A practical data science, machine learning, or artificial intelligence project benefits from various organizational and managerial prerequisites. The effective collaboration between various data scientists and domain experts is perhaps the most important, which is discussed here. Based on practical experience, the principal theses put forward here are that (1) data science projects require domain expertise, (2) domain expertise and data science expertise generally cannot be provided by the same individual, (3) effective communication between the various experts is essential for which everyone requires some limited understanding of the others’ expertise and real-world experience, and (4) management must acknowledge these aspects by reserving sufficient project time and budget for communication and change management.

This paper describes the procedures and steps implemented in the introduction and the instigation of a Drilling Performance Analysis Workflow. The task of drilling performance or offset analysis is paramount to the understanding and enactment of a successful drilling campaign, conversely in order to gain exceptional knowledge and profound understanding of problems root cause and the interdependency of the individual relationships a more comprehensive methodology has to be employed. An Operator experienced several BHA failures in multiple and sequential runs that generated significant non productive time NPT within the multimillion dollar operation. Traditionally, the root cause analysis of a problem follows a certain path involving confirmation by the equipment manufacturing centre that the tools were prepared to specifications, while in parallel the drilling engineers scrutinize the environment where the tools were used and attempt to identify the culprit(s). The conclusion may combine the two findings, nonetheless our observation was that this is not generally the dominant outcome. Hence, we embarked on developing a unique multifaceted workflow to tackle these inadequacies utilizing several 3-D and 4-D simulation and analysis tools. Individual workflows were established focusing on understanding the interrelated events and using 3D/ 4D modeling tools to relate events in the context of the environment and the interdependency of the BHA behavior and the milieu including exacerbating weather conditions. The software technology integrates data from various databases and organizes it in ways that aid visualization. Any particular areas of interest can be further examined thoroughly looking simultaneously at the geological references, telectric logging data, drilling parameters, and weather conditions all at a glance. The unique arrangement allows offset data from previous wells to be examined concurrently while the subject well is being drilled to assess the timeline of the issue or the recurring possibilities. Utilizing the software to gather the information and assemble it in a manner that allow the engineers to spend more time analyzing the outcome rather than gathering and arranging data is a significant achievement on its own. The benefits extend to create a system of ownership with accountability for all involved personnel at the base who prepare the tools, at the office who plan and follow up the daily operations, and those who execute the plans at the wellsite. The approch was proven to add significant value, with the next two well section drilled without any issues avoiding and improving the operator's time versus the planned authority for expenditure (AFE).

One of the critical operations during the exploration phase is well testing required determining fluid type, flow rate, and the sustainability of the production. With the right planning, technology and implementation, well testing can ensure reservoir quality and production such as, permeability, initial reservoir pressure, hydraulic fracture parameters, near wellbore formation damage, geometry of the reservoir, and reserve quantities. Exploration Well Testing Operations require a complex integration of various services including surface well testing, artificial lift via coiled tubing, downhole data transmission and on-site operational activities. The increase in exploration activities involves various service companies’ proprietary data acquisition systems that introduce a challenge for decision makers due to segmented data and information. This calls for establishing an integrated unified viewer combining the operational data for engineers to enable real-time data supervision, technical support and decision making from the headquarters to well-site locations reducing operational risks and optimize required cost. This paper highlights the progress of the real time data transmission interface to support highly active exploration well testing operations in Saudi Aramco.

There is more to Intelligent Energy than information and communications technology. Getting full value from digitization in oil production requires rethinking how groups get work done, and providing the organizational capabilities to support that change. A study of six major oil and gas companies that have all been implementing Intelligent Energy for more than five years was carried out. In this study we find that in order to implement changes at the asset level, we need to focus not just on providing an information and communications technology backbone, but more importantly, on documenting and clarifying business and group interaction rules, roles & accountabilities, and on providing ongoing coaching and feedback to all participants. We also find that implementing effective group operational decision making across a global firm requires active involvement of local groups as well as global support, in the form of specific global organizational units that sustain and scale new ways of working. These global units are not implementing change top-down; rather they are working center-out. They coordinate efforts around continuous improvement and integration of effective practices, adoption through business pull, global governance by top operational leaders, and multiple forms of ongoing coaching. This paper will summarize the results from the study and make recommendations for the effective implementation of Intelligent Energy.

