Technology Focus: Production and Facilities (December 2018)

The complex downhole tools in upstream oil & gas industry are subjected to internal and external pressure due to variety of fluids ranging from drilling mud to reservoir fluids which dictates downhole tool performance in the well bore. Extensive laboratory testing is needed to quantify the downhole tool performance which can be cost and time intensive process. An alternative approach is to conduct numerical simulations to investigate the real operating scenarios and predict the downhole tool performance including high pressure high temperature (HPHT) conditions which are difficult to set up in laboratory environment. The objective of this work is to underscore importance of advanced simulation technology in evaluating down-hole tool performance. To attest usage of simulations two examples are presented, the first one is utilization of computational fluid dynamic (CFD) simulations to analyze the performance of flow regulation inflow control device (ICD) for challenging multi-phase flow operations to predict onset of cavitation and second is to analyze the hold-down slip indentation dynamic operation using advanced explicit finite element simulation methodology. The completions ICD tool aids in maintaining uniform inflow of production fluid in horizontal and deviated wellbores by providing pressure drop utilizing nozzles. Advanced flow modeling is critical to understand the flow behavior through ICD and check for onset of phase change/cavitation of the production fluid. Three dimensional CFD simulations are conducted using pressure based algorithm for numerically solving mixture multi-phase model coupled with Reynolds-Averaged Navier-stokes (RANS) equation and k-ε turbulence model to predict onset of cavitation for given operating conditions. The dynamic hold down slips operation is important to set up a packer and during this step casing gets indented with the carbide buttons. The setting up of slips can cause localized permanent deformation in the casing and estimating the setting force along with hanging load capacity of the slip system is important to avoid permanent damage to the casing. Three dimensional explicit non-linear FEA is conducted to predict the stresses and deformations in the casing. Multi-phase simulations for ICD are conducted with different nozzle configurations and operating conditions. CFD results highlighted velocities, pressure drop through ICD and also indicated onset of cavitation for provided operating conditions. Advanced modeling results helped in configuring the ICD and operating conditions to avoid cavitation. FEA conducted for hold-down slip predicted the load needed to cause ~0.030" button indentation on casing and also provided insights in collapse analysis of the casing. A detailed presentation of the stress field helped in identifying the loading limits for this system and also probable failure locations due to loading. Advanced simulations helped in assessing the downhole tool performance for given operating envelopes and provided critical insights that delivered confidence in utilizing these tools for field operations.

Objectives/Scope The Laverda Field is an offshore waterflooded field developed with two long horizontal producers targeting two stacked high quality sandstone units. The oil producer LAV02ST2 is completed with sand screens and Inflow Control Devices (ICDs). Elevated Gas Oil Ratios (GORs) were experienced during start-up, which indicated free gas production downhole, raising concerns over ICD erosion and sand production. While the ICDs have defined operating limits in the presence of single-phase flow, the safe operating range in multi-phase flow conditions was highly uncertain. Given the significant risk of well failure due to erosion, additional bean up was halted pending studies to understand and quantify the erosion risk. Erosion risk was influenced by: the distribution of gas along the well (concentrated vs dispersed inflow), the presence of an open annulus and associated erosion risk due to solids production, and tolerance of the ICDs to higher velocities under three-phase flow. Methods, Procedures, Process Collaboration between subsurface and completions disciplines was required to understand the source of the gas and assess the risk to completions. Initially, production trends were analysed in conjunction with a review of geological data and numerical simulation insights to identify likely sources of gas and which areas within the well were more susceptible to gas exposure. Near-wellbore modelling using NETool® and GAP was undertaken to understand the range of feasible gas inflow scenarios and eliminate scenarios inconsistent with observed production data. The most likely scenario was then used to establish the relationship between total well rate and peak velocities in the ICDs, for a worse-case erosion outcome. To understand the risk of ICD erosion under multi-phase flow and potential for loss of well integrity, Computational Fluid Dynamics (CFD) modelling was conducted on a range of expected production scenarios to establish safe operating limits. Both, ICD slot erosion and housing erosion behaviour was investigated, as a function of peak ICD gas rate/velocity, well liquid rate and well GOR. Results, Observations, Conclusions The CFD study helped to establish a relationship between erosion rate and total downhole rate at reservoir conditions for various production scenarios, thus allowing calculation of erosion over the course of field life. A revised safe operating envelope was recommended for the oil producer in multi-phase conditions that allowed the production rate to be doubled without compromising well integrity. Novel/Additive Information Traditionally, industry physical erosion testing of the ICDs by the vendor is restricted to single-phase, liquid conditions only. Successfully benchmarking the CFD model to the single-phase physical tests allowed quantification of erosion rates in multi-phase flow and establishment of a safe operating envelope over the life of the well.

