et al., (2007) and Rybacki et al., (2016) on a blind dataset.\u0000 The predictive model was also validated by comparing with two widely used mineralogy-based approaches. The developed approach can be applied to identify the brittle layers/zones within the shale gas reservoirs to optimize the hydraulic fracturing stimulation treatment. Results showed that the proposed model outperformed previous models by giving less error.","PeriodicalId":148855,"journal":{"name":"Day 4 Thu, June 09, 2022","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134280879","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 Bastian Panggabean, Tania Busran Pramadewi, Erwin Andri Kusuma, Adam Maryanto
JTB and SKW Field are proven fields which are hydrocarbon producing fields in Indonesia. JTB Field which is part of the Cepu Block is a proven field as well as the SKW Field which belongs to Pertamina EP Block. These two fields are 40 km apart and are currently a stranded field due to different operators. The JTB field is an early development field with CO2 characteristics > 35%, while the SKW field is a mature field with oil producers. The SKW field has been produced for more than 30 years so it is a mature field with a fairly high decline rate. Feasibility Study conducted to these project to know incremental value, especially value of engineering and carbon emission incentives from this project. After the formation of integration in the existing fields, where these two fields are under 1 Region, so that the integration of these two fields becomes possible. This integration is necessary considering that currently the JTB Field will be onstream in 2022, while on the one hand the SKW Field has started studies related to CO2 EOR. The pilot project that will be implemented is expected to be a pilot and proof of CO2 EOR which is a very new technology in the oil and gas industry in Indonesia. Carbon emissions for around that can be saved with this method become integrated value engineering that provides value creation. For implementation on pilot phase, capital expenditure about USD 75 millions with additional carbon value around USD 30 millions. This paper will use a Value engineering approach combined with environmental analysis to see the value and incremental value for these two fields. Feasibility Study of this integrated project will be used for searching another financing and get evaluated by project sanctions Deliverable for this feasibility study to calculate incremental return and amount of carbon emission value for this integrated project.
{"title":"Designing CO2-EOR in Indonesia by Matching Business Strategy: Study Case East Java Field, Indonesia","authors":"Yan Bastian Panggabean, Tania Busran Pramadewi, Erwin Andri Kusuma, Adam Maryanto","doi":"10.2118/209704-ms","DOIUrl":"https://doi.org/10.2118/209704-ms","url":null,"abstract":"\u0000 JTB and SKW Field are proven fields which are hydrocarbon producing fields in Indonesia. JTB Field which is part of the Cepu Block is a proven field as well as the SKW Field which belongs to Pertamina EP Block. These two fields are 40 km apart and are currently a stranded field due to different operators. The JTB field is an early development field with CO2 characteristics > 35%, while the SKW field is a mature field with oil producers. The SKW field has been produced for more than 30 years so it is a mature field with a fairly high decline rate.\u0000 Feasibility Study conducted to these project to know incremental value, especially value of engineering and carbon emission incentives from this project. After the formation of integration in the existing fields, where these two fields are under 1 Region, so that the integration of these two fields becomes possible. This integration is necessary considering that currently the JTB Field will be onstream in 2022, while on the one hand the SKW Field has started studies related to CO2 EOR. The pilot project that will be implemented is expected to be a pilot and proof of CO2 EOR which is a very new technology in the oil and gas industry in Indonesia.\u0000 Carbon emissions for around that can be saved with this method become integrated value engineering that provides value creation. For implementation on pilot phase, capital expenditure about USD 75 millions with additional carbon value around USD 30 millions. This paper will use a Value engineering approach combined with environmental analysis to see the value and incremental value for these two fields. Feasibility Study of this integrated project will be used for searching another financing and get evaluated by project sanctions\u0000 Deliverable for this feasibility study to calculate incremental return and amount of carbon emission value for this integrated project.","PeriodicalId":148855,"journal":{"name":"Day 4 Thu, June 09, 2022","volume":"2 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113963259","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}
Menhal A. Al-Ismael, Ali Ahmad Al-Turk i, Ali Husain Al-Saffar
