Day 2 Tue, November 01, 2022最新文献

{"title":"Successful Delivery of the First Extended Reach Well Using an Integrated Multidisciplinary Approach; A Case Study in a Mature Field, Onshore Abu Dhabi UAE","authors":"A. Shahat, Mohamed Osama Abd Elmeguid, Luis Gerardo, A. Saleh, S. Almazrouei, A. B. Sumaida, A. Mutawa, Chuma Ibeziako, Faisal Siddiqui, Shamsa Al Menhali, Fawad Zain Yousfi, Rohit V. Deshmukh, Sanjiv Kumar, Ashim Dutta, R. Reddy, M. Baslaib, Alexander Mikhaylov, Lama Atallah, M. Nasrallah, W. Fares, T. Hamdan, M. Husien","doi":"10.2118/211492-ms","DOIUrl":"https://doi.org/10.2118/211492-ms","url":null,"abstract":"\u0000 Drilling extended reach drilling (ERD) wells starting from the planning phase and engaging various disciplines including drilling, cementing, drilling fluids and geoscience teams. The pre-well engagement and integration between multiple disciplines are vital to define the associated drilling/geosteering challenges and accordingly optimize the drilling program to deliver a successful ERD well. These challenges are included and not limited to geological model uncertainties, differential sticking, high torque and drag, ECD limitation, friction factors and expected mud losses. An integrated and optimized plan was constructed to meet the associated challenges. The drilling engineering team optimized the bottom hole assembly (BHA) design in all sections to ensure a smooth profile using optimum drill bits designs. The BHA included LWD technologies to mitigate the geological challenges and helping in determining the casing points and geosteering operations. A new generation of intelligent fully rotating high dogleg pushthe-bit rotary steerable system was selected with matched drilling bits to geosteer the well in the thin target layer while maintaining the planned target trajectory with minimum borehole tortuosity by means of realtime drilling optimization.\u0000 Effective collaboration led to successful delivery of the first extended reach well, the geosteering objectives were achieved with 100% reservoir contact and delivered 20,000 feet targeting thin carbonate layer and overcoming the complex geology environment. The well was drilled to record depth of 32,300 feet with 29% ROP improvement in same field. ECD was always maintained below the fracture gradient along with optimal hole cleaning without cuttings buildup or tight hole while reducing the wellbore friction to ensure smooth pulling out of hole operation. Cementing operations were successfully achieved and ensured zonal isolation. Furthermore, a customized and innovative drilling fluid with free RDF Non Aqueous Fluid (NAF) and compatible lubricant were deployed along the different hole sections to reduce the expected induced losses and provide proper hole cleaning. The cementing program has been optimized for the 18 5/8\", 13 3/8\" and 9 5/8\" casings using an innovative flexible expandable lead and tail slurries with enhanced mechanical properties to mitigate the expected losses while cementing and ensure proper isolation across all formations.\u0000 The best practice of the multidisciplinary approach along with the captured lessons learned opens the door to drill more challenging wells. in addition, it proved that proper planning and execution can shift the boundaries further and gave confidence to drill even deeper.","PeriodicalId":249690,"journal":{"name":"Day 2 Tue, November 01, 2022","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117187403","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":"Integrated Production Optimization Leads Significant Gain from North Kuwait Jurassic Gas Challenging Deep Tight Carbonate Fields","authors":"Mohamed Abdel-Basset, Mohammad Al-Sharad, D. Al-Muhanna, Hind Bin Mutlaq, K. Al-Mefleh, Mansour Al-Awadhi, Y. Al-salali, Hanan Bushehrai, Khaled Nazar","doi":"10.2118/211411-ms","DOIUrl":"https://doi.org/10.2118/211411-ms","url":null,"abstract":"\u0000 This paper demonstrates the production optimization methodology being used by Kuwait Oil Company Jurassic gas that added significant contribution of approximately 37% of total field incremental production gain in 2021.\u0000 Production optimization is a continuous iterative process to improve production, especially in mature fields. The North Kuwait Jurassic Gas field’s team has adopted an integrated enhanced and structured process to identify opportunities for production optimization with a pro-active approach focusing on flowing wells and rig-less interventions to tackle production challenges and achieve production targets.