Horizontal wells are considered superior to vertical and deviated wells because they increase reservoir contact; however, they can cone unwanted fluids (gas, water) causing reduced oil recovery and early well abandonment. Inflow Control Devices (ICDs) are typically installed along the completion string to delay coning and restrict water/gas influx. Once the coning occurs, conventional ICDs, such as channels and orifices, were found to be inadequate in choking back the unwanted fluids. Thus, new types of "autonomous" ICDs, or AICDs, were developed that choke back unwanted fluids more than conventional ICDs. Conversely, such AICDs have limitations related to bulkiness, moving parts, wellsite adjustability, flow performance predictability, and erosion. To overcome these limitations, a new AICD, operating on a principle of a cyclone, was developed by a synergy of the latest numerical technologies, such as Computational Fluid Dynamics (CFD) utilizing a high-fidelity Large Eddy Simulation (LES) turbulence model, and Design of Experiments (DOE) techniques. This CFD-driven design optimization involved utilization of high-performance computing (HPC) coupled with experimental validation. A DOE matrix of CFD analyses runs was performed to identify a geometry that would generate significantly higher pressure drop for water and gas than for oil. Early multiphase testing on a prototype device validated the concept, and CFD was used to improve the understanding of the operating principle and hence the design. CFD was further used to extrapolate the flow performance to a wider range of operating conditions. An expanded flow performance map and the use of non-dimensional parameters led to the development of a mechanistic AICD performance model which further enhanced our understanding of AICDs and allowed reservoir software programs to evaluate the production performance of wells with AICDs versus wells with conventional ICDs or no inflow control. The overall result is the new cyclonic AICD presented herein which is: 1) relatively compact, 2) without moving parts, 3) erosion resistant, 4) superior in multiphase performance, 5) easily adjustable at the wellsite with many settings, 6) accurately modeled with CFD, and 7) easy to incorporate into state-of-the-art reservoir simulation models.

To prevent or minimize problems associated with water coning in horizontal oil producers, inflow control devices (ICDs) are installed along the wellbore to better equalize the toe-to-heel flux. Nozzle-based ICDs are popular because they are: 1) easy to model accurately, 2) virtually viscosity independent, and 3) easy to install at the wellsite with many unique settings. Nozzles can be installed either in the wall of the base pipe (radial orientation) or in the annulus between the base pipe and housing (axial orientation). The advantages of the former are: 1) smaller max running OD, and 2) no need for a leak-tight, pressure-rated housing. One disadvantage is the high exit velocity that raises concern of erosion or erosion-corrosion of the basepipe. To overcome this disadvantage, a new nozzle had been developed with a novel geometry that reduces the exit velocity about ten-fold compared to a conventional nozzle for the same pressure drop and flow rate. Computational fluid dynamics (CFD) was used to first fine tune the design to meet strict erosion-corrosion prevention requirements on the wall shear stress downstream of the nozzle for both production and (acid) injection directions, and then to develop flow performance curves for four different nozzles "sizes" that vary in their choking ability, thereby allowing many unique settings per joint at the wellsite. Full scale prototype manufacturing and flow loop testing were then performed to validate the CFD flow performance predictions and to demonstrate mechanical integrity and erosion resistance for high rate production and injection. The results, as presented herein, demonstrate a robust and commercially viable ICD design that: 1) has predictable flow performance using CFD, 2) minimizes erosion and erosion-corrosion in either direction, 3) minimizes running OD, 4) simplifies the housing design, and 5) allows easy installation at the wellsite with 34 unique settings per joint. Also discussed are two new advantages over other ICDs that were not anticipated in the original development.

