Performance evaluations of oil and gas assets are crucial for continuously improving operational efficiency in the mainstream petroleum industry. The success of such evaluations is largely driven by the analysis of the data accumulated during the asset's operational cycle. Usually, the amount of data stored in the databases dramatically exceeds the ability to approach the analysis with traditional spreadsheet-based tools or linear modeling. In this study we use data mining with multivariate predictive analytics and monetize on the value of data by transforming the inferred information into knowledge and further into rigorous business decisions. With the expansion of the Digital Oil Field and transformation into the 4th Industrial Revolution, the oil and gas industry is acquiring tremendous amounts of data that come from disparate sources in a variety of origins, time scales, structures and quality. The underlying variable root-cause relationships are highly non-linear and non-intuitive, and simplistic linear regression methods are suboptimal. We approach the challenge by developing a data-driven workflow that integrates components of artificial intelligence, machine learning and pattern recognition to enhance quantitative understanding of complex data. The sanitized aggregated data set combines 470 horizontal wells, covering 15 numerical (e.g., stimulation interval length, production rates) and categorical (e.g., target zone, proppant type) predictors and the total produced BOE, as the response variable. The objective is to predict an optimal set of variables that maximize the production. We utilize an integrated analytics platform that enables a variety of sophisticated statistical operations on large-scale data: a) comprehensive data QA/QC for outliers, consistency and missing entries; b) Exploratory Data Analysis and visualization; c) feature selection, screening and ranking; d) building and training of multiple machine learning (ML) models for multi-variate regression (e.g. generalized linear model, deep learning, decision tree, random forest and gradient boosted machine); and e) response optimization of an identified "best-performing" ML model for highest prediction accuracy. Our study introduces the initiative to establish concepts best practices for predictive and prescriptive analytics in domains of reservoir simulation, description and asset management. Given the unique volume and information richness of operational data, acquired over decades of production history, the anticipated applications of predictive analytics could expand to drilling optimization, smart data aggregation, well stimulation and equipment maintenance.

Conventional production logging tools proved to be efficient in vertical wells. When it comes to work in horizontal laterals production logging becomes much more complex. Common challenges are layered flow of reservoir fluid, deviation, wellbore accessibility, and stagnant zones along lateral. The tracer technology features a synthesis of a combination of marker-reporters made of a few quantum dots and a mixture of the polymer-based chemical composition. Quantum dots are nanocrystals produced using the process called colloidal synthesis. A single quantum dot is compounded of few hundred atoms and as small as 2-10 nanometer in diameter. Colloidal quantum dots irradiated with a laser emit light of different colors due to quantum confinement. The emittance of a particular specter of light can be detected using flow cytometry method. Several quantum dots joined together creates a unique and traceable marker-reporters element. There could be many unique tracer signatures (over 60). Utilization of quantum dots exclude any chance of misinterpretation while identifying tracers in samples of formation fluid. To achive superior accuracy in tracer identification we use software based on "machine learning". Qualitative and quantitative analysis of quantum dot marker-reporters in samples of formation fluid allows making informed conclusions about the performance of productive intervals of a horizontal well. Application of the technology showed the following benefits: the possibility of monitoring inflows for a long time, in contrast to a one-time logging operation; a significantly lower resource intensity and cost; confidence in conditions when the traditional downhole logging operations are complicated. Quantum dot tracer technology allows solving a number of problems, such as: post-fracturing inflow profile evaluation extended in time; assessment of each production interval in regard to water and oil production; optimization of technical solutions for well completions in the early stages of field development, such as number of ports; analysis of hydrocarbons extraction ratio; detailed information in the analysis of mutual influence of neighbouring wells in the oilfield. The application of the technology is particularly effective in the early diagnosis of water breakthrough, which allows enough time to choose the right technology for water shut off operation. Ultimately, this fact reflects in declining production rates and increasing incurred costs Major benefit is an ability to monitor production per zone at any time during five (5) years after deploying tracer-containing material downhole. Implementation of the technology is time efficient and does not require field equipment as well as crew for operation, which reflects on operating costs carried by customers.

