Day 3 Wed, February 14, 2024最新文献

{"title":"Unlocking Reservoir Potential: Machine Learning-Driven Prediction of Reservoir Properties and Sweet Spots Identification","authors":"M. Khan, A. A. Bery, S. S. Ali, S. Awfi, Y. Bashir","doi":"10.2523/iptc-23557-ms","DOIUrl":"https://doi.org/10.2523/iptc-23557-ms","url":null,"abstract":"\u0000 Reservoir properties prediction and sweet spots identification from seismic and well data is an essential process of hydrocarbon exploration and production. This study aims to develop a robust and reliable approach to predict reservoir properties such as acoustic impedance and porosity of a fluvio-deltaic depositional system from 3D seismic and well data using Machine Learning techniques and compare the results with conventional stochastic inversion.\u0000 A comprehensive machine learning methodology has been applied to predict reservoir properties in both log-to-log and log-to-seismic domains. First, 1D predictive models were created using an Ensemble modelling process which consists of 4 models each from Random Forest, XGBoost and Neural Networks. This was used to predict missing logs for eight wells. Subsequently, a 3D time model with 2ms temporal thickness was built and a seismic stack volume, seismic attributes volumes (envelope, sweetness, RMS Amplitude etc.) and low frequency model were resampled to the model resolution. The conventional post-stack stochastic inversion process is executed in the model to generate acoustic impedance, which is subsequently utilized to compute porosity through the acoustic impedance versus porosity transform. 3D predictive models are then created by incorporating seismic attributes, low frequency model and the target acoustic impedance log (AI) to establish a relationship and predict the 3D acoustic impedance property within the model. Additionally, another regression function is generated, employing the predicted acoustic impedance versus porosity, to forecast the 3D porosity property.\u0000 Machine Learning 1D predictive models enabled the prediction of partial or full missing logs such as gamma ray, density, compression sonic, neutron porosity, acoustic impedance (AI), and porosity (PHIE) to complete the full logs coverage on eight wells in the reservoir zones. XGBoost 1D models produced the best results for training with R^2 score of 0.93 and validation score of 0.87. The stochastic inversion approach enabled the generation of high-resolution acoustic impedance and porosity properties in the 3D model. 3D predictive models established a relationship of seismic attributes volumes with well logs (AI) at well locations and predicted the acoustic impedance property in the whole 3D volumes away from the wells. To assess the prediction accuracy, we employed a randomly-selected blind wells approach, and the optimal model achieved an 82% validation accuracy. Notably, Neural Networks exhibited superior performance in proximity to the well locations, with a decline in quality observed as we moved away from the wells. On the other hand, Random Forest and XGBoost consistently produced continuous results. The predictive properties of AI and porosity were combined to train an unsupervised Neural Network model for facies prediction. This process aided in identifying sweet spots associated with the optimal reservoir sand saturate","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"254 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140527602","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}

{"title":"Predicting Interfacial Tension in CO2/Brine Systems: A Data-Driven Approach and Its Implications for Carbon Geostorage","authors":"M. Khan, Zeeshan Tariq, Muhammad Ali, M. Murtaza","doi":"10.2523/iptc-23568-ms","DOIUrl":"https://doi.org/10.2523/iptc-23568-ms","url":null,"abstract":"\u0000 CO2 Interfacial Tension (IFT) and the reservoir rock-fluid interfacial interactions are critical parameters for successful CO2 geological sequestration, where the success relies significantly on the rock-CO2-brine interactions. IFT behaviors during storage dictate the CO2/brine distribution at pore scale and the residual/structural trapping potentials of storage/caprocks. Experimental assessment of CO2-Brine IFT as a function of pressure, temperature, and readily available organic contaminations on rock surfaces is arduous because of high CO2 reactivity and embrittlement damages. Data-driven machine learning (ML) modeling of CO2-brine IFT are less strenuous and more precise. They can be conducted at geo-storage conditions that are complex and hazardous to attain in the laboratory. In this study, we have applied three different machine learning techniques, including Random Forest (RF), XGBoost (XGB), and Adaptive Gradient Boosting (AGB), to predict the interfacial tension of the CO2 in brine system. The performance of the ML models was assessed through various assessment tests, such as cross-plots, average absolute percentage error (AAPE), root mean square error (RMSE), and coefficient of determination (R2). The outcomes of the predictions indicated that the XGB outperformed the RF, and AdaBoost. The XGB yielded remarkably low error rates. With optimal settings, the output was predicted with 97% accuracy. The proposed methodology can minimize the experimental cost of measuring rheological parameters and serve as a quick assessment tool.","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140527622","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}