As part of the Islands Project which involves the use of 4 artificial islands to drill & complete over 300 ERD wells in a giant offshore oilfield, several completion designs have been piloted to test & monitor their suitability for the brownfield development. One well design incorporated the use of Inflow Control Devices (ICDs) & swell packers which was ZADCO's first use of such technology in a production well. The technology was installed in the pilot well to test in-flow control along a 10,000ft lateral & to manage future water production. The Paper will cover: The design of the well detailing the ICD configurations & swell packer arrangements providing 15 compartments along the reservoir section, The inflow performance recorded annually along the lateral showing differing results, The outcome of an extensive intervention program in 2013 utilising different logging tools to record internal & external data, live camera to view condition in low water cut well & venturi tool to recover downhole samples that concluded the mechanical failure of ICDs in the heel, The extensive post-failure investigation undertaken such as extensive review of installed ICD design, flow assurance, computational fluid dynamic (CFD) simulations, laboratory testing for different conditions & materials, comparison of modelled with actual data to determine failure mode & The way forward for future ICD installations with initial short term solution & plans for future long term design solutions to give a required 30 year life.

Technology Focus The oil- and gas-production industry has experienced dramatic price swings over the past year. Crude-oil (spot) prices have varied from more than USD 120/bbl to less than USD 40/bbl since the third quarter of 2014. In high-price environments, technology can be developed economically to exploit additional resources. In low-price environments, technology must be deployed selectively to optimize production. New technology may still be developed and applied, but it is likely to be very focused on reducing operating costs; on the other hand, existing technologies may be revisited, to be applied more effectively. At all times, industry seeks to improve well productivity. Well productivity is critical during low-price cycles; it is directly related to cash flow and to reserves calculations. Major advances in inflow-control-device (ICD) design and installation have occurred over the past few years. These devices generally are used to manage water breakthrough or to improve the production profile across a large interval. The goal is to minimize workover requirements while optimizing hydrocarbon production costs. Paper SPE 171836 discussed results of an extensive study to compare actual well performance to design with ICDs. The study includes results of failure analyses, which showed that material selection is important for a device to reach its design life. System operation affects field productivity. Slugging flow in subsea flowlines and risers, leading to pressure surges and excessive liquid levels in the first stage separator, is a major contributor to downtime and suboptimal performance in offshore production facilities. Production facilities operate most efficiently when flows are fairly stable. Slug-suppression technology has been applied historically in shallow water and onshore facilities. Paper SPE 170731 described the successful use of active slug-suppression technology in a deepwater facility. This is an example of integrating existing technologies— slug suppression and process-simulation/ process-control theory. The number of subsea wells is continuing to increase. These wells typically are designed to higher standards than onshore or platform wells because interventions are difficult and costly. However, lower-cost options are needed in the event that an intervention is required. Paper SPE 173647 described a case study in which a contingency riserless (light) intervention plan was implemented. Although this technology may not be applicable to all subsea well- intervention needs, it demonstrates that lighter (lower-cost) options should be considered on the basis of an engineering assessment. The oil and gas industry is a cyclical business. Technology progress can be made during the high- or the low-price phase. As engineers, we have the responsibility to identify and apply appropriate technologies throughout all phases of the business cycle. Let us rise to the challenge. JPT Recommended additional reading at OnePetro: www.onepetro.org. SPE 170780 Autonomous Inflow-Control Valves—Their Modeling and Added Value by Eltazy Eltaher, Heriot-Watt University, et al. SPE 172776 Integrated Approach to Liquid Management for Deepwater Gasfield Developments by S. Ahmed, BG Group, et al. OTC 25656 Pipeline Repair Using Epoxy Technology by Kenneth Bryson, Subsea 7, et al.

American Petroleum Institute(1) Recommended Practices (API RP) 970 - Corrosion Control Documents (CCDs) and 584 - Integrity Operating Windows (IOWs) are becoming valuable resources in a Refinery Mechanical Integrity (MI) Program.1,2 The ability to usefully identify unit corrosion loops and document the expected damage mechanisms is critical for Risk-Based Inspection (RBI). When overlaid with susceptibility based on both normal and process upsets conditions, these become a benchmark for turnaround planning improvements in plant reliability programs. This paper will summarize both a plant-wide and a fleet-wide approach toward this process. One summarized approach will be an orderly progression for a single plant conducting RBI on most of the operating units and moving to CCD/IOW as part of a robust MI program. A second summarized approach will be an Owner-User implementation of this CCD/IOW process with a focus on a few similar typical refining units at multiple sites and on a pilot basis using multiple vendors to implement this project in a staged program.