This paper discusses the implementation of an intelligent operating system for oilfield processing. It examines the infrastructure of this intelligent software system, from the database backend to the graphical user interface (GUI) frontend. Oilfield processing generally includes the measurement and analysis of reservoirs, controlling oil or gas production flow through the wellbore, risers and manifolds operation, and wellhead operations, then proceeds to the flare point or transportation out from the production facilities. This paper describes how the system can be applied to upper stream oil and gas production management and forecasting. An intelligent solution was used for the research described in this paper. Several sample workflows were implemented for the proof of concepts. The study results indicate that the selected system met all requirements and prove that an integrated and completed system can reduce both human error and operating costs. The system also includes sufficient flexibility to apply to other industrial applications, such as assembly and manufacturing processes.

The dependency on well-head and field real time data has significantly increased in the past few years in the oil and gas industry. The data is used to maximize oil and gas recovery, increase revenue and improve health and safety. This new mode of operation mandates the availability of reliable real time information sent by the different well and field digital equipment for optimum right-time decision making. The challenge is in the fact that intelligent field components include many different layers and nodes that increase the complexity of such assurance. Therefore, the health and the data transmitted from these components, such as digital gauges (e.g., multi-phase flow meters and permanent downhole monitoring systems) and the communication network must be continuously monitored and well maintained. This paper will highlight a newly developed comprehensive and interactive monitoring and key performance indices reporting solution to quantify, assess and visualize the health of the different intelligent field components. The new system is using advance technologies, such as GIS maps to locate fields, equipment, real-time data historian servers, and networks to highlight their availability and reliability status. This solution provides real time alerting and alarming in case of transmission failure, well data integrity situation or inaccurate data detected using an automated diagnostic engine, thereby maximizing safety and increasing accuracy and data reliability.

This paper presents an approach to monitor, support and optimize reservoir performance in real time using an Intelligent Field. The approach is demonstrated with a case study based on the experience of implementing Intelligent Field solutions in one of Saudi Aramco's onshore fields. The field is equipped with surface and subsurface instrumentation to capture and deliver real time data. The case study highlights the critical process of utilizing Intelligent Field data to monitor compliance between actual well production/injection rates and the reservoir management guidelines. The case study shows a giant field with under-saturated, heterogeneous and peripheral water-flooded reservoirs. A fundamental part of reservoir management best practices is to balance the pressure distribution within the reservoir and to ensure uniform flood front movement in the field through maintaining a calculated voidage replacement ratio (VRR). Due to the heterogenous nature of the reservoirs, the voidage replacement level is different from one area to another, which adds complexity in designing and monitoring the optimal injection-production ratios and guidelines. Frequent violations of these guidelines could lead to unwanted consequences, such as early water breakthrough and undesired reservoir pressure. The demonstrated workflow starts by assigning monthly wells production/injection guidelines based on the field target rate, well status and reservoir/well performance. Then, the workflow captures the real time flowing wellhead pressure and temperature to convert them through IPR/VLP models to rates. Then the calculated rate per well is compared to the assigned target rate per the production/injection guidelines. Responsible engineers receive compliance reports twice a day to take remedial action as needed. Implementing this workflow helped both reservoir and production engineers to monitor changes in well performance and ensure the compliance to the target rates in real time.