During drilling or production operations, poisonous, highly flammable hazardous gases can be released into the environment. A next-generation gas emission monitoring system monitors gas leaks and can help the oil and gas industry improve workplace safety. The initial design, architecture, and development of a real-time monitoring and surveillance system consisting of drones capable of performing autonomous aerial inspections is discussed. This system monitors and reports the spatiotemporal evolution of hazardous gas clouds, such as H 2 S, CH 4 , and CO 2 , in the oil and gas facilities in real time and provides necessary actions for a safe operation. The proposed monitoring system is compared to the traditional monitoring approach where sensors are placed near the ground. This work is a significant improvement from the authors’ previous work leveraging state-of-the-art machine learning technologies to create smart drones capable of making intelligent decisions involving gas leak monitoring.

A concept platform integrating the precise movement of a linear or azimuthal actuator, such as in instrumented wireline intervention tools (IWIT), with fast pressure measurement is presented. This device is intended to accurately move a measurement probe or sampling assembly either in the longitudinal or azimuthal direction in the wellbore to significantly improve data quality and operational efficiency. Precise movement control enables acquiring data at exact intervals to eliminate errors induced by cable stretching, overpulls, or variable cable creep. Monte Carlo simulations of this concept using current IWIT capabilities suggest significant reduction of the pressure gradient uncertainty over common wireline protocols. The operational procedure includes correlation using standard wireline gamma ray logs, anchoring of the platform at the top of the interval to be tested and performing the distributed survey using a combination of tractors and linear actuators for every probe displacement. Removing cable movement significantly reduces an important source of error in distributed pressure measurements. These acquisition errors induce interpretation uncertainties like position of contacts and connectivity between flow units. These have profound impacts in exploration and appraisal decisions and field development plans. This concept platform would enable reducing the time spent on pressure surveys if similar accuracy to current standard practices is acceptable. Because the remaining source of error is mostly due to gauge accuracy, results show that fewer stations are necessary to replicate standard wireline results. Where accuracy is important, as with distributed pressure measurements to quantify reserves using gradient intersection to define fluid contacts or determine compositional gradients, the proposed approach is shown to significantly reduce gradient error using the same number of stations. We use synthetic data sets built from previous work to show the impact of the error reduction in the position of the fluid contact. IWITs currently used in cased hole employ active anchoring to perform intervention tasks. The controlled downhole force available for these operations goes up to 80,000 lbf while the anchoring force could be up to 150,000 lbf. In the proposed concept platform, this pulling force could be instrumental where there is high risk of differential sticking. By anchoring the upper part of the platform in overlying impermeable intervals, the probe could be lowered into the permeable interval to conduct the pressure survey without exposing the full length of the platform to the pressure differential forces for significant risk mitigation. The high pulling capacity of the anchoring module can be used to apply up/down force on the probe in case of differential sticking without applying high tensions to the wireline cable. The proposed architecture for the concept platform innovatively combines several operational concepts used today as separate entities in wireline operations. Their integration, however, generates important efficiency gains, reduces the risk in stationary measurements and operations, improves accuracy, and enables the implementation of unprecedent distributed pressure measurements with azimuthal rotational capabilities using wireline. Azimuthal movements can be used to align the measurement probe away from breakouts, drilling induced fractures, debris or geological features like vugs or fractures that may compromise the sealing ability of the probe.