{"title":"Opportunities in Utilization of Digital Twins in Unconventional Gas Fields: Enhancing Efficiency and Performance through Virtual Replication","authors":"Nouf Alsulaiman, Karri Reddy, Uchenna Odi, Jaime Rabines, C. Temizel","doi":"10.2523/iptc-23176-ms","DOIUrl":"https://doi.org/10.2523/iptc-23176-ms","url":null,"abstract":"\u0000 \u0000 \u0000 Digital twin technology offers significant opportunities for the utilization and optimization of unconventional gas fields by providing virtual replicas of physical assets and processes. The idea of a digital twin is to build a model completely devoid of the typical physics and equations that the analytical or numerical simulation model usually depends on. A virtual twin is a model that is purely data driven without any physical context. This paper explores the potential benefits and applications of digital twins in unconventional gas fields, focusing on enhancing operational efficiency, improving production performance, and enabling proactive decision-making. This study is solely based on synthetic/public data, it doesn't include any privileged or confidential data.\u0000 \u0000 \u0000 \u0000 Digital twins serve as virtual counterparts of physical assets, capturing real-time data and simulating their behavior in a dynamic and integrated environment. In the context of unconventional gas fields, digital twins enable operators and engineers to monitor, analyze, and optimize various aspects of field operations, including reservoir behavior, well performance, hydraulic fracturing, surface facilities, and production systems. One of the key opportunities provided by digital twins is the ability to enhance reservoir understanding and optimize production performance. By integrating real-time data from sensors, downhole monitoring devices, and production measurements, digital twins enable the modeling and simulation of reservoir behavior, predicting key performance indicators such as production rates, pressure profiles, and fluid flow. This facilitates proactive decision-making for reservoir management, well placement, and production optimization.\u0000 Digital twins also enable the optimization of hydraulic fracturing operations in unconventional gas fields. By integrating geological, geophysical, and engineering data, digital twins provide insights into fracture propagation, stimulation effectiveness, and fracture network connectivity. This allows for the optimization of completion designs, well spacing, and fracturing parameters, leading to improved well performance and increased hydrocarbon recovery.\u0000 \u0000 \u0000 \u0000 Digital twins enhance the monitoring and control of surface facilities and production systems in unconventional gas fields. By capturing real-time data from sensors and equipment, digital twins facilitate predictive maintenance, early fault detection, and optimization of operational parameters. This results in improved operational efficiency, reduced downtime, and optimized production rates.\u0000 The paper discusses the applications and benefits of digital twins in unconventional gas fields through case studies and industry examples. It highlights the successful implementation of digital twin technology, showcasing the achieved improvements in operational efficiency, production performance, and cost optimization.\u0000 \u0000 \u0000 \u0000 The findings of this study contribute to the advanc","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"23 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140527633","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}

{"title":"At-The-Bit Look-Around 3D Inversion; Key Milestone Achieved with Innovative Close to the Bit Ultra-Deep Azimuthal Resistivity Sensors","authors":"A. Elkhamry, A. A. Maimani, M. Fouda, A. Taher","doi":"10.2523/iptc-24508-ms","DOIUrl":"https://doi.org/10.2523/iptc-24508-ms","url":null,"abstract":"\u0000 Efficient well placement profoundly depends on early geo-steering decisions to maximize reservoir contact. In highly undulated thin target zones, this can be more concerning as the formation dip changes abruptly. Such environments present a significant challenge where geo-mapping instruments are placed farther behind the bit in the bottom hole assembly, leading to relatively late decision making and more aggressive well path corrections. This paper presents the advantages of placing geo-mapping tools close to the drilling bit position leading to enhanced reservoir contact (Net-to-Gross) and less tortuous well bores.\u0000 Deep and ultra-deep azimuthal resistivity measurements have historically provided a step change for proactive geo-steering, yet the challenge has always been the proximity of the sensors to the bit opposed to other less sophisticated near bit sensors. Well placement with conventional configurations have been regularly utilized to ensure maximum reservoir exposure with varying results due to unforeseen geo-structural changes such as the formation dipping regime (1D environment), lateral boundaries (2D environment) or channels (3D environment). A new tool design was introduced in which the ultra-deep resistivity transmitter was embedded into the rotary steerable system allowing 1D and 3D inversions to be closest to the bit position, offering at-the-bit visualization of the reservoir, hence, earlier, and less aggressive well path corrections could be made to optimize well placement and increase reservoir contact. Geo-mapping formation boundaries while drilling high angle sections with a near bit ultra-deep azimuthal resistivity inversion minimized potential reservoir exits while also minimizing wellbore tortuosity. This is critical for efficient well placement, minimizing drilling risks and smooth completions deployment. Horizontal wells were placed in thin reservoir targets that are successfully resolved by integrating 1D and 3D inversions to improve reservoir mapping, remote lithology and fluid identification to optimize well placement and reservoir evaluation. The accuracy of reservoir visualization from the near-bit resistivity inversion has been validated by other logging while drilling measurements in the drill string, such as triple combo and azimuthal images from several sensors.\u0000 This paper presents the global first at-the-bit look-around inversion utilizing an ultra-deep resistivity sensor embedded in a rotary steerable system for horizontal well placement in two target sand packages. The proximity of the ultra-deep sensor to the bit enabled quicker decisions to optimally place the well in the target zone while reducing well tortuosity leading to a higher net-to-gross and a smoother well trajectory. This also facilitated the deployment of the completion equipment saving costly rig time.","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"131 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140527642","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}