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 183383, “Integrated Off-Bottom Cemented Inflow-Control-Device System Design Toward Well-Delivery Optimization,” by Mohammed A. Al Madan and Mazen Bu Khamseen, Saudi Aramco, and Hedy Suherdiana and Ahmad Al Abdulmohsen, Baker Hughes, a GE company, prepared for the 2016 Abu Dhabi International Petroleum Exhibition and Conference, Abu Dhabi, 7–10 November. The paper has not been peer reviewed. Off-bottom-cementing (OBC) operations are unique to Saudi Arabia and represent a very challenging approach to drilling and workover operations when deployed in combination with inflow-control devices (ICDs) across horizontal sections. The multitasking-valve (MTV) feature in upgraded ICDs offers safe, simple, and cost-effective deployment operations. This paper discusses the first deployment of an ICD system combined with an OBC system for a workover operation in a mature producer well in the Kingdom of Saudi Arabia. Introduction In wells where an OBC liner is required to cover nontargeted formations above the production zone, two methods of deployment can be used: the one-trip system and the two-trip system. These refer, respectively, to whether the OBC components are deployed in a single trip along with the ICD or in a second trip with string in the previously deployed ICD completion. The one-trip OBC ICD completion does not allow an inner-string application. Therefore, circulation while running in hole was ineffective in this producer, which caused deployment problems. The two-trip OBC ICD completion was then considered. The idea was to split the completion into a lower ICD completion, which is dropped off inside the openhole horizontal section with a setting sleeve. The earlier two-trip OBC ICD completion used an inner string, a circulating system, and an openhole-packer-setting tool. This allowed 100% circulation from the shoe during deployment of the lower ICD completion, although circulation rate is limited because of pumping through the small internal diameter (ID). The upgraded ICD with an MTV allows the lower completion to be deployed without an inner string while achieving 100% circulation at the shoe, which smooths operations and saves up to 24 hours of rig time. The MTV temporarily blocks the communication between string and annulus while running in hole. Once reaching the setting depth, MTVs are actuated by hydraulic pressure. All hydraulically set equipment can also be set at this point. Ultimately, in the case outlined in the complete paper, it was decided to combine once again the separated deployment into a single system by use of the MTV feature, which provides important functions for the one-trip OBC ICD completion—the ability to perform 100% circulation from the shoe and to set all hydraulic downhole tools with one setting ball.

Today, many wells in heterogeneous carbonate reservoirs throughout the Middle East and Caspian Sea area are being completed with long intervals and complex completion equipment, such as limited entry liners and inflow control devices (ICDs). Accurate modeling and understanding of fluid placement during a stimulation operation through such long complex completions can be quite challenging. In this paper, an integrated approach of modeling, experiments and computational fluid dynamics (CFD) simulations will be presented. A computational tool based on a transient one-dimensional (1D) approach has been developed in-house to model stimulation through such completions. In order to validate the 1D approach for reliable fluid displacement predictions, annulus fluid displacement experiments in perforated liners supported by CFD simulations have been conducted. The experimental setup consists of an outer Lucite pipe representing the well-bore geometry and an inner aluminum pipe with multiple perforations of variable diameter. The setup mimics the real field application in a 1:1 scale with respect to the pipe and perforation diameters while the test section is limited to 27 ft. The experimental procedure is as follows: fluid is pumped into the annulus through the perforations until the annulus is completely filled,the fluid tank is switched "on-the-fly" to the tank with the displacing fluid resulting in the displacement of the annulus fluid by the displacing fluid through the perforations. The experiments and the CFD simulations indicate that even with a single open perforation inside the 27-ft test section, the three-dimensional (3D) flow field around the perforation rapidly transitions to uniform annular flow within a few feet uniformly displacing the annulus fluid. The model also provides insight into various well injection processes in sandstone and carbonate formation, such as scale squeezes, solvent treatments, and HF acid treatments. Introduction The length of production and injection intervals in a single well continues to increase in order to contact more reservoir rock with a single wellbore penetration and improve project economics. Multiple, thick stacked reservoirs are accessed by vertical and deviated wells while thinner reservoirs are being exploited with longer and longer horizontal wells1–3. To keep up with drilling capability, completion technology has advanced considerably in the past few years. Horizontal wells are "compartmentalized" using mechanical and/or swellable packers. Within a given compartment, injection and production can be controlled by use of inflow control devices (ICDs), limited entry (LE) liners, and/or sliding sleeves. The liners also make it easier to enter the completion interval with logging tools, wire line, and coiled tubing. While various tools are available to evaluate long-term, steady-state production and injection into such wells, modeling of short-term, transient injection into such completions is very challenging due to the long lateral lengths, limited entry points from the liner to each compartment, and the presence of an open annulus with occasional packer isolations. This is especially important for long wells in carbonate formations as all wells require acid stimulation upon initial completion, and occasionally throughout the well life.