Nanomaterials have drawn considerable attention of the oil and gas industry due to their peculiar properties and interesting behaviors. Many experiments, trials and practices were conducted by petroleum scientists and engineers in the last two decades to use various novel nanomaterials to improve exploration and production. Based on the published literature, this article comprehensively reviews the strategies and experience of nanomaterial application in frac fluids, the current problems, and relevant challenges. Based on elaborated design, the nanomaterials such as nano-sized metal, metal oxide, silica, carbonate, carbon, polymer, fiber, organic-inorganic hybrid and other composites can be incorporated in frac fluids to greatly enhance or precisely tune the properties and performances. Consequently, nanomaterial-assisted frac fluids perform well in different aspects including density, rheology, stability, heat conductivity, specific heat capacity, fluid loss, breaking, clean up, proppant suspendability and frictional drag. To optimize the performance and cost-effectiveness of nano-frac fluids, advanced principles and theories in physical chemistry, heat and mass transfer, mechanics and rheology along with industrial design philosophy have been considered and applied. According to the investigation of the literature, nanomaterials have successfully fulfilled the following functions in frac fluids: (1) Improving the rheological behavior by intermolecular interactions (e.g., pseudo-crosslinking in frac fluids, or changing the aggregation pattern of surface-active molecules in surfactant based fluids); (2) Increasing the stability of fluids by enhancing the interfacial strength and toughness, especially in foams and emulsions; (3) Forming a low-permeability pseudo-filter cake to lower the fluid loss; (4) Increasing the viscosifying effect of polymers, which dramatically decreases the required loading of polymer in the fluid; (5) Boosting the thermal stability of frac fluids; (6) Improving the regained fracture conductivity; (7) Reducing the frictional drag of frac fluids; (8) Helping self-suspended proppants achieve better performance and (9) Reducing the required displacing pressure for the residual frac fluid by decreasing interfacial tension to help clean up. These achievements, along with the related design ideas, are reviewed. This paper also discusses the major difficulties and challenges for nano-frac fluids including compatibility, cost and HSE issues. Comprehensive laboratory work should be performed before field application to ensure the reliability of nano-assisted fluid formulations. Large-scale industrial production and a steady supply of nanomaterials will promote the application of nano-frac fluids. Exposure risk, eco-toxicity and biodegradability of nanomateials should be paid more attention. Incorporating the attractive, cutting-edged achievements in chemical and material sciences, nano-frac fluid is predicted to be fully accepted by the petroleum industry due to its great potential and the increasingly declining price of nanomaterials.

Surfactants have been used in the oil industry for decades as multi-functions additive in stimulation fluids. In hydraulic fracturing, surfactants and microemulsions have been extensively reported numerously as flowback additives to lower surface and interfacial tension to aid water recovery. Fracturing fluids invade the matrix during the fracturing, and if not recovered, leads to water blockage and a reduction to relative permeability to gas or oil. This problem is more challenging in low- permeability formations since capillary forces have more profound impact on water retention, and hence water recovery and subsequent oil productivity. In this work, surface tension, interfacial tension, foam stability, sand-packed columns, and coreflood experiments were performed on a selected environmentally friendly water-based surfactant formulation. The performance of the surfactant of interest was compared to two commercial microemulsion and one non-ionic alcohol ethoxylated. The results confirmed the benefit of using surfactants for flowback compared to non-surfactant case. Surface tension (ST) alone cannot be used as a selecting criterion for flow back. The alcohol exthoxylated, while reducing the ST to same level as the two microemulsions, showed very poor performance in packed column and coreflood tests. Although interfacial tension (IFT) seems to be more reasonable criteria, adsorption and emulsion tendency are other challenges that can hinder the performance of good surfactants with low IFT. Based on the data, a surfactant that lowers the IFT with the selected oil to below 1 mN/m is more likely to outperform other surfactants with higher IFT.

The development of deep oil and gas reservoirs requires high temperature stable drilling fluid systems. The properties of conventional polymers in water-based systems decline above 300°F which led to the development of the new high temperature water-based system. The high temperature water-based system, featuring a newly developed synthetic polymer, has been developed to provide enhanced rheological profiles and fluid loss control, along with long-term stability under elevated temperature and pressure conditions. The system has been designed to minimize formation damage by forming a thin and ultra-low permeable filter cake. The versatility of the developed polymer allows the new system to be formulated at a wide range of densities using most conventional oilfield brines including monovalent and divalent halide and formate brines. The clay-free high temperature drilling fluid has stable rheological properties, no gelation and low sag tendencies which are ideal for high temperature logging applications. Also, the highly branched nature of the polymer provides a rheological profile suitable for coil tubing applications. A new breaker package was developed along with the high temperature water-based system to slowly and uniformly clean-up its deposited filter cake, reducing near wellbore damage and maximizing production when the system is used to drill open-hole completion wells. This paper summarizes the fluid design in the lab and recent field applications, where the new high temperature polymer-based system was successfully deployed in different locations around the world.

