Dung T. Phan, Chao Liu, M. AlTammar, Y. Abousleiman
{"title":"Predicting Mud Weight Window from Well Logs by Integrating Deep Neural Networks and Physics Models","authors":"Dung T. Phan, Chao Liu, M. AlTammar, Y. Abousleiman","doi":"10.2523/iptc-23340-ms","DOIUrl":"https://doi.org/10.2523/iptc-23340-ms","url":null,"abstract":"\u0000 The selection of an appropriate mud weight is important in drilling operations, as it plays a pivotal role in mitigating the potential for costly wellbore instability issues. The safe mud weight window is typically computed through analytical solutions that necessitate detailed rock properties as integral inputs. Conventionally, these rock properties are estimated based on well logs through empirical correlations. This paper introduces a wellbore stability analysis workflow that makes two changes to the conventional methodology. First, microporomechanics models are used to upscale the nano and micro properties of the mineral constituents to the macro rock properties. Unlike the correlation methods, this scientific approach can explain the origin of the rock properties. To help get the mineral composition data, a deep neural network (DNN) is trained on 15,979 data points to predict the volume fractions of silt inclusions, clay, and kerogen from gamma ray, resistivity, density, neutron porosity, and photoelectric logs. Second, another DNN is used in the workflow to speed-up the analytical solution for mud weight window computation. This DNN is trained to predict the mud weight window from in-situ stresses, pore pressure, well trajectory, and the rock properties. Its prediction is used as the starting point in the analytical wellbore stability solution to quickly determine the correct mud weight window. To demonstrate the practical application of this workflow, evaluations were conducted using a 480-foot shale well segment comprising 961 depth intervals. The results show that the hybrid approach can calculate 961 mud weight windows 5 times faster than the purely analytical solution.","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"23 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528375","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}
Xidi Lyu, Kexi Liao, Zihan Zou, Guoxi He, Shitao Liu
{"title":"Effects of Flow Velocity on Biofilm formation and corrosion behavior of L245 steel in the presence of sulfate reducing bacteria","authors":"Xidi Lyu, Kexi Liao, Zihan Zou, Guoxi He, Shitao Liu","doi":"10.2523/iptc-24640-ms","DOIUrl":"https://doi.org/10.2523/iptc-24640-ms","url":null,"abstract":"Shale gas is a type of unconventional natural gas that is found primarily within reservoir rock sequences dominated by organic-rich shale, and is usually exploited by hydraulic fracturing technology, which typically requires a large amount of water to be injected into the gas well, and when the fracturing process is completed, a portion of the injected water immediately flows back. The fracturing flow-back fluid contains a large number of microorganisms when it enters the surface gathering and transportation system, resulting severe internal corrosion of the pipelines, especially those built during the early exploitation process, using carbon steel like L245 steel[1]. The anoxic environment and large amount of fluid accumulation in the pipeline provide appropriate conditions for the growth and reproduction of microorganisms, which increased the risk of Microbiologically Influenced Corrosion (MIC).\u0000 MIC is a prevalent form of corrosion instigated by the bioactivity of diverse microorganisms. Representing a substantial challenge in the oil and gas sector, it is estimated that MIC accounts for approximately 40% of all incidents of internal pipeline corrosion[2]. SRB are typically considered the primary culprits in causing MIC, mainly because SRB are often found at the sites of corrosion believed to be associated with MIC[3]. SRB is a general term for a group of bacteria that are widely distributed in anaerobic environments, such as soil, seawater, river water, underground pipes and oil & gas wells where are rich in organic matter and sulfate[4-6]. The presence of SRB will lead to the corrosion of metal pipelines and equipment, moreover, its corrosion products FeS and Fe(OH)2 and the bacteria themselves will cause the blockage of pipelines and formation, and affect the subsequent gas production and development. SRB can use sulfides with valence states above -2 as electron acceptors, including HSO3, S2O32- and element S, to reduce S to a stable -2 valence. SRB is a strict anaerobe, its growth and reproduction are inhibited when exposed to oxygen, but it can survive for a period of time[7]. The theories related to SRB-induced corrosion include cathode depolarization theory[8, 9], metabolite corrosion theory[10-12], concentration difference cell theory[13], Extracellular Electron Transfer (EET) theory[14, 15] and Biocatalytic Cathodic Sulfate Reduction (BCSR) theory[16]. According to the researches of many scholars, factors such as biofilm structure[17, 18], ambient temperature[19], pH level[20], Cl−[21], CO2[22], H2S[23], cathodic protection potential[24, 25] and magnetic field[26] all can affect the corrosion behavior of SRB.