Looking back at our industry’s approach to produced water over the past several decades reveals a subtle but persistent transformation. The industry no longer considers the water as only a logistical problem, mostly pushed to the facilities or operations teams. Now, it is a front-and-center component of any life-cycle planning, with multiple pathways addressed by subsurface control, surface treatment technologies, reuse, injection, and safe environmental discharge. This paradigm shift in our industry is a direct result of coming to the realization of its own dependence on having an effective, economic, and sustainable plan for managing the water life cycle. Just in the past several months in the Gulf of Mexico, we have seen the commencement of several high-profile waterflood projects by major regional operators. This comes on the heels of the most recent action taken by the US Environmental Protection Agency to introduce a revised version of its discharge permit for the region. Across the land and in the prolific basins of Oklahoma, Texas, and New Mexico, regulatory frameworks are evolving to curtail seismicity induced by water injection. In Latin America, major operators continue to evolve with the changing guidelines and environmental regulations, committing to long-term sustainability goals such as a reduction in freshwater withdrawal, recycling and reuse, and efforts to improve discharged-water quality and develop advanced monitoring techniques. In the Middle East, major operators continue to improve water-management practices to maximize the use of this scarce resource for their operations and pursue improved water quality for environmental discharge. The North Sea region continues with water recycling and reuse as the cornerstone of planning and a risk-based approach to environmental discharge. Contrary to the common theme that associates the water problem with the large volumes produced—albeit, in most cases, larger than the oil production—the drivers influencing the planning for the water cycle have much more diversity than just the volumes. For most cases in the past, the simplistic technoeconomic approach was sufficient on its own by merely proposing the best available and economically viable solution. This approach no longer satisfies the broader social and environmental demands affecting the outcome. In fact, today, a concerted socio-technoeconomic group of drivers is dictating our planning for the water life cycle of any project. As the industry continues with the quest for technological innovations for more cost-efficient solutions at the operational level, it must do so with full adherence to evolving regulations and by prioritizing environmental protection. I have selected a few of the most recent papers in support of these megatrends affecting oilfield water management. Paper SPE 221002 provides an example of a decision matrix for an operator to define and design its produced-water-treatment strategy. It also provides a universal and comprehensive review of produced-water-management risks and challenges, not as an end-of-pipe solution but as comprehensive, multidimensional planning that must address technical challenges while maintaining economic viability within the confines of the regulatory framework of the region. Paper SPE 218794 provides a unique window to the application of the Internet of Things, including radio-frequency identification and global-positioning-system sensors for subsurface intelligent completions, and its deployment in deepwater Gulf of Mexico. It describes a real-life example of the deployment of such intelligent completions for zonal isolation as a component of subsurface water-management techniques. Paper SPE 218979 describes the environmental impact of sheening from overboard water discharge as the result of water-soluble organics. It provides a detailed chemical-treatment approach as a strategy in water management for overboard discharge. Recommended additional reading at OnePetro: www.onepetro.org. SPE 218616 Produced Fluid, Water Treatment Plant, and Boiler Feed Water for Steam-Generation Management at Mukhaizna Heavy Oil Field by M. Al-Asimi, Occidental, et al. SPE 219062 Water-Injection Optimization Based on Operational Key Performance Indicators by C.J.A. Furtado, Petrobras, et al.