\u0000 The Jurassic gas asset has unique mature-field challenges. It produces mainly from deep (up to 19,000 ft MD) high pressure and temperature, conventional and unconventional tight carbonate reservoirs, highly deviated to horizontal wells, different completion configurations (4.5in monobore, 3.5in × 5in liner, and 4.5in Multi-stages completions), wellbore cleaning and accessibility, scaling and flow assurance, high heterogeneity and permeability contrast among different flow units and dual permeability effect (matrix and natural fractures), production decline due to pressure depletion, liquid loading, high H2S (up to 13 mol%), surface production facilities limitations (e.g. limited MP and H2S handling capacity). effectiveness of subsequent stimulation treatments of such complex heterogeneous reservoir to improve well productivity and connect the natural fractures. The recovery from such complex heterogeneous reservoirs is extremely challenging if conventional development strategies are applied and need for appropriate production optimization methodology outlined here.\u0000 The Heterogeneity Index process is utilized to rapidly demonstrate production gain opportunities via quick screening method of identifying preliminary candidate wells with anomalous behavior (over/under performance) for further analysis. The results from this screening tool were utilized to identify the families of type productivity problems at field and well levels with solution categories for production enhancement. Representative wells were selected for detailed diagnostics based on the relevance and size of productivity impact and the potential of its well deliverability. Once a few \"top potential\" wells were identified, production engineering workflows were implemented to assess and forecast the potential of production increase and to determine and evaluate the best solution design and intervention action.\u0000 Detailed production optimization process provided recommendations of various remedial intervention solutions to improve well production potential via productivity enhancement ranging from complex matrix and fracturing stimulation, additional and/or re-perforations, wellbore cleaning, flow assurance solutions, to choke management. Other advanced technologies were applied to improve various strategies, including completions, perforation, stimulation, and prod","PeriodicalId":249690,"journal":{"name":"Day 2 Tue, November 01, 2022","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128422604","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":"Monitoring Health of Minagish Reservoir Through Tracking Movement of Reservoir Fluids","authors":"Pruthviraj Kasaraneni, T. Al Rashidi, Mishary Al Zamanan, G. S. Padhy, Jeevankumar Silambuchelvan","doi":"10.2118/211376-ms","DOIUrl":"https://doi.org/10.2118/211376-ms","url":null,"abstract":"\u0000 This paper describes the methodology adopted to Monitor Health of Reservoir by tracking historical movement of reservoir fluids in an Oolitic limestone reservoir in Kuwait. The reservoir has a weak aquifer support, hence Gas injection followed by Water injection was implemented to provide necessary pressure support and improve overall reservoir sweep.\u0000 Since injection is being undertaken for a long period of time, drainage radius of water injectors is estimated through streamlines and accordingly the reservoir is divided into different regions based on the injection radius. Thereafter, historical movement of reservoir fluids in each region is analyzed for a period of 60 years to understand the following, Identify the position of leading edge of water and its associated flood-front with respect to each zone & region.Capture oil saturation changes during the last 60 years and identified which regions had minimal changes in oil saturation to accelerate implantation of new infill wells to maximize recovery.Locate where is the remaining oil in the reservoir and identified on what is it causing presence of remaining oil at any given location.Capture the changes in region-wise pressure by coupling with movement of Injected water.Generate distribution of Voidage replacement ratio and injection efficiency in different regions of the reservoir.","PeriodicalId":249690,"journal":{"name":"Day 2 Tue, November 01, 2022","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132141583","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":"Energy Efficiency Improvement of a Gas Compressor Through Process Parameters Adjustments","authors":"Abdulaziz A. Al-Mulhim","doi":"10.2118/211234-ms","DOIUrl":"https://doi.org/10.2118/211234-ms","url":null,"abstract":"\u0000 As a global leader in energy supply, Saudi Aramco spares no efforts in maintaining the global energy demand by operating major onshore and offshore oil fields. This comes while ensuring to minimize the carbon footprint that