\u0000 In oil and natural gas pipeline, the flow of medium is complicated, and the influence of flow conditions on corrosion behavior of SRB cannot be ignored. The change of flow regime and flow velocity can affect the mass transfer in the pipeline, and thus affect the biochemical reaction process[27]. Furthermore, the change of shear ","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"36 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140527777","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":"Evaluation of Real-Time and Post-Drilling Petrophysical Data Acquisition Impact on Wellbore Stability and Mechanical Rock Integrity","authors":"Ammar Qatari","doi":"10.2523/iptc-23354-ms","DOIUrl":"https://doi.org/10.2523/iptc-23354-ms","url":null,"abstract":"\u0000 The objective of this paper is to examine filtrate and mud solids invasion effect on wellbore stability and rock mechanical integrity. A stable wellbore depends on the mechanical and chemical interaction between the wellbore fluid and the walls of the wellbore. Excessive wellbore pressure can cause lost circulation and low pressure of the wellbore can cause blowout or collapse. Multiple factors affect mechanical integrity of the rock including the time at which the acquisition of rock mechanical data was taken in the subsurface. The impact of invasion is measured by the exploitation of real-time and post-drilling petrophysical data. A thorough investigation of invasion and its effect on rock mechanical properties is performed to establish a full understanding of the association between time dependency and rock integrity. A mechanical earth model (MEM) is built utilizing petrophysical data acquired in both real-time and post-drilling. Mechanical properties are then cross checked with core measurements to examine the accuracy of the results. The effect of invasion is then highlighted showcasing the time dependency effect on both wellbore stability and rock mechanical integrity.\u0000 Leveraging real-time and post-drilling petrophysical data across abrasive sandstone formation is key to investigate invasion effects. The effects were witnessed in the readings of resistivity. Separation of deep, medium, and shallow resistivities were observed highlighting the invasion effect due to the time passed after the drilling process and before logging the section. When it comes to invasion effects on strength of the rock, an (MEM) was run on a well with both LWD and wireline acoustic data. Fracture point was analyzed for the effects of invasion. A data comparison is highlighted showcasing the effect of time on the integrity of the rock. Capillary force and osmotic pressure effects are examined and cross checked with the logged data and wellbore stability impact. This paper examines the direct impact of invasion on the mechanical properties of the rock along with wellbore stability. Complex formations can be problematic in lithology during the drilling operation where it might be capable of creating issues such as stuck pipe. The geomechanics of borehole stress has a direct impact on the hazards and problems encountered during drilling operation which causes inefficiency in terms of time and cost spent operationally. The full understanding of invasion effect is a potential solution to such issues.","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
K. Nguyen, A. Mehrabian, A. Santra, D. Phan, A. Bathija
{"title":"Lost Circulation Material Size Selection for Naturally Fractured Rocks","authors":"K. Nguyen, A. Mehrabian, A. Santra, D. Phan, A. Bathija","doi":"10.2523/iptc-24460-ms","DOIUrl":"https://doi.org/10.2523/iptc-24460-ms","url":null,"abstract":"\u0000 This paper presents a scheme for designing lost Circulation Material (LCM) blends that are commonly used to mitigate loss of wellbore drilling fluid through natural fractures of rock formations. The method involves using the history of drilling fluid loss rates to estimate the mean aperture size of the formation natural fractures. This estimate is enabled via an inverse solution based on a nonlinear optimization algorithm to obtain the most likely value of the effective permeability of the natural fractures network. The inverse solution embeds a forward semi-analytical solution that models the displacement of formation rock fluid by the drilling fluid as the losses occur. The forward solution accounts for yield-power law rheology of drilling fluid and considers the formation fluid displacement occurring through a network of connected natural fractures, as opposed to a single isolated fracture. Once the mean aperture size is determined, a blend of selected LCMs may be recommended via a particle size criterion that optimizes the LCM particle size distribution for effective plugging of fractures. The overall LCM design scheme is discussed via a case study.","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"35 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528350","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":"Prediction of Microbial Induced Bacteria Using