Drilling, as a direct and effective method of opening oil and gas layers, has been widely used. A reasonable combination of drilling tools plays a key role in increasing the rate of mechanical drilling, reducing drilling costs, and reducing downhole accidents. Conventional drilling relies on years of experience of on-site workers and reference to the operation of drilling wells, making use of drilling tools and lacking scientific basis. However, the reservoir situation is erratic, the unknown factors are very numerous, unpredictable, and the difficulty of drilling is increased. Drilling into unknown reservoirs, especially high-temperature and high-temperature risk wells, poses a huge threat to the lives of workers on site. Conventional drilling of known reservoirs will also encounter unknown problems such as drilling distance growth, stuck drilling, drilling tools falling, increased inclination, and deviation from the intended target position, which seriously reduces drilling efficiency, increases operating time, risk and drilling difficulty affected by the reasonable use of the drilling tool combination. With the development and application of computational intelligence, through the accumulation of massive geological property data, reservoir structure data, drilling tool parameters, construction data, drilling fluid parameters and other drilling data, intelligent drilling is used to predict unknown drilling information which can reduce the risk of drilling and improve drilling efficiency. In this paper, the work mode of "data running first, operation post" is used to further strengthen the application of drilling tools combination to improve the rate of mechanical drilling and reduce downhole problems.

Enzyme Enhanced Oil Recovery (EEOR) has recently been categorized as one of the most effective EOR mechanisms. Laboratory and field studies have reported up to 16% of incremental oil recovery rates. EEOR recovers oil mainly by two main mechanisms: lowering the interfacial tension between brine and oil and altering the wettability on rock grains to a more water-wet condition. Therefore, EEOR would promote mobilization of capillary-trapped oil after regular waterflooding. Since capillary-trapped oil resides at the micro-scale, it is essential to assess EEOR fluid-fluid interaction at that scale. To further investigate the ways in which these enzymes contribute to EOR, an experimental micro-scale approach was developed in which EEOR was analyzed using polydimethylsiloxane (PDMS) microfluidic devices. The PDMS microfluidics device was based on X-ray micro-CT images of a Bentheimer sandstone with resolution of 4.95 μm. We first compared the IFT reduction capabilities of one class of enzyme (Apollo GreenZyme ®) and a commercial surfactant (J13131) obtained from Shell Chemicals. For GreenZyme concentrations of 0.5, 1.5 and 2 wt%, the IFT values between GreenZyme solution and oil are 4.2, 0.7 and 0.6 mN/m, respectively. Whereas the IFT values for 0.5 wt% surfactant solutions and deionized water are 1.1 and 32 mN/m, respectively. We then compared the oil recovery of the two systems using the aforementioned sandstone PDMS microfluidics device. Recovery values up to 92% of oilwere obtained using GreenZyme. Surfactant and waterflooding on the same PDMS chips had recovery values of 86 and 80%, respectively. This study provides insights and direct visualization of the micro-scale oil recovery mechanisms of EEOR that can be used for design of effective EEOR flooding.