will be resulted oil production, and to maximize the value creation from the operating facilities. The production of crude oil from these oil fields will involve producing associated gas at a facility that is called Gas Oil Separation plant (GOSP) which will be handled through gas gathering trains at the Gas Oil Separation Plants (GOSPs) to accommodate this valuable by-product with the produced crude oil from the connected oil field to increase the value creation and reduce flaring of the associated gas which may negatively impact the surrounding environment which includes but not limited to impacting climate change and air pollution. This is also part of Saudi Aramco commitments toward circular economy by reducing waste the amount of waste at the oil producing facilities.\u0000 Therefore, Saudi Aramco strives to improve energy efficiency at its premises. In spite of all the exerted efforts, strict policies, challenging targets and investments to achieve a continual improvement in energy efficiency, it would be hard to avoid a performance plateau without breakthrough solutions. This is particularly true in Saudi Aramco, considering the large geographical area in which different facilities are scattered.\u0000 Energy efficiency and environmental protection are two important parameters that are interconnected, and both are critical for the quality of future generation. Effective power utilization can eventually help sustainability and circular economy.","PeriodicalId":249690,"journal":{"name":"Day 2 Tue, November 01, 2022","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130221192","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":"Reviving a Complicated Idle Well: A Multi-Intervention Example from the Sultanate of Oman","authors":"Hamdan Al Gheilani, Khalid Al Sawwafi, Dragos Cruceru, Pearl Bezboruah, A. Charushin, Said Al Maskari, Saja Mohamed Murad Al Balushi, Sami Makawi, Hatem Al Hatmi, Yousif Eltorabi","doi":"10.2118/211203-ms","DOIUrl":"https://doi.org/10.2118/211203-ms","url":null,"abstract":"\u0000 A well targeting deep a gas formation in the central part of the Sultanate of Oman was drilled in February 2010. At a later stage a fracturing operation was conducted but an integrity issue. This integrity issue consisted of a communication between tubing and casing annulus which led to the well having been isolated with cement plugs. This paper describes a successful work cycle of restoring well accessibility and reviving production from an idle complex well using different means of well intervention.\u0000 A Hydraulic Workover Unit attended the well to fix the integrity issue of the casing/ tubing annulus communication. An old casing was recovered and a new one installed. Next a coiled tubing unit attended the well; it encountered complicated well conditions characterized by the presence of metal junk left behind after a previous milling operation. In addition there were 3 cement plugs and 700 m of proppant which needed to be removed in order to establish access to the producing formation. We adopted an \"\"agile\" approach and deployed a \"super magnet\" by slickline. Following the removal of the cement plugs we cleaned the well from proppant using coiled tubing with sand return management at surface.\u0000 The well which was originally planned to be abandoned due to the complexity of its integrity issues was successfully recovered. The integrity issue was fixed by installation of a new external casing patch using a hydraulic workover unit. The approach of using a combination of different well intervention methods enabled reviving the idle well and unlocking access to hydrocarbon reserves. Full passage to the target depth was confirmed which made the operation a full success. Challenges such as the presence of metal junk, logistics constraints to supply a large volume of water for long-interval milling and cleanout operations, management of abrasive sandy returns at surface were overcome through a collaborative approach between all parties involved.