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 208988, “Novel Application of Abrasive Jet Perforating To Restore Productivity of a High-Potential Inactive Horizontal Oil Producer,” by Sadaf S. Chishti, SPE, Steven H. Craig, SPE, Baker Hughes, and Edward J. Wheatley, SPE, ADNOC, et al. The paper has not been peer reviewed. The complete paper illustrates a novel methodology that enabled the safe application of coiled tubing (CT) abrasive perforation to increase production in a sour horizontal extended-reach (ER) oil producer. The well was underperforming at 10% of the anticipated production rate because of a damaged lower completion. To avert a costly workover, abrasive perforation with CT was selected as a safe alternative to conventional explosives-based perforating conveyed on electric line. Introduction An offshore horizontal ER producer well was drilled with a total depth (TD) in excess of 24,000-ft measured depth (MD). During the completion phase, a 4.5-in. liner with 16 inflow control devices (ICDs) and eight swellable packers was run with the ICDs in the closed position. Swellable packers were placed after every two ICDs. To open these ICDs, an internal pressure of 2,500 psi was required, achieved by dropping a ball that would seat in the float collar. Multiple attempts were made to pressure up and open the ICDs without success. The decision was made to run the upper completion with a plan to activate the ICDs using rigless CT intervention. After a drift CT run, multiple attempts were made to run a through-tubing inflatable packer bottomhole assembly (BHA) on CT to isolate and pressure up the well. All attempts failed to reach target depth, with repeated holdup at approximately 20,273-ft MD. Production-logging passes performed in injection mode determined that the well interval between 20,262 and 20,300 ft was taking more than 80% of the injected fluid. In a subsequent CT logging run, a caliper log identified that the liner section in this interval was parted and identified an openhole section with washouts in excess of 7-in. inner diameter. The results from the log are shown in Fig. 1, with the enlarged section representing the parted liner/openhole interval. Because the ICDs remained closed along with a damaged liner section, the options of recovery leaned heavily toward a rig-based workover for sidetrack and recompletion. Considering time and cost constraints, studies commenced to identify an efficient alternative to establish flow contribution from the inactive compartments by adding perforations. CT was chosen as the conveyance method based on previous success in reaching TD, and three options were evaluated. Based on the lowest risk level and availability of resources, the safest and most-viable option was abrasive perforation with CT. This technique uses a sand jet perforator, a downhole tool that uses high-pressure abrasive-laden fluids to penetrate the casing, liner, and cement and extend a cavity into the reservoir.

_ The relentless march of computational intelligence continues to redefine the paradigms of petroleum engineering, offering sophisticated solutions to long- standing challenges in subsurface characterization and operational optimization. A compelling triptych of recent research illuminates this trajectory, showcasing the burgeoning capacity of machine learning (ML) to unlock substantial efficiencies and enhance decision-making across the exploration and production lifecycle. Paper SPE 222299 presents a framework for synthesizing crucial openhole well logs by ingeniously leveraging readily available mud-log and logging-while-drilling data within the complex geological context of the Gulf of Thailand. The authors demonstrate that robust algorithms, particularly random forest and gradient-boosting regressors, can achieve remarkable predictive accuracy. This offers a pragmatic solution to populate data-deficient legacy wells, crucial for informed reservoir management, and promises tangible fiscal benefits by curtailing the necessity for costly conventional logging. Paper SPE 35892 introduces a physics-informed ML framework to elevate permeability prediction in notoriously heterogeneous carbonate reservoirs. By integrating physics-based constraints—specifically, modeling the discrepancy between core and nuclear-magnetic-resonance-derived permeability—this research enhances the predictive power of tree-ensemble algorithms. Physics-informed models transcend purely data-driven methodologies, offering more-robust and generalizable frameworks by embedding domain-specific physical understanding directly into the learning process, thereby bridging the gap between empirical observation and fundamental reservoir physics. Further exemplifying ML’s strategic value, paper SPE 224365 details an intelligent system for optimizing depth selection in formation pressure testing (FPT). An artificial neural network trained on an extensive suite of well logs demonstrates a remarkable 94% specificity in identifying depth intervals likely to yield invalid pressure data. This capability is paramount in minimizing resource expenditure on unproductive tests, particularly in complex reservoir settings. The model provides a data-driven, consistent alternative to traditional, often subjective, FPT planning, underscoring the value of ML in derisking and streamlining critical field operations. Collectively, these contributions signal a mature phase in the application of ML within the oil and gas sector. No longer confined to academic exploration, these techniques are providing robust, field-deployable solutions that enhance subsurface interpretation, improve operational foresight, and potentially drive economic benefits. The continued success of such endeavors will undoubtedly rely on the synergistic fusion of domain expertise, high-quality data, and the ever-evolving sophistication of ML algorithms. Summarized Papers in This August 2025 Issue SPE 222299 - Machine Learning Unlocks Potential of Mud Logs, LWD in the Gulf of Thailand by Sethawut Palviriyachote, Texas A&M University, et al. OTC 35892 - Machine-Learning Approach Optimizes Formation-Pressure Testing in Complex Reservoirs by Ahmed K. Khassaf, Basrah University of Oil and Gas, et al. SPE 224365 - Physics-Informed Machine Learning Enhances Permeability Prediction in Carbonate Reservoirs by Mohammad K. Aljishi, University of Oklahoma, et al. Recommended Additional Reading at OnePetro: www.onepetro.org. SPE 224566 - Applying Machine Learning in Highly Laminated Formation To Differentiate Pay and Nonpay Zones and Resolve Rt for Fit-for-Purpose Azimuthal Resistivity Tool Selection by Armando Vianna, Baker Hughes SPE 223396 - Early Signs of Gas Recognition Based on Machine-Learning Analysis of Passive Acoustics by Y. Maslennikova, TGT Diagnostics, et al.