Petrophysics is a pivotal discipline that bridges engineering and geosciences for reservoir characterization and development. New sensor technologies have enabled real-time streaming of large-volume, multi-scale, and high-dimensional petrophysical data into our databases. Petrophysical data types are extremely diverse, and include numeric curves, arrays, waveforms, images, maps, 3-D volumes, and texts. All data can be indexed with depth (continuous or discrete) or time. Petrophysical data exhibits all the "7V" characteristics of big data, i.e., volume, velocity, variety, variability, veracity, visualization, and value. This paper will give an overview of both theories and applications of machine learning methods as applicable to petrophysical big data analysis. Recent publications indicate that petrophysical data-driven analytics (PDDA) has been emerging as an active sub-discipline of petrophysics. Field examples from the petrophysics literature will be used to illustrate the advantages of machine learning in the following technical areas: (1) Geological facies classification or petrophysical rock typing; (2) Seismic rock properties or rock physics modeling; (3) Petrophysical/geochemical/geomechanical properties prediction; (3) Fast physical modeling of logging tools; (4) Well and reservoir surveillance; (6) Automated data quality control; (7) Pseudo data generation; and (8) Logging or coring operation guidance. The paper will also review the major challenges that need to be overcome before the potentially game-changing value of machine learning for petrophysics discipline can be realized. First, a robust theoretical foundation to support the application of machine leaning to petrophysical interpretation should be established; second, the utility of existing machine learning algorithms must be evaluated and tested in different petrophysical tasks with different data scenarios; third, procedures to control the quality of data used in machine leaning algorithms need to be implemented and the associated uncertainties need to be appropriately addressed. The paper will outlook the future opportunities of enabling advanced data analytics to solve challenging oilfield problems in the era of the 4 th industrial revolution (IR4.0).

Cationic surfactant is never used in Enhanced Oil Recovery (EOR) for negative charged sandstone reservoirs because of high adsorption. Since January 2012, the first field scale application of alkaline surfactant polymer (ASP) flood in the world with thermal stable, highly efficient mixtures of anionic- cationic surfactants (S) for super low acid oils, was carried out in Sinopec for a high water cut mature sandstone reservoir with approximately 8,000 mg/L total dissolved solids (TDS), temperature of 81°C, to demonstrate the potential of this novel surfactants to recover residual oil from as high as 53.3% recovery percent of reserves. The maximal water cut decreased from 97.9% to 90.2%, along with peak daily oil production increased from 23.0 t to 106.1 t. The cumulative incremental oil by ASP flood at the end of December 2018 is about 276.1 kt and the oil recovery was increased by 10.65% OOIP. The estimated ultimate oil recovery can be increased by 14.2% OOIP and yield up to 67.5% OOIP.

Study made from the results observed over a particular application objective with one of the recently developed proppant fracturing techniques known as Channel Fracturing. This technique was used in this application to place a proppant fracturing treatment in a tight gas reservoir which pushes the installed well completion to reach its mechanical limit capabilities. Channel (or pillar) fracturing was applied in multiple cases with the intention to constrain the pressure increase commonly observed during a fracture job execution.

This work is an ongoing effort to design a numerical platform based on machine learning algorithms to characterize, predict, optimize and guide the interaction of [high power] electromagnetic (HPEM) sources (laser, microwave, RF, etc.) with subsurface matter (e.g. rocks, oils, brines, etc.). Advanced statistical analysis routines are essential to identify key variables and relations in the thermal- mechanical-electromagnetic coupling in heterogeneous and anisotropic materials. Advanced statistical analysis and machine learning have been recently used to evince relations in complex environments and physical dynamics; e.g. fluid dynamics, P&ID analytics, and drill cuttings classification, to cite a few. The methods make use of sophisticated algorithms to classify and model problems in multiple areas, from image processing to certain optimization problems. In the realm of subsurface photonics, and in particular for high power electromagnetic (HPEM) interaction with subsurface matter, these routines could become essential to identify key variables, assess the environment and process, and evince models to predict the outcome of an inherently multiphysics and multi-dimensional problem. Numerical models that capture the interaction between HPEM sources and subsurface matter are essential to predict, optimize, adapt, and evaluate the process prior to, and during, deployment in subsurface. These models can come as the solution to a set of coupled partial differential equations that fully describe the physical dynamics, or as the result of supervised-learning algorithms and analysis of experimental and field data. The former is highly sensitive to dynamic material properties, environmental conditions, and source parameters. In addition, it can be challenging to characterize the properties of subsurface materials over the wide range of temperatures and pressures observed in the process. Thus, a machine learning method could provide an ever-improving alternative that learns from the available data to build a numerical platform that can predict, optimize, and guide the process. Machine learning and advanced statistics provide a compelling alternative to build numerical tools to predict, optimize, and control physical processes. This work introduces a variety of numerical approaches to identify essential variables, predict their impact, and optimize the outcome for subsurface applications. Combined, the methods described in this work can help guide the control of the governing dynamics and parameters for use in multiple applications. This numerical platform can be extended to other applications, enhance experimental prototypes, and advance the design of a comprehensive numerical tool for downhole HPEM operations.