Innovative Semisolid Growth Media for General Aerobic Bacteria at Specific PH","authors":"Mohamed A. Mahmoud, Ahmed H. Al-Salman","doi":"10.2523/iptc-24637-ms","DOIUrl":"https://doi.org/10.2523/iptc-24637-ms","url":null,"abstract":"\u0000 Structural steel is widely used in marine environments because it is strong, readily available, easy to fabricate, and cost-effective. But steel is also subject to corrosion. Microbiologically influenced corrosion (MIC) plays a critical role in the pipeline corrosion process, caused by electrochemical reactions created by microorganisms that form ‘biofilms’ on immersed steel structures. The close monitoring of microbial growth is an essential process to protect the structural steel from biofilm formation. A semisolid growth media for quantitative and qualitative analysis of general aerobic bacteria (GAB) was studied and counterchecked with commercially available ready-made media Paddle tester double-sided slides, to prove the suitability to use the Total Coliform agar media with a two-day incubation at 35°C, for quantitative determination of GAB colonies at a specific pH range from 5.5 to 7.5. Several trials were conducted, including water streams at upstream facilities, rich with GAB and Coliform sources, and all the obtained results from both media were matched.","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"475 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528189","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}
Mahesh Narayanan, Michael Macphee, Robert Weight, Ghaith Alghaithi
{"title":"Application of Representative Stochastic Models to Guide Development Decision Making in Large Unconventional Projects with Variable Fluid Composition","authors":"Mahesh Narayanan, Michael Macphee, Robert Weight, Ghaith Alghaithi","doi":"10.2523/iptc-23214-ms","DOIUrl":"https://doi.org/10.2523/iptc-23214-ms","url":null,"abstract":"\u0000 Commercial development of large green field unconventional projects with concurrent late-stage appraisal and initial development drilling is fraught with challenges. While the resource may be laterally extensive, extracting the resource efficiently is an engineering challenge that involves decision making at multiple stages to sequence and stack segments so as to maximize value and minimize risk. In large unconventional developments, allocating capital for appraisal and development sequencing benefits from a structured stochastic approach addressing risks and uncertainties to remove subjectivity. This paper illustrates the application of stochastic methods to guide management decision making during initial project development.\u0000 Large unconventional plays show spatial variability in fluid composition and productivity. A good appraisal program ensures sufficient wells are drilled, completed and tested to understand this variability. Learnings from such programs combined with learnings from analogue wells aid in categorizing PVT and well performance variability to identify priority areas of focus. Based on this analysis, representative models are determined for fluid windows incorporating a range of expected well deliverability. Using a structured stochastic approach, these representative models leverage a bespoke economic workflow integrating multiple uncertainties, constraints, costs and risks through a stochastic method. The workflow shown in this paper is based on synthetic data.\u0000 Based on a range of outcomes, decision making metrics such as probability of commerciality, expected monetary value and peak funding exposure are calculated integrating value of information criteria. The key output from this integrated workflow enables prioritization of focus areas for appraisal and development including stacking and sequencing of resource segments to ensure effective capital allocation and supporting optimum development value.\u0000 This paper highlights the benefit of applying a stochastic economic method to guide management decision making at the early stages of project development. The aim is to support management with an unbiased scientific approach which considers multiple uncertainties. This method helps prioritize appraisal and development options with multifaceted criteria for decision making and capital allocation.","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140527619","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}
Syed Hamza Ahmad, R. Anwar, Arif Yousaf, S. Y. Khokhar, Hossam A. Elmoneim, Abdul Asad