As the oil and gas industry is continuously pushing boundaries of exploiting resources, it becomes more of a mandate to model and optimize forefront technologies. Multilateral wells are one example of a prevalent technology to maximize reservoir contact and return on investment. Optimum design and placement of this type of wells is significant. This work presents a multi-parametric optimization approach that optimizes the design of multilateral wells and maximizes the contact with highly productive hydrocarbon zones in the reservoir. Given a number of input parameters, the design and placement of multilateral wells is modeled using the Graph Theory principles and is optimized using Mixed Integer Programming (MIP) algorithms. The objective function is defined in this work as maximization function of the Total Contact with Sweetspots (TCS). At first, multiple main wellbores are optimized globally across the field and then several local optimizations are performed around each main wellbore to place the laterals. This optimization is subject to a number of input constraints, such as the maximum number of laterals, minimum spacing between wells, and maximum lateral length. Different sets of uncertainty parameters are generated using Latin-Hypercube Sampling (LHS) technique and used as input constraints in multiple well design realizations. In this work, the SPE10 benchmark model with 4 million grid cells and 10 existing producer wells was used. MIP was used in this work to optimize the initial geometry and placement of 20 new multilateral producers while LHS was used to fine-tune well configurations. Using TCS as the objective function in this multi-parametric optimization approach dramatically reduced the number of numerical simulation runs. The multi-parametric optimization generates multiple realizations with different sets of multilateral wells with different configurations. Numerical results from the benchmark model revealed the optimum solution with maximized hydrocarbon production. This resulted in a more practical approach to simultaneously optimize the placement of multilateral wells in large simulation models. In addition, the results reveal that the design, placement and performance of the new wells are highly sensitive to the sweetspot maps and reservoir heterogeneity. Using TCS as the objective function resulted in avoiding the excessive use of numerical simulation and cutting down the turnaround time for optimizing the design and placement of multilateral wells. In addition, the global and local optimizations used in this approach significantly simplified the mathematical formulation and avoided complex network modeling and optimization for multilateral wells.
{"title":"Multi-Parametric Optimization of Multilateral Wells for Optimum Reservoir Contact","authors":"Menhal A. Al-Ismael, Ali Ahmad Al-Turk i, Ali Husain Al-Saffar","doi":"10.2118/209647-ms","DOIUrl":"https://doi.org/10.2118/209647-ms","url":null,"abstract":"\u0000 As the oil and gas industry is continuously pushing boundaries of exploiting resources, it becomes more of a mandate to model and optimize forefront technologies. Multilateral wells are one example of a prevalent technology to maximize reservoir contact and return on investment. Optimum design and placement of this type of wells is significant. This work presents a multi-parametric optimization approach that optimizes the design of multilateral wells and maximizes the contact with highly productive hydrocarbon zones in the reservoir. Given a number of input parameters, the design and placement of multilateral wells is modeled using the Graph Theory principles and is optimized using Mixed Integer Programming (MIP) algorithms. The objective function is defined in this work as maximization function of the Total Contact with Sweetspots (TCS). At first, multiple main wellbores are optimized globally across the field and then several local optimizations are performed around each main wellbore to place the laterals. This optimization is subject to a number of input constraints, such as the maximum number of laterals, minimum spacing between wells, and maximum lateral length. Different sets of uncertainty parameters are generated using Latin-Hypercube Sampling (LHS) technique and used as input constraints in multiple well design realizations. In this work, the SPE10 benchmark model with 4 million grid cells and 10 existing producer wells was used. MIP was used in this work to optimize the initial geometry and placement of 20 new multilateral producers while LHS was used to fine-tune well configurations. Using TCS as the objective function in this multi-parametric optimization approach dramatically reduced the number of numerical simulation runs. The multi-parametric optimization generates multiple realizations with different sets of multilateral wells with different configurations. Numerical results from the benchmark model revealed the optimum solution with maximized hydrocarbon production. This resulted in a more practical approach to simultaneously optimize the placement of multilateral wells in large simulation models. In addition, the results reveal that the design, placement and performance of the new wells are highly sensitive to the sweetspot maps and reservoir heterogeneity. Using TCS as the objective function resulted in avoiding the excessive use of numerical simulation and cutting down the turnaround time for optimizing the design and placement of multilateral wells. In addition, the global and local optimizations used in this approach significantly simplified the mathematical formulation and avoided complex network modeling and optimization for multilateral wells.","PeriodicalId":148855,"journal":{"name":"Day 4 Thu, June 09, 2022","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127495105","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}