\u0000 This paper presents a case where we successfully brough back on production a well which had been shut in due to complex well integrity issues. We present the lessons learnt as many of these can be applied to other challenging projects. This show case reveals how the combination of different types of well intervention techniques can help restore production from a well with complex well integrity issues.","PeriodicalId":249690,"journal":{"name":"Day 2 Tue, November 01, 2022","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130286860","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":"A Machine Learning-Based Data Augmentation Approach for Unconventional Reservoir Characterization Using Microseismic Data and EDFM","authors":"J. Leines-Artieda, M. Fiallos-Torres, Amena Alharthi, S. Mahmoud, Abdullah Al Hashmi, Maryam Alqaydi, T. Ramsay, Yiwen Gong, Wei Yu, J. Miao, Alvaro Escorcia, Franklin Useche, Aamer Al Bannay, R. Fonseca, K. Sepehrnoori","doi":"10.2118/210989-ms","DOIUrl":"https://doi.org/10.2118/210989-ms","url":null,"abstract":"\u0000 Multi-stage hydraulic fracturing has recently gained strong interest in unconventional plays in the Middle East due to high natural gas production potential. However, prevalent characteristics of the area, including high-pressure / high-temperature (HPHT) conditions and presence of complex natural fracture networks, pose significant challenges to reservoir characterization. These challenges have motivated the development of an integrated workflow using microseismic data for the characterization of reservoir properties resulting from the interaction between natural and hydraulic fractures.\u0000 This study proposes a reliable method for modeling hydraulic fractures from scarce microseismic data. Initially, a microseismic model—based on field records of microseismic data and natural fracture spatial characterization—was developed. Issues related to limited microseismic data availability were tackled through combination of a probabilistic algorithm, Gaussian Mixture Model, and a DFN model. Then, the resulting synthetic microseismic events enabled the generation of a hydraulic fracture model using the embedded discrete fracture model (EDFM) and an in-house microseismic spatial density algorithm that captured major hydraulic fracture growth tendencies. Next, the created hydraulic fracture geometries were validated against a physics-based hydraulic fracture propagation model. Lastly, a single-well sector model—based on a corner point grid that honored the original 3D discrete fracture network (DFN)—was history matched, confirming the successful application of the proposed methodology.","PeriodicalId":249690,"journal":{"name":"Day 2 Tue, November 01, 2022","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129235442","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":"Assessment of Integrated MMV Plan for CCS Projects in Depleted Gas Reservoir and Saline Aquifer Offshore Malaysia: From 4D Time Lapse Seismic Perspective","authors":"P. Tiwari, Dr. Rabindra Das, M. N. F. C Mat, R. Leite, P. Chidambaram","doi":"10.2118/210938-ms","DOIUrl":"https://doi.org/10.2118/210938-ms","url":null,"abstract":"\u0000 There are many gas fields associated with large amount of CO2 concentrations (>50 mol%) in offshore Malaysia. Development of the contaminated gas fields is only possible if a geologically safe storage site is identified for the storage of produced CO2. The critical component of CCS project field development plan is monitoring of the storage site for the long-term containment and conformance security. 4D time- lapse seismic is key in monitoring, measurement, and verification (MMV) plan as it can demonstrate the periodic movement of stored CO2 within storage reservoir. Time-lapse seismic response depends on several parameters ranging from reservoir rock properties, initial fluid and saturation of CO2 during injection period. This study focuses on the different characteristics on 4D seismic attributes for carbonate and clastic reservoirs and discusses to effectively utilize for MMV.\u0000 The time-lapse 4D seismic has been traditionally used to identify the potential threats associated with reservoirs with enhanced oil recovery plan. The application of 4D seismic would benefits CCS project for monitoring CO2 plume migration along existing or induced fractures. The study was conducted on identified CO2 storage sites in both depleted carbonate gas reservoir and clastic saline aquifer. It highlights two methods applied in the 4D AVO analysis, that quantifies the changes in CO2 saturation within reservoir during injection. The Aki and Richards' approximation were analyzed for the effect of changes in gas saturations on the seismic amplitudes and the Smith and Gidlow's approximation for the reflection coefficient relationship between the AVO gradient/intercept attributes and reservoir fluid/properties.