{"title":"Engineered Polymeric Solution for Lost Circulation Treatment in Fractured Limestone and Sandstone Formation: Case Studies","authors":"Syed Hamza Ahmad, R. Anwar, Arif Yousaf, S. Y. Khokhar, Hossam A. Elmoneim, Abdul Asad","doi":"10.2523/iptc-24415-ms","DOIUrl":"https://doi.org/10.2523/iptc-24415-ms","url":null,"abstract":"\u0000 Lost circulation is a major concern during drilling and workover operations, particularly in aging fields and depleted reservoir, resulting in significant financial and time losses. In addition to the loss of expensive drilling fluids, it also leads to wellbore instability and drill string sticking, necessitating additional resources and time for safe operation. Despite significant research and engineering efforts, the use of traditional lost circulation materials (LCMs) remains limited due to operational and technical constraints. These materials are often solid-laden, limiting their use with advanced BHAs containing directional drilling and MWD tools. Similar challenges exist during rig less well intervention operations that use coiled tubing (CT) for well intervention solutions.\u0000 To address these challenges, a temperature-activated anionic polymer combined with a carboxylate complex cross-linking agent is formulated to produce a rubber-like ringing gel structure that reduces the formation permeability to milli darcy immediately once cross linking starts and improves wellbore stability by strengthening the formation, rather than just plugging the sand face. In addition to being solids-free, the product is non-biodegradable and insoluble in acid enhancing the product's robustness and effectiveness in workover operations. This paper presents two case studies that demonstrate the successful implementation of the engineered LCM solution in drilling and workover operations. In first case, the product was deployed thru the drill bit to seal off naturally fractured limestone that had caused the drill string to become stuck due to total losses in the underlying thief zone and unstable shale above it. The polymeric LCM for formulated to initiate immediate cross-linking to effectively seal off the fractures. To increase structure sturdiness, it was reinforced with a silicious-based bond enhancer. It immediately shuts off the thief zone and allows to establish returns and stabilize shale to release the stuck string. In a different scenario, the product was formulated and applied using Coiled Tubing (CT) to seal off a low-pressure (BHP ~600psi) depleted sandstone formation with extremely high bottom hole temperature (>300degF). This enabled safe perforation of the deeper zone and the addition of reserves without requiring rig workover.\u0000 The polymer gel is solids-free, non-biodegradable, and acid-insoluble, enhancing its effectiveness. Two case studies demonstrate the successful use of this engineered LCM solution. In one case, it sealed off fractured limestone to cure complete loss and release stuck drill string, while in another, it sealed a low-pressure depleted sandstone formation via coiled tubing, enabling safe perforation and reserve addition. This innovative approach overcomes traditional LCM limitations for improved well isolation. This approach highlights the limitations of traditional LCMs and offers a new opportunity to design ringing polymer ","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"47 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140527775","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 Research of Imbibition Law in the Continental Shale in Sichuan Basin in China","authors":"Chao Zhou, Yashu Chen, Zuqing He, Zhifa Wang, Wei Zhang, Yuzhu Xu","doi":"10.2523/iptc-23286-ms","DOIUrl":"https://doi.org/10.2523/iptc-23286-ms","url":null,"abstract":"\u0000 Marine shale has been developed successfully in China, however, the exploration and development of the continental shale is still limited. Study about imbibition and influence factors of the continental shale is insufficient. The objective of the proposed paper is to design and conduct an imbibition experiment to research imbibition rate, imbibed volume, induced crack and influence factors in the Jurassic continental shale in Sichuan basin in China. The imbibition experiment is developed based on the low field Nuclear Magnetic Resonance(NMR) and accurate weighting. The permeability, porosity and mineral composition of shale samples of LU Formation and DD Formation are measured and the differences are analyzed. The change of permeability and porosity before and after the imbibition process is set as the evaluation index and the influence factors of imbibition in the continental shale are analyzed. The influence factors include lithology, imbibition fluid, imbibition pressure and clay content. Besides, the wettability of the continental shale is estimated in the experiment. The experimental results show that the imbibition capacity of the limestone sample is weaker than that of shale samples, and the shell limestone interlayer in the continental shale reservoir may inhibit the imbibition and crack propagation in the shale. Oil phase may enhance the crack propagation after the shale samples induced crack in aqueous phase, and the complicated phase imbibition in the continental shale reservoir may be beneficial to the permeability improvement. The forced imbibition has weaker capacity of crack induction and permeability improvement compared to the spontaneous imbibition, and the influence of the reservoir confining pressure on the imbibition should be considered during the well shut-in process after hydraulic fracturing. The higher clay content shale sample has stronger capacity of crack induction and permeability improvement compared to the lower clay content shale sample. The wettability of the continental shale sample is water-wet. The imbibition experiment reveals the imbibition law and the induced crack character of the continental shale samples, whose results fill the gap in existing studies and have a theoretical guidance for the shut-in and flowback design in the continental shale reservoir.","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"48 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140527986","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. Baghdadi, Souvik Sen, P. Chakrabarti, J. Vossen, Kashif Malik, Ivan Salmin, Munir Bashir, Ahmed Bakr