_ For decades, artificial lift optimization has relied heavily on manual intervention, periodic well tests, and the judgment of experienced engineers. Electric submersible pumps (ESPs), gas lift, and beam pumps (the three most widely used lift systems) each have presented their own optimization challenges, such as balancing set points, managing compressor constraints, and interpreting dynamometer cards. These processes, while effective, have historically been time-intensive, reactive, and difficult to scale across large well inventories. The accelerating deployment of machine learning (ML) and automation is changing this landscape. By embedding intelligence into the control loop, operators now can move from reactive decision-making to proactive, continuous optimization. What was once a manual task handled by individual engineers is increasingly performed by autonomous systems that learn from data, adjust in real time, and scale effortlessly across hundreds or thousands of wells. Recent case studies illustrate how this transformation is unfolding across different lift types, each demonstrating that the age of autonomy in artificial lift is no longer aspirational but is now an operational reality. Neural-network models trained on ESP data sets in the Permian Basin now recommend and directly write optimal pump set points, as shown in paper SPE 219528. The deployment delivered a 2–4% oil uplift and longer run life, while demonstrating full self-pumping capability, where pumps operate with minimal human oversight. In gas lift, ExxonMobil’s large-scale rollout of a closed-loop optimization workflow has been equally impactful. As detailed in paper SPE 219553, more than 1,300 wells are now managed by an automated system that runs multirate tests, updates downhole pressure models, and applies ML for wells without gauges. The outcome: a consistent approximately 2% production uplift, achieved with little incremental operational or capital expenditure. On the beam-pump side, manual interpretation of dynamometer cards is being replaced by real-time ML classification. In paper SPE 224979, more than 700,000 dynacards were analyzed with models such as XGBoost and convolutional neural networks, achieving approximately 95% classification accuracy. By integrating with OSIsoft AF and exception-based surveillance, the solution provides predictive analytics and proactive alerts, reducing downtime and extending equipment life. When comparing the three approaches, some clear distinctions emerge. In ESP optimization (SPE 219528), operators relied on neural networks to recommend and autonomously adjust set points, achieving production uplift across more than 200 wells. Gas lift optimization (SPE 219553) took a broader fieldwide approach, scaling a closed-loop workflow to more than 1,300 wells, where multirate testing and ML models continuously updated injection rates, delivering uplift at minimal incremental cost. Meanwhile, beam-pump optimization (SPE 224979) focused less on direct production uplift and more on reliability and predictive surveillance, where ML models enabled proactive maintenance and reduced downtime. Despite their differences, the three initiatives share commonalities: Each system moved from manual, engineer-driven adjustments to automated and autonomous optimization; each leveraged ML in combination with existing field infrastructure; and each demonstrated that even modest per-well improvements, when scaled across hundreds or thousands of wells, translate into substantial fieldwide gains. Across ESPs, gas lift, and beam pumps, these case studies demonstrate a unifying shift: ML is redefining artificial lift as a self-optimizing, continuously learning system. Production uplifts of 2–4%, when multiplied across fields, translate into substantial incremental barrels. Equipment longevity improves as systems learn to operate within optimal ranges, while engineers are freed from repetitive monitoring to focus on higher-value analysis. The advances described here are more than isolated technical improvements; they are signposts of a broader digital transformation across upstream operations. Artificial lift, long the domain of manual adjustments and engineer intuition, is now becoming a proving ground for autonomy. By embedding AI into the very core of production systems, operators are not just optimizing individual wells; they are building the foundation of the digital oilfield of the future, where decisions are data-driven, workflows are autonomous, and engineers focus their expertise on complex challenges rather than routine tuning. Summarized Papers in This October 2025 Issue SPE 219528 - Machine Learning Optimizes Autonomous ESP Use in the Permian by Ryan D. Erickson, Vital Energy, et al. SPE 219553 - Gas Lift Optimization in the Permian Uses Machine Learning, Artificial Intelligence by Pooya Movahed, ExxonMobil, et al. SPE 224979 - Real-Time Machine Learning Enhances Dynacard Surveillance, Predictive Analytics by Shifa Khaliah Al Kiyumi, Daleel Petroleum, et al.