\u0000 The application of 4D seismic would benefits CCS project for monitoring CO2 plume migration along existing or induced fractures. The study was conducted on identified CO2 storage sites in both depleted carbonate gas reservoir and clastic saline aquifer. It highlights two methods applied in the 4D AVO analysis, that quantifies the changes in CO2 saturation within reservoir during injection. The Aki and Richards' approximation were analyzed for the effect of changes in gas saturations on the seismic amplitudes and the Smith and Gidlow's approximation for the reflection coefficient relationship between the AVO gradient/intercept attributes and reservoir fluid/properties. This study focuses on the different characteristics on 4D seismic attributes for carbonate and clastic reservoirs and discusses to effectively utilize for MMV.","PeriodicalId":249690,"journal":{"name":"Day 2 Tue, November 01, 2022","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123329491","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":"Experimental Investigation of High Pressure, High Temperature (HPHT) Adsorption of Methane and Natural Gas on Shale Gas Samples","authors":"J. Tsau, R. Barati, J. Zaghloul, M. Alhajeri, K. Bradford, B. Nicoud","doi":"10.2118/210981-ms","DOIUrl":"https://doi.org/10.2118/210981-ms","url":null,"abstract":"\u0000 The adsorption capacity of shale is commonly measured in the laboratory under low pressures. At low pressures, the excess adsorption capacity is approximately equal to the absolute adsorption capacity. Under high pressure, however, the excess adsorption is far less than the absolute adsorption capacity. The objective of this paper is to extend the adsorption measurements to a high temperature of 275 °F and pressure up to 9000 psi. Under such a HPHT, the adsorption curve shows a characteristic of supercritical high-pressure isotherm in which a critical desorption pressure can be identified. The adsorption isotherm under HPHT facilitates a better assessment of gas reserves for an effective assessment of shale gas reservoirs. The adsorption is measured based on a volumetric method. An in-house built setup was constructed to conduct the adsorption measurement at HPHT. The volume of sample cell and reference cell was calibrated with non-adsorbed Helium gas. Methane and field produced natural gas were used as adsorbate while the shale samples at different depth from a Gulf Coast organic shale were used as adsorbent. Excess adsorption measurements were carried out at reservoir temperature of 275 °F with 500 psi incremental pressure at a time until the pressure reaches 9000 psi. The absolute adsorption was calculated from the excess adsorption accordingly.\u0000 The excess adsorption isotherm shows a typical supercritical fluid adsorption behavior. The adsorption increases with pressure, reaches a peak point at which pressure is defined as critical desorption pressure (CDP), and then decreases at pressures above CDP. The CDP of methane is higher than that of natural gas while methane is a majority of its component. The maximum amount of adsorption determined from the measurement varies from 203 to 213 SCF/ton. The Langmuir model does a good job predicting the absolute methane adsorption but fails to properly describe the adsorption behavior of natural gas at high pressure. This work presents a HPHT adsorption measurement at pressures and temperatures typically seen in deep shale gas reservoirs. The supercritical fluid adsorption behavior presented may assist the assessment of gas reserve and development of gas production.","PeriodicalId":249690,"journal":{"name":"Day 2 Tue, November 01, 2022","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123381682","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":"An Integrated Solution for Reservoir Model Initialization with Areal and Vertical Composition Variation in the Presence of Tilted Contacts","authors":"K. Ghorayeb, S. Tahir, Shi Su, Nour El-Droubi, Georges Assaf, Samat Ramatullayev, Chakib Kada Kloucha, Hussein Mustapha","doi":"10.2118/211405-ms","DOIUrl":"https://doi.org/10.2118/211405-ms","url":null,"abstract":"\u0000 Capturing fluid composition variation and distribution in the reservoir is an essential first step for reservoir modeling. Vertical fluid composition variation is commonly considered. However, fluid samples taken from wells in different areas of a reservoir can highlight significant areal variation in the composition to be modeled. Fluid contacts may be tilted, and despite many studies on the subject, the setup is not straightforward. The combination of all three makes the initialization challenging and time consuming.\u0000 In this paper we describe an automated workflow that integrates fluid sample data and petrophysical data to generate an initial fluid composition distribution that captures vertical and areal composition variations and accurately computes the initial fluid distribution to represent tilted contact configurations and their associated transition zones.