F. Anifowose, M. Mezghani, Saleh Badawood, Javid Ismail
Background gas is the baseline gas measurement due to the recycled gas dissolved in or expelled from the drilling mud additives. It occurs more in oil-based mud systems than in water-based. A cut-off is usually applied on the mud gas data to remove the background gas effect in traditional mud gas analyses. This imposes an overhead on modeling procedures. This study investigates the effect of applying the cut-off on the performance of machine learning algorithms. A case of porosity prediction using advanced mud gas data is considered in this study. Using data from six wells, we implemented two experiments to compare the performance of artificial neural networks (ANN) with and without the cut-off. The first experiment applies a cut-off of 100 ppm on the total normalized gas while the second uses the entire data without the cut-off. The comparative results are benchmarked with those of a multivariate linear regression (MLR). Each well dataset was split into training and validation subsets using a randomized sampling approach in the ratio of 70:30. The results compare each of the MLR and ANN models individually and over all the datasets without and with the cut-off applied. The ANN models show better or same performance on the datasets without the cut-off in four out of six cases (67%). This shows that the ANN models may be less affected by the presence of the background gases in the mud gas datasets. It could be preliminarily concluded, based on the data used in this study, that it might be unnecessary to apply cut-offs on the mud gas data for ML algorithms due to their capability to handle noisy data. This conclusion is, however, subject to more extensive studies while ensuring consistency. Avoiding the application of the cut-off will remove the unnecessary overhead and provide more data for effective ML model training. While the results of this preliminary study somewhat agree with the traditional practice of applying a cut-off on advanced mud gas data, more extensive experiments will be conducted in our future work to further validate the conclusion. The background gas is traditionally considered noisy. In ML modeling, it could provide more information to further explain the nonlinear relationship between the input features and the target variable, hence improving the predictive capability.
{"title":"Should We Care About the Background Gas Effect on Reservoir Properties Prediction Using Machine Learning and Advanced Mud Gas Data?","authors":"F. Anifowose, M. Mezghani, Saleh Badawood, Javid Ismail","doi":"10.2118/209648-ms","DOIUrl":"https://doi.org/10.2118/209648-ms","url":null,"abstract":"\u0000 Background gas is the baseline gas measurement due to the recycled gas dissolved in or expelled from the drilling mud additives. It occurs more in oil-based mud systems than in water-based. A cut-off is usually applied on the mud gas data to remove the background gas effect in traditional mud gas analyses. This imposes an overhead on modeling procedures. This study investigates the effect of applying the cut-off on the performance of machine learning algorithms.\u0000 A case of porosity prediction using advanced mud gas data is considered in this study. Using data from six wells, we implemented two experiments to compare the performance of artificial neural networks (ANN) with and without the cut-off. The first experiment applies a cut-off of 100 ppm on the total normalized gas while the second uses the entire data without the cut-off. The comparative results are benchmarked with those of a multivariate linear regression (MLR). Each well dataset was split into training and validation subsets using a randomized sampling approach in the ratio of 70:30.\u0000 The results compare each of the MLR and ANN models individually and over all the datasets without and with the cut-off applied. The ANN models show better or same performance on the datasets without the cut-off in four out of six cases (67%). This shows that the ANN models may be less affected by the presence of the background gases in the mud gas datasets. It could be preliminarily concluded, based on the data used in this study, that it might be unnecessary to apply cut-offs on the mud gas data for ML algorithms due to their capability to handle noisy data. This conclusion is, however, subject to more extensive studies while ensuring consistency. Avoiding the application of the cut-off will remove the unnecessary overhead and provide more data for effective ML model training.\u0000 While the results of this preliminary study somewhat agree with the traditional practice of applying a cut-off on advanced mud gas data, more extensive experiments will be conducted in our future work to further validate the conclusion. The background gas is traditionally considered noisy. In ML modeling, it could provide more information to further explain the nonlinear relationship between the input features and the target variable, hence improving the predictive capability.","PeriodicalId":148855,"journal":{"name":"Day 4 Thu, June 09, 2022","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134365943","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}