The objective of this work is to establish a communication between the tight hydrocarbon-bearing formation and the wellbore by using high power laser technology. This paper presents different methods of utilizing the energy of the laser to enhance and improve the flow in unconventional reservoirs including tight formation, the successful results are used for field deployment strategy. High power laser is an innovative alternative to several currently used downhole stimulation methods and technologies. The system consists of the laser source which is mounted on the surface on a coiled tubing unit, fiber optics cable to transmit the energy and the downhole tool. The advantages of utilizing high power laser technology for downhole applications are the ability to control and orient the laser energy precisely. Laser energy generates heat when in contact with the rock samples, the heat impacts the rock samples by dehydrating, collapsing and dissociating some minerals near the wellbore, as well as creating micro- and macro fractures in the formation. In addition, heat removes the blockage around the wellbore and the effect extends deeper into the tight formation for production. Continues efforts over the past two decades have been proven that high power lasers provide controllable heat source while penetrating the formation, this mechanism enhances flow properties especially in tight formation. Low permeability in these formations restricts the flow and reduces production. Shale, Sandstones (including tight sandstones) and carbonate rocks have been treated with high power laser. Pre and post-treatment measurements are conducted for comparisons; the results from all rock types show improvement in permeability and flow. The results of advanced core characterizations, imaging and visualization are presented. The success of the lab experiments leads to the development of field deployment strategy to use high power laser for in-situ treatment in unconventional wells. Utilizing state-of-the-art high power lasers technology in downhole provides innovative and safe stimulation methods. Reliability, accuracy, and precision in controlling the power, orientation and the shape of the beam are some of the properties of the technology that made it attractive for downhole applications. Different tools have been developed for different applications that can fit any slim holes.

The objective of the paper is to share the experience and result of deployment of Virtual Workstation in Malaysia Oil and Gas Company replacing the more expensive high-end workstation. This is a part of company's digital transformation program towards the 4th Industrial Revolution. VWS is a modern technology that accelerates and improves subsurface and petroleum engineering application and function. It replaces outdated high-end workstation set-up. In high-end workstation set-up, subsurface technical software was installed at user workstations. Master Data on the other hand, located at centralized data center, BDC; but in order for the user to retrieve the data, it has to go through regional data center at KPC first. All these processes happened through existing small 1 GB cable networks capacity. Separate software and data location, multiple location points for data retrieval and weaker cable network capacity lead to less efficient software performance and data insecurity. But in VWS set-up, issues of under-performed software and data security are eliminated. Now both software and data are installed and located at BDC. Then the user will access their software and data virtually via company's intranet at with the strength of 10 GB cable network capacity that VWS has. VWS deployment resulting in: i) Performance and productivity: increased efficiency for technical applications and optimization of technical resources. ii) Cost: optimization of cost on IT infrastructure. iii) HSE: Reduced IT footprint and energy consumption. iv) Data security: increased data security. v) Flexibility: improved collaboration for technical users. vi) Standardization: standardized desktop environment for enhanced support. VWS deployment only need the VWS system and standard normal workstation to function as good as the more expensive high-end workstation. With VWS, standard workstation is enough to process and run petroleum engineering software and data, since the workstation only act as a visualizer of their actual software and data that located in BDC. With deployment of standard workstation instead of high-end workstation, VWS expected to contribute to cost saving of RM 86k per user for 3 years of leasing.