\u0000 Fluid sample data such as composition, pressure, temperature, and sampling depth are provided to an engine that computes composition variation with depth for each sample based on the equation of state (EOS) that characterizes the fluid behavior of the reservoir. The generated composition variation with depth for each sample is spatially distributed at their associated wells and is used to compute the areal composition distribution between the wells in the reservoir. This results in a tridimensional distribution of each fluid component representing the fluid model that captures both vertical and areal composition variations.\u0000 In parallel, saturation height functions and hysteresis models are used to automatically generate drainage capillary pressure data and associated imbibition and scanning curves used to capture the drainage and imbibition processes responsible for the paleo and current water saturation distribution in the reservoir.\u0000 The fully automated reservoir initialization process accounts for all available pressure-volume-temperature (PVT) samples. The solution is portable, significantly faster, and accurately captures complex reservoir geology and reservoir history. We present field examples of the proposed approach and illustrate its flexibility and associated comprehensiveness and efficiency.\u0000 The complete automation of complex initialization methods considering areal and vertical composition variation, combined with tilted contacts modeling, is helping to resolve significant challenges faced across the industry.","PeriodicalId":249690,"journal":{"name":"Day 2 Tue, November 01, 2022","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126199242","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":"Real-Time Compressional Sonic Log Prediction from Drilling and Mud Gas Data Using Machine Learning","authors":"Ruba M. Afifi, F. Anifowose, M. Mezghani","doi":"10.2118/211614-ms","DOIUrl":"https://doi.org/10.2118/211614-ms","url":null,"abstract":"\u0000 Sonic logs are important for deriving elastic moduli of rocks, which can be useful in calculating in-situ stresses, estimating safe drilling mud weight, controlling wellbore stability, and constructing velocity models for seismic processing. Practically, determining the geomechanical information of the subsurface in real-time can alleviate operational risks and improve formation evaluation. Since sonic logs are not acquired in real-time, machine learning can be utilized to estimate them in real-time using drilling parameters and mud gas data.\u0000 This study uses Random Forest machine learning technique to predict compressional wave slowness in real-time by utilizing surface drilling parameters and mud gas data. Out of a total of five wells, the regression model is trained with data from four wells. The input parameters for each depth point include conventional drilling parameters (rate of penetration, torque, weight on bit, etc.) and mud gas data. Various preprocessing techniques were applied on the input parameters prior to model training to ensure good quality. Validation was performed on wells with existing sonic logs that were not included in the training. Model performance is measured by the correlation coefficient and the mean absolute percentage error.\u0000 Results show that predicting compressional sonic logs in real-time is feasible using machine learning. First, a model was tested to observe the effect of excluding certain depth intervals with high uncertainty in data values on model performance. The model's performance was enhanced and gave better correlation coefficient and lower mean absolute error. Therefore, cleaning data of uncertain intervals before running the model can improve sonic log prediction. Second, we investigated the effect of adding mug gas data as input features on model performance. Improvement in sonic log prediction was observed in some cases, and not in others. A sensitivity analysis was conducted on the developed models to determine the relative importance of the various input parameters on compressional sonic log prediction.\u0000 Valuable information can be extracted from sonic logs in real-time to reduce operational risks associated with drilling. This study demonstrates the effectiveness of utilizing real-time data for compressional wave slowness prediction, saving significant time and cost. Through the use of machine learning, data cleaning, and model fitting, prediction can be automated. This allows for scaling up the analysis on all the data available. We plan to apply additional preprocessing techniques, include more wells, and perform feature selection on the data to improve the prediction accuracy.","PeriodicalId":249690,"journal":{"name":"Day 2 Tue, November 01, 2022","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121611647","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}