When nonlinear constraints such as field liquid and water production rate are imposed onto the problem and need to be honored, optimizing well controls such as producing bottom-hole pressures (BHPs) and injection rates becomes more challenging. Hence, the main objective of this paper is to present an efficient production optimization tool to handle nonlinear state constraints for well-control waterflooding optimization problems. The proposed efficient optimization tool uses our newly improved physics-based data-driven interwell waterflooding simulator (referred to as INSIM-BHP) that handles both rate and pressure controls. Our previous waterflooding optimization applications used an old version of INSIM which only considered the linear constraints and did not incorporate the correct well indices for computing BHPs in the case of well BHP control optimization. In this study, we use our newly developed interwell waterflooding simulator that removes the mentioned restrictions in well-control optimization to maximize the net-present-value (NPV) with nonlinear state constraints. We use a recently developed line-search sequential quadratic programming (LS-SQP) algorithm coupled with stochastic simplex approximate gradients (StoSAG). We tested our proposed methodology on a three-dimensional (3D) channelized reservoir with multi-segmented wells and compared it with a commercial simulator. Results show that our methodology provides optimal well controls that satisfy the specified nonlinear state constraints successfully. In addition, the optimal well controls and NPV obtained from our INSIM-based optimization method compare well with the corresponding results from a high-fidelity commercial reservoir simulator but in a far less computational time. The novelty of our work is its presentation of an improved physics-reduced data-driven proxy simulator (INSIM-BHP) to replace the high-fidelity simulators to simulate the oil saturation and pressures to perform computationally efficient well-control waterflooding optimization under nonlinear constraints.
{"title":"Physics-Based Data-Driven Interwell Simulator for Waterflooding Optimization Considering Nonlinear Constraints","authors":"Ying Li, Q. Nguyen, M. Onur","doi":"10.2118/209634-ms","DOIUrl":"https://doi.org/10.2118/209634-ms","url":null,"abstract":"\u0000 When nonlinear constraints such as field liquid and water production rate are imposed onto the problem and need to be honored, optimizing well controls such as producing bottom-hole pressures (BHPs) and injection rates becomes more challenging. Hence, the main objective of this paper is to present an efficient production optimization tool to handle nonlinear state constraints for well-control waterflooding optimization problems. The proposed efficient optimization tool uses our newly improved physics-based data-driven interwell waterflooding simulator (referred to as INSIM-BHP) that handles both rate and pressure controls. Our previous waterflooding optimization applications used an old version of INSIM which only considered the linear constraints and did not incorporate the correct well indices for computing BHPs in the case of well BHP control optimization. In this study, we use our newly developed interwell waterflooding simulator that removes the mentioned restrictions in well-control optimization to maximize the net-present-value (NPV) with nonlinear state constraints. We use a recently developed line-search sequential quadratic programming (LS-SQP) algorithm coupled with stochastic simplex approximate gradients (StoSAG). We tested our proposed methodology on a three-dimensional (3D) channelized reservoir with multi-segmented wells and compared it with a commercial simulator. Results show that our methodology provides optimal well controls that satisfy the specified nonlinear state constraints successfully. In addition, the optimal well controls and NPV obtained from our INSIM-based optimization method compare well with the corresponding results from a high-fidelity commercial reservoir simulator but in a far less computational time. The novelty of our work is its presentation of an improved physics-reduced data-driven proxy simulator (INSIM-BHP) to replace the high-fidelity simulators to simulate the oil saturation and pressures to perform computationally efficient well-control waterflooding optimization under nonlinear constraints.","PeriodicalId":148855,"journal":{"name":"Day 4 Thu, June 09, 2022","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125592175","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：