Oil/gas exploration, drilling, production, and reservoir management are challenging these days since most oil and gas conventional sources are already discovered and have been producing for many years. That is why petroleum engineers are trying to use advanced tools such as artificial neural networks (ANNs) to help to make the decision to reduce non-productive time and cost. A good number of papers about the applications of ANNs in the petroleum literature were reviewed and summarized in tables. The applications were classified into four groups; applications of ANNs in explorations, drilling, production, and reservoir engineering. A good number of applications in the literature of petroleum engineering were tabulated. Also, a formalized methodology to apply the ANNs for any petroleum application was presented and accomplished by a flowchart that can serve as a practical reference to apply the ANNs for any petroleum application. The method was broken down into steps that can be followed easily. The availability of huge data sets in the petroleum industry gives the opportunity to use these data to make better decisions and predict future outcomes. This paper will provide a review of applications of ANNs in petroleum engineering as well as a clear methodology on how to apply the ANNs for any petroleum application.

As the oil and gas industry undergoes a digital transformation, the massive volume and variety of information being ingested at increasing velocity necessitates new methods of data interaction for decision making. Additionally, effective management of safety risks and flawless operational execution in an evolving oil and gas industry requires innovative applications of digital technology. By superimposing contextually-relevant digital information on the physical world, augmented and mixed reality (AR/MR) technologies have tremendous potential to meet these challenges by providing a more intuitive way to interact with data, train personnel, and ensure process safety. However, a major challenge with AR and MR technologies is the limited processing power and capability of available hardware. A cloud-based software platform has been developed to overcome computational limitations of AR and MR devices, enabling interaction with significantly more complex 3D content. Additionally, this enhanced AR/MR software platform enables real-time connectivity across different hardware architectures – such as smartphones and Microsoft HoloLens devices – creating powerful new capability for remote collaboration. This unique software platform transforms consumer-grade AR and MR devices into powerful industrial tools useful for a variety of oil and gas applications. This study will illustrate the functionality enhancements provided by this software platform and how it greatly increases the application potential of AR and MR, including a case study on adoption of this enhanced AR/MR technology for process safety using threat response drill (TRD) scenarios. Enhanced AR and MR provides full-scale virtual TRD scenarios that enable practical demonstration of operational readiness and proactive risk management. Crew response capability and human performance can be collaboratively evaluated with gamified AR/MR techniques, allowing for multiple outcomes based on user inputs through multiple interaction modalities, enabled by the underlying software platform. Enhanced AR/MR enabled by this software platform can drive major improvements in process safety and ultimately help reduce CAPEX, increase efficiency, and mitigate risk across the oil and gas industry.

Smart field technologies offer outstanding capabilities that increase the efficiency of the oil and gas fields by means of saving time and energy as far as the technologies employed and workforce concerned given that the technology applied is economic for the field of concern. Despite significant acceptance of smart field concept in the industry, there is still ambiguity not only on the incremental benefits but also the criteria and conditions of applicability technical and economic-wise. This study outlines the past, present and the dynamics of the smart oilfield concept, the techniques and methods it bears and employs, technical challenges in the application while addressing the concerns of the oil and gas industry professionals on the use of such technologies in a comprehensive way. History of smart/intelligent oilfield development, types of technologies used currently in it and those imbibed from other industries are comprehensively reviewed in this paper. In addition, this review takes into account the robustness, applicability and incremental benefits these technologie bring to different types of oilfields under current economic conditions. Real field applications are illustrated with applications in different parts of the world with challenges, advantages and drawbacks discussed and summarized that lead to conclusions on the criteria of application of smart field technologies in an individual field. Intelligent or Smart field concept has proven itself as a promising area and found vast amount of application in oil and gas fields throughout the world. The key in smart oilfield applications is the suitability of an individual case for such technology in terms of technical and economic aspects. This study outlines the key criteria in the success of smart oilfield applications in a given field that will serve for the future decisions as a comprehensive and collective review of all the aspects of the employed techniques and their usability in specific cases. Even though there are publications on certain examples of smart oilfield technologies, a comprehensive review that not only outlines all the key elements in one study but also deducts lessons from the real field applications that will shed light on the utilization of the methods in the future applications has been missing, this study will fill this gap.