Although oilfield workflow automation processes have been implemented in the oil and gas industry during the last decade, the full impact and value of these technologies has yet to be realized. Tremendous potential still exists to implement new technology to maximize production, increase operational efficiency, and reduce down time/non-productive time. The Kuwait Integrated Digital Field project (KwIDF) is a novel intelligent digital oilfield operation for Kuwait Oil Company, the operator of the Sabriyah field in North Kuwait. The project has successfully implemented improvements in field's operational efficiency by reducing the down time in artificial lift completion, increasing well productivity, and preventing water production. This paper provides an overview of the project from the perspective of field data acquisition, data analysis, model analysis, diagnostics, and operational optimization conducted in "right time" in the operator’s state-of-the-art collaboration center. The automated workflow system orchestrates integrated solutions that not only provide monitoring in real time, but also enable diagnostics and optimization for individual wells. The automated workflow integration and orchestration conducted by the production team within a collaborative work environment covers the following aspects described in this paper: production surveillance (including alarming and alert events), well performance, production losses, artificial lift optimization, and key performance monitoring.

Intelligent digital oilfield (iDOF) operations include the transfer, monitoring, visualization, analysis, and interpretation of real-time data. Enabling this process requires a significant investment to upgrade surface, subsurface, and well instrumentation and also the installation of a sophisticated infrastructure for data transmission and visualization. Once upgraded, the system then has the capability to transfer massive quantities of data, converting it into real information at the right time. The transformation of raw data into information is achieved through intelligent, automated work processes, which are referred to here as "smart flows," which assist engineers in their daily well surveillance activities, helping make them more productive and improve decision making. A major oil and gas operator in the Middle East has invested in such an infrastructure and is developing a set of smart flows for key activities and work flows for its production operations, with the ultimate goal of improved asset performance. The project includes a smart flow to monitor, diagnose, and optimize wells that include electric submersible pumps (ESP); 50% of the wells in this field use ESPs. The ESP smart flow includes leading-edge technologies, such as: variable speed drive controller, subsurface equipment and sensors, advanced diagnostics based on artificial-intelligence agents, analysis of sensors signals, and automatically identifying ESP optimum operating conditions. Using a steady-state nodal-analysis model combined with an artificial intelligent technique, the ESP smart flow is designed to provide rapid diagnostics and optimization in real time, generating actions, such as decreasing and increasing the pump frequency and choke setting. The ultimate benefit is to detect the signals that foresee unexpected well downtime and predict ESP system pump failures. The paper describes the main functionalities of the ESP smart flow as a powerful optimization tool that is capable of providing an interactive monitoring system that can assist operations personnel in managing ESP-operated wells.

Surveillance and optimization of waterfloods in low-permeability carbonate reservoirs pose many challenges. Updating reservoir models is tedious and time-consuming, involving multiple data sources, model updates, and simulations. Technological challenges include large simulation models, waterflood complexities, and limited real-time data. Human challenges must be addressed as well, since waterflooding decisions affect multiple disciplines: reservoir engineers, production engineers, facilities engineers, IT, Operations, and asset managers. The ‘languages’ and interests of these disciplines are quite different; necessitating a workflow that satisfies the needs of all disciplines and integrates people, processes, and technology. This paper presents an innovative automated workflow to enable monitoring, diagnostics, forecasting, and optimization of waterflooding processes in days instead of weeks. This workflow seamlessly captures historical and monthly real-time data, updates simulation history, creates simulation restart prediction points, runs numerical simulations with optimization scenarios, selects the global optimum solution by scenario, and compares results so that multi-disciplinary teams can make reactive or proactive decisions to maximize short-term oil rates and long-term oil recovery, while honoring constraints on voidage replacement ratios, reservoir pressure, sweep efficiencies, production, and injection. The workflow automatically updates real-time production data in the simulator each month. A base case is run to recalculate waterflooding indicators. The process then starts a 24-month production forecast, running hundreds of scenarios under constrained optimization to achieve global optimization points. The optimizer changes control variables such as injection volumes, tubing head pressure, bottomhole pressure, and production allowable. The workflow ranks potential well decisions with important impacts on oil rate and water cut. The workflow uses an intuitive user interface incorporating the needs of multiple engineering and operations disciplines, and facilitates one common language while evaluating and optimizing waterfloods. This workflow has been implemented for a waterflood in a Middle East carbonate reservoir to help engineers evaluate the waterflood and make better, faster decisions.