{"title":"An Integrated Engineering Approach","authors":"A. Baghdadi, Souvik Sen, P. Chakrabarti, J. Vossen, Kashif Malik, Ivan Salmin, Munir Bashir, Ahmed Bakr","doi":"10.2523/iptc-23351-ms","DOIUrl":"https://doi.org/10.2523/iptc-23351-ms","url":null,"abstract":"\u0000 This study presents a case of successful delivery of a challenging build-up and lateral section through heterogenous lithologies from an exploration field in the Middle East using an integrated multidisciplinary approach of optimization, planning and execution. Based on the offset well drilling experiences, poor ROP, mechanical instability, and differential sticking against some of the highly porous and permeable carbonate reservoirs were identified as the main drilling challenges impacting delivery for the 8-1/2\" and 6-1/8\" sections parallel to the regional minimum horizontal stress azimuth. Comprehensive geomechanical modeling and wellbore stability analyses were carried out to recommend a safe mud weight window to tackle mechanical instabilities. Utilizing an optimum drill bit design ensured improved durability, trajectory control, a higher rate of penetration and resulted in a 33 % performance improvement on the field average. Drilling fluid chemistry was optimized with required bridging concentrations based on particle size distribution assessment. The 7\" liner shoe placement and drilling practices were optimized based on the offset well events and subsurface characteristics to ensure successful execution of the landing section. Real-time monitoring of the LWD data (includes density imaging), aided by right-time geomechanical advisory support ensured successful well delivery without any significant drilling challenges. As a result of the implementation of this systematic and integrated multidisciplinary approach, both sections achieved geological objectives with zero NPT. The well was delivered 8.6 days ahead of the plan, and 14 days ahead of the best similar well.","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"47 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528001","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":"Machine Learning Classifier for Detecting Non-1D Features Using Deep Directional Resistivity Measurements","authors":"X. Zhong, J. Jith, Y. Chang, J. Gremillion","doi":"10.2523/iptc-23464-ms","DOIUrl":"https://doi.org/10.2523/iptc-23464-ms","url":null,"abstract":"\u0000 Currently, most geosteering jobs can rely on 1D inversion to accurately capture the properties of multiple planarly layered formations in real time. However, when complex non-1D features are present in the formation, higher dimensionality inversions will be required, which need intensive computation resources and more data channels containing 3D information sent to the surface. When abnormal results from 1D inversion are observed, switching telemetry rates and starting higher-order inversions is usually late, which inevitably delays the real-time geosteering decision.\u0000 To address this, we have developed a machine learning classifier capable of early detection of non-1D features in the formation before the drill bit reaches the higher dimensional feature. A large number of synthetic formations were generated with and without non-1D features that included faults, water coning, and sand injectites, etc., and then fed into a 3D forward model to generate the deep directional resistivity measurements. We trained the classifier to distinguish between 1D and non-1D cases with high accuracy, specifically employing a multilayer perceptron classifier, which is both accurate and suitable for downhole deployment.\u0000 In practice, this classifier can signal the presence of non-1D features, dynamically select telemetry channels, and initiate specialized inversions in real time. Synthetic and field testing validated its effectiveness, achieving over 80% accuracy when the tool is even 10 m from a non-1D feature, with increasing accuracy as the tool approaches the feature. Field results aligned with geological interpretations, affirming the model's robustness and accuracy.\u0000 This innovation enhances the ability to recognize complex formations during drilling, automating non-1D inversions and improving bandwidth management in real time, which ultimately increasing drilling speeds. This is one step in the journey towards autonomous geosteering.","PeriodicalId":518539,"journal":{"name":"Day 3 Wed, February 14, 2024","volume":"46 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528002","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}