Innovation in the analysis of oil well surface measurements has led to the discovery of an instantaneous and straightforward emulsion detection calculation. When applied in the Bahrain Field, this led to the treatment of emulsion in over 100 wells, resulting in a cumulative production gain of over 500,000 barrels to date at negligible cost. Artificial Intelligence (AI) was then employed to identify and understand factors related to emulsion and optimisation treatment programs. Once the wells were treated and the method was confirmed to prove emulsion existence, a focused approach was carried out to understand it further. Wells were categorised based on their production response to standard demulsifier bullheading. In addition to a variety of well parameters, this data was used to build a machine learning model that helped identify patterns with regards to problematic zones, properties of wells with emulsion, and the best treatment method for each well. The results of the study were rather substantial and resulted in numerous new insights. Firstly, a model was built to predict the sustainability and economics of expected bullheading job treatments. This is currently being used to rank the priority of wells for either bullheading treatment or continuous chemical injection. Once the wells were classified into basic sub groups and sorted by zones, geographic analysis was carried out to identify wells with emulsion being formed as a result of waterflooding. This led to further insight into the nature of emulsion blocks, where in some cases, although it was found that these blocks exist downhole, traces of emulsion will flow to the surface and can have a unique signature. This paper discusses in further detail insights into emulsion and the different types of AI algorithms used to answer questions raised as a result of the discovery. The necessity of using machine learning cannot be overstated enough and the observations made in the paper could not have been found if it were purely by observed by the naked eye. The topic of emulsion is highly understudied, and the concept of using the emulsion detection calculation was not published before. In addition to highlighting this discovery, this paper can influence other operators to test their findings and have a real world application of machine learning in their fields.

This paper discusses an optimum approach to design and execution of a robust chemical enhanced oil recovery (EOR) surveillance program considering the physics and uncertainties involved during the implementation of a chemical EOR (CEOR) application at reservoir scale. The surveillance includes techniques, measuring points, and frequency of data acquisition. Based on field experience, a robust surveillance plan plays a key role in ensuring high performance of a CEOR application during implementation and execution at reservoir conditions. A proper surveillance program should focus on acquiring information associated with the main uncertainties related to fluid-fluid and rock-fluid interactions, the impact of reservoir heterogeneities at reservoir scale, fluid dynamics, and the composition and stability of the chemical formulation. The acquired information should be given to the CEOR modeling team to follow up, interpret, and adjust the CEOR process and reservoir model. Also, the information should be given to the reservoir operation team to tune up the CEOR injection and production process to help optimize performance. Typically, specialized literature focuses on describing CEOR formulation design and evaluation; laboratory requirements, experimental settings, and analysis results; field application design and implementation; and overall results of field applications. This work emphasizes CEOR process surveillance, its importance, and impact with respect to oilfield scale applications. There are multiple uncertainties regarding the physical parameters and phenomena that control the performance of the CEOR at reservoir scale (e.g., are uncertainties associated with fluid saturation and properties, rock-fluid interactions, reservoir heterogeneities, and alkali-surfactant-polymer (ASP) formulation behavior at reservoir conditions). A proper surveillance design and implementation help mitigate the impact of the mentioned uncertainties. Therefore, surveillance is paramount for the success of a CEOR application. The design and execution of a robust surveillance program should consider the main uncertainties associated with the CEOR formulation operating window, fluid-fluid and rock-fluid interactions, reservoir heterogeneities, reservoir conditions, injection-production environment, and various time scales for the timely use of the acquired information and the interpretation feedback to the CEOR modeling and operation teams. This work discusses the physics and uncertainties considered during the design and execution of an optimized surveillance program. A systematic approach is provided considering fluid-fluid and rock-fluid interactions, reservoir heterogeneities, CEOR formulation operating window, injection – production environment, and time scales to feedback the acquired and interpreted information during the surveillance program execution.