Drilling and Workover activities generate a lot of information that can be further used to improve the optimization of future activities and reduce: costs, drilling time and the time drilling engineers require to prepare a drilling program. To address this concern, Saudi Aramco developed the Well Planning Engineering Integrated Tools (WellPlanET). The well planning process is the most critical activity during drilling and completion. It starts by capturing the requirements from Exploration & Reservoir Engineering, and ends with a drilling program outlining the drilling execution plan. Supplements and revisions of the original plan may occur during the execution. This planning process involves consideration of many data types, including: formation pressures, offset well data, reservoir location, time, cost, etc. Overlooking any single data aspect could lead to severe drilling problems and time losses, especially for an Oil & Gas Operator like Saudi Aramco, where the Drilling & Workover agenda includes a large number of wells, of different types, and the operational involvement of many stakeholders. For that reason, Saudi Aramco has recently commissioned a new Well Planning Engineering Integrated Tools (WellPlanET) environment as a one box solution for drilling engineers to facilitate, plan, manage and streamline the well design in a simple, yet smart way. This involves a new re-engineering D&WO Planning Systems environment and workflows from desktop- based to a more integrated web-based environment that employs Aramco data repositories (structured, unstructured, file systems, etc.), application portfolio (in-house, vendor, real-time, historical, Drilling, Exploration, PE, etc.) and workflows to deliver users requirements and address the Drilling & Workover strategic goals and plans. It also provides a systematic way of generating, validating, simulating and optimizing the Drilling Program during both pre-drilling, execution and post-drilling phases. WellPlanET is a comprehensive integrated knowledgebase that ultimately facilitates well planning engineering, and advanced well design optimization. The system automates capturing all Drilling Program planning data (over 14 different data types such as Trajectory, Mud designs, Wellhead designs, etc.) in a structured manner to establish a complete integrated well planning repository to enable many advanced engineering modules such as Prediction, Simulation and Artificial Intelligence analysis features, using historical and planning data with full integration with key industry standards systems such as Geo- Pressure & Geomechanics analysis tools, Drilling Fluids and Well Hydraulics optimization tools, BHA/Wellhead/CrossSection designing tools to optimize the overall drilling program. This paper shares Saudi Aramco’s experience in building and deploying WellPlanET as a smart and efficient way of generating the drilling well program.

In recent years, oilfield companies have realized the value of real-time data and have set up real-time centers to monitor multiple wells in a given area remotely. With the advancement of rig communications, several wells can be streamed to these real-time centers where they are monitored by real-time engineers. In addition to the data streamed from both surface and downhole sensors to real-time centers, operational information is communicated electronically via emails, daily reports, and meetings; this information must be manually entered or interpreted by real-time engineers. We have observed that this takes precious time away from the real-time engineers’ core function of monitoring. However, as real-time centers mature, there must be a focus on merging operational information with real-time streaming data to reduce communication lag time and raise the real-time engineer’s situational awareness at all times. Coupling business systems with real-time monitoring software will have an immediate impact on the entire process, reducing communication time and instantaneously syncing the real-time center with rig operations. A first step towards this goal is to provide the real-time monitoring software with the ability to pull in and merge operational data with streamed data from the wellsite. Operational data can then be viewed on demand and updated automatically as well as visualized together with the streamed data through predefined dashboards. Up-to-date operations information changes will be synchronized to the real-time monitoring systems and brought to the attention of the real-time engineers. As a result of the implementation, a step change has been observed in the situational awareness of real-time engineers, improving their interpretation of the current situation and their influence on operational changes. Finally, there remains a need to move towards digital information exchange between these systems in both directions to provide a more collaborative environment.