The energy transition and global geopolitical situation present numerous oil and gas operators with opportunities to accelerate production growth and monetize hydrocarbon resources. While rapid production growth comes with proportional risks, it becomes crucial for reservoir surveillance engineers to quickly identify, derisk, and mitigate subsurface performance uncertainties. In this demanding scenario, the need for high-frequency reservoir performance surveillance is more critical than ever. Fortunately, advanced technologies have emerged as a refuge for subsurface engineers facing these challenges. One such technology is fiber optics, which has matured significantly over the past two decades, allowing for real-time well-performance overviews in various applications. This capability enhances well-management efficiency and enables prompt corrective actions, as demonstrated in papers SPE 200088 and SPE 200806. Along similar lines, the dynamic nature of the industry has also driven subsurface practitioners to think innovatively and apply existing technologies for out-of-the-box solutions. For instance, tracers, traditionally used for understanding subsurface connectivity, are now being used to calibrate surface networks and optimize gas lift injection performance. Such unconventional approaches have been explored in paper SPE 207431, highlighting their effectiveness. In addition to tracers, technologists are turning rock cuttings, often considered mere waste, into valuable information. As demonstrated by paper SPE 206214, these insights aid in elucidating depositional sequences and fluid-migration paths, thereby facilitating better field development decisions. Furthermore, technology groups are working on innovative solutions that use advanced sensing and artificial-intelligence (AI) -based technologies. As a result, interventionless downhole pressure and temperature surveying are no longer distant dreams (paper IPTC 22255). In another example, the power of AI has elevated sensing intuition, optimizing reservoir and fluid characterizing operations and leading to improved drilling-cost efficiency and the quality of well delivery (paper SPE 210091). Embracing advanced technologies is vital for oil and gas operators to optimize production, reduce risks, and make informed decisions in the evolving energy landscape. From real-time fiber optic monitoring to unconventional tracer applications and AI-driven solutions, reservoir surveillance engineers now have an array of tools at their disposal to drive the industry toward a more efficient and sustainable future. Recommended additional reading at OnePetro: www.onepetro.org. SPE 200806 An Industry Overview of Downhole Monitoring Using Distributed Temperature Sensing: Fundamentals and 2 Decades Deployment in Oil and Gas Industries by Mohammad Soroush, RGL Reservoir Management, et al. SPE 206214 Reservoir Architecture and Fluid Connectivity in an Abu Dhabi Oil Accumulation by Erik Tegelaar, Triple EEE, et al. IPTC 22255 Sensor Ball: Field Deployment of Autonomous and Untethered Surveillance by Mohamed Larbi Zeghlache, Saudi Aramco, et al. SPE 211543 The Sensor Ball Revolutionizes Wireline Operations by Nasser M. Al-Hajri, Saudi Aramco, et al.

In the current study, Artificial Intelligence (AI) approach was used for the learning of a physical system. We applied four inputs and one output in the learning process of AI. In the learning process, the inputs are space locations of a BCR (bubble column reactor), which are x, y, and z coordinate as well as the amount of gas fraction in BCR. The liquid velocity is also considered as output. A variety of functions were used in learning, such as gbellmf and gaussmf functions, to examine which functions can give the best learning. At the end of the study, all of the results were compared to CFD (computational fluid dynamics). A three-dimensional (3D) BCR was used in this research, and we studied simulation by CFD as well as AI. The data from CFD in a 3D BCR was studied in the AI domain. In AI, we tuned for various parameters to achieve the best intelligence in the system. For instance, different inputs, different membership functions, different numbers of membership functions were used in the learning process. Moreover, the meshless prediction was used, meaning that some data in the BCR have not participated in the learning, and they were predicted in the prediction process, which gives us a special capability to compare the results with the CFD outcomes. The findings showed us that AI can predict the CFD results, and a great agreement was achieved between CFD computing nodes and AI elements. This novel methodology can suggest a meshless and multifunctional AI model to simulate the turbulence flow in the BCR. For further evaluation, the ANFIS method is compared with ACOFIS and PSOFIS methods with regards to model’s accuracy. The results show that ANFIS method contains higher accuracy and prediction capability compared with ACOFIS and PSOFIS methods.