In EP industry, the dynamic behavior of well and process facilities is hardly considered. As a consequence, the full design capacity of the plant is under-utilized and at the same time extension projects/ de-bottlenecking are easily justified. Petroleum Development Oman (PDO) solution to this has been the creation of the process control and optimization team which continuously reviews and optimizes the dynamic performance of the production processes in view of improving the equipment/plant availability, enabling smoother operations, freeing-up hidden capacity and operating closer to equipment/plant constraints. The Process Control & Optimization (PCO) team has also been active in developing control innovation solution to different process dynamic behavior problems and input to engineering project for robust process control design and flawless start up. Typical control solutions have saved the company millions of dollars in waste elimination and in providing in house control solution to engineering design projects. Some of these intelligent solutions are a key enabler of successful execution of Well, Reservoir and Facilities Management (WRFM), Process Safety Management (PSM) and Production System Optimization (PSO). This paper presents the PCO journey in PDO with a look back to the 15 years of existence of the PCO team with main focus on people, process, technology and sustainability.

Eni Australia is operating the Blacktip gas field offshore Australia and Kitan oil field offshore East Timor. The main challenge was to manage these green fields remotely, with lean resources and strict deadlines covering tasks like data capture and acquisition, data validation, application integration and field analysis efficiently. The implications of the decisions made during the development of a green field are imperative to the optimization of reservoir production. Therefore, an integrated production decision support system was required for performance monitoring of asset health and optimizing production to meet the targets. This paper describes how these challenges were overcome at Eni Australia by centralizing the operations of both fields into a standardized production platform, providing a seamless data transfer from offshore assets to the onshore technical office and establishing the foundation towards a digital oilfield. The platform framework automates the process of acquisition, transfer, conditioning, aggregation and storage of production and operations data into a secure centralized data repository with an auditable amendment history. The production platform provides improved operational and reservoir visibility, which forms the basis for all subsequent analysis and underpins the engineering justification to support operational decisions. The current solution framework provides a multifunctioning system that can be expanded for future assets and fields as they come online by leveraging the investment in the existing system. All the domain experts, from production operations to reservoir engineering, will have the required information at their fingertips for collaborative decision making. Thus, a centralized production platform provides engineers with an improved field visibility for remote field management, proactive decision making and help them to strategically develop fields by optimizing production.

Marathon Oil operates several brownfields in the Rockies, most of which are approaching an operating life of 100 years. To optimize the production from these mature fields, Marathon Oil is implementing several technology upgrades under the banner of the digital oil field—using information technology innovations to better monitor, record and analyze field data for faster and more informed optimization decisions. One area receiving particular focus is the artificial lift method of electrical submersible pumps (ESPs). In 2010 Marathon Oil began installing downhole sensors in all ESP wells that were pulled for either a failure or a workover and downloading the data into an ESP real-time monitoring, diagnosis and analysis software system. The system brings intelligence to ESP operations by monitoring pump data from each well in real time, and collecting this data in a central location. The operator can then select from different software tools—also centrally located—to analyze the information, verify ESP operation within required parameters and if necessary, decide how to change the operating parameters to improve pump performance and boost production. The system also can be set with alarm capabilities to provide real-time notification of a problem. The intelligent capabilities of the system plugged into Marathon Oil’s digital oilfield architecture help field engineers work smarter and more efficiently. Instead of spending needless hours travelling from field to field to monitor pump performance, engineers are notified of problems early and receive instant verification of field performance. The system minimizes nonproductive time (NPT) and frees up the field crews to work on other projects designed to increase production. This paper provides several case studies that highlight through a digital oilfield solution how an intelligent ESP-optimization option is identifying problems early and extending the economic production life of Marathon Oil’s mature fields in the Rocky Mountain (Rockies) region of the United States (US). At the time of this paper, Marathon Oil installed downhole sensors in more than 430 of its 770 ESP wells, which are all presently being monitored via the ESP real-time monitoring and analysis program. Within this short period of real-time monitoring, Marathon Oil has realized production gains of over 700 Barrels of Oil per Day